{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T07:05:25Z","timestamp":1779692725702,"version":"3.53.1"},"reference-count":114,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T00:00:00Z","timestamp":1772409600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.neunet.2026.108768","type":"journal-article","created":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T15:00:01Z","timestamp":1772377201000},"page":"108768","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["WEViT: weight-entangled vision transformers with class-specific attention for weakly supervised semantic segmentation"],"prefix":"10.1016","volume":"200","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1824-4831","authenticated-orcid":false,"given":"Narges","family":"Saeedizadeh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2169-4350","authenticated-orcid":false,"given":"Seyed Mohammad Jafar","family":"Jalali","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1765-935X","authenticated-orcid":false,"given":"Burhan","family":"Khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8851-1635","authenticated-orcid":false,"given":"Shady","family":"Mohamed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.108768_bib0001","series-title":"2024 13th Iranian\/3rd international machine vision and image processing conference (MVIP)","first-page":"1","article-title":"Leveraging swin transformer for local-to-global weakly supervised semantic segmentation","author":"Ahmadi","year":"2024"},{"key":"10.1016\/j.neunet.2026.108768_bib0002","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2209","article-title":"Weakly supervised learning of instance segmentation with inter-pixel relations","author":"Ahn","year":"2019"},{"key":"10.1016\/j.neunet.2026.108768_bib0003","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"4981","article-title":"Learning pixel-level semantic affinity with image-level supervision for weakly supervised semantic segmentation","author":"Ahn","year":"2018"},{"key":"10.1016\/j.neunet.2026.108768_bib0004","doi-asserted-by":"crossref","first-page":"3468","DOI":"10.24996\/ijs.2024.65.6.39","article-title":"Generating various deep dream images through maximizing the loss function of particular layers using inception-v3 and inception-resnet-v2 models","author":"Al-Khazraji","year":"2024","journal-title":"Iraqi Journal of Science"},{"issue":"8","key":"10.1016\/j.neunet.2026.108768_bib0005","doi-asserted-by":"crossref","first-page":"621","DOI":"10.32985\/ijeces.16.8.5","article-title":"Integrating squeeze-and-excitation network with pretrained CNN models for accurate plant disease detection","volume":"16","author":"Ali","year":"2025","journal-title":"International Journal of Electrical and Computer Engineering Systems"},{"key":"10.1016\/j.neunet.2026.108768_bib0006","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","first-page":"4253","article-title":"Single-stage semantic segmentation from image labels","author":"Araslanov","year":"2020"},{"key":"10.1016\/j.neunet.2026.108768_bib0007","series-title":"International conference on machine learning","first-page":"550","article-title":"Understanding and simplifying one-shot architecture search","author":"Bender","year":"2018"},{"key":"10.1016\/j.neunet.2026.108768_bib0008","unstructured":"Brock, A., Lim, T., Ritchie, J. M., & Weston, N. (2017). Smash: One-shot model architecture search through hypernetworks. arXiv: 1708.05344."},{"key":"10.1016\/j.neunet.2026.108768_bib0009","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","article-title":"Weakly-supervised semantic segmentation via sub-category exploration","author":"Chang","year":"2020"},{"key":"10.1016\/j.neunet.2026.108768_bib0010","series-title":"European conference on computer vision (ECCV)","first-page":"347","article-title":"Weakly supervised semantic segmentation with boundary exploration","author":"Chen","year":"2020"},{"issue":"4","key":"10.1016\/j.neunet.2026.108768_bib0011","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","volume":"40","author":"Chen","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.108768_bib0012","series-title":"Proceedings of the European conference on computer vision (ECCV)","first-page":"801","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"Chen","year":"2018"},{"key":"10.1016\/j.neunet.2026.108768_bib0013","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"12270","article-title":"Autoformer: Searching transformers for visual recognition","author":"Chen","year":"2021"},{"key":"10.1016\/j.neunet.2026.108768_bib0014","first-page":"8714","article-title":"Searching the search space of vision transformer","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108768_bib0015","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4288","article-title":"Self-supervised image-specific prototype exploration for weakly supervised semantic segmentation","author":"Chen","year":"2022"},{"key":"10.1016\/j.neunet.2026.108768_bib0016","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"3135","article-title":"Extracting class activation maps from non-discriminative features as well","author":"Chen","year":"2023"},{"key":"10.1016\/j.neunet.2026.108768_bib0017","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"410","article-title":"Lctr: On awakening the local continuity of transformer for weakly supervised object localization","volume":"vol. 36","author":"Chen","year":"2022"},{"key":"10.1016\/j.neunet.2026.108768_bib0018","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2219","article-title":"Attention-based dropout layer for weakly supervised object localization","author":"Choe","year":"2019"},{"key":"10.1016\/j.neunet.2026.108768_bib0019","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume":"34","author":"Chu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108768_bib0020","unstructured":"Chu, X., Tian, Z., Zhang, B., Wang, X., & Shen, C. (2021b). Conditional positional encodings for vision transformers. arXiv: 2102.10882."},{"key":"10.1016\/j.neunet.2026.108768_bib0021","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"12239","article-title":"Fairnas: Rethinking evaluation fairness of weight sharing neural architecture search","author":"Chu","year":"2021"},{"key":"10.1016\/j.neunet.2026.108768_bib0022","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops","first-page":"702","article-title":"Randaugment: Practical automated data augmentation with a reduced search space","author":"Cubuk","year":"2020"},{"key":"10.1016\/j.neunet.2026.108768_bib0023","series-title":"2009\u202fIEEE Conference on computer vision and pattern recognition","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.neunet.2026.108768_bib0024","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107140","article-title":"Context sensitive network for weakly-supervised fine-grained temporal action localization","volume":"185","author":"Dong","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108768_bib0025","unstructured":"Dosovitskiy, A. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv: 2010.11929."},{"key":"10.1016\/j.neunet.2026.108768_bib0026","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The pascal visual object classes (voc) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.108768_bib0027","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4283","article-title":"Learning integral objects with intra-class discriminator for weakly-supervised semantic segmentation","author":"Fan","year":"2020"},{"key":"10.1016\/j.neunet.2026.108768_bib0028","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"10762","article-title":"Cian: Cross-image affinity net for weakly supervised semantic segmentation","volume":"vol. 34","author":"Fan","year":"2020"},{"key":"10.1016\/j.neunet.2026.108768_bib0029","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"2886","article-title":"Ts-cam: Token semantic coupled attention map for weakly supervised object localization","author":"Gao","year":"2021"},{"key":"10.1016\/j.neunet.2026.108768_bib0030","series-title":"Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, proceedings, part XVI 16","first-page":"544","article-title":"Single path one-shot neural architecture search with uniform sampling","author":"Guo","year":"2020"},{"key":"10.1016\/j.neunet.2026.108768_bib0031","series-title":"2011 international conference on computer vision","first-page":"991","article-title":"Semantic contours from inverse detectors","author":"Hariharan","year":"2011"},{"key":"10.1016\/j.neunet.2026.108768_bib0032","unstructured":"Hendrycks, D., & Gimpel, K. (2016). Gaussian error linear units (gelus). arXiv: 1606.08415."},{"key":"10.1016\/j.neunet.2026.108768_bib0033","unstructured":"Hoffer, E., Ben-Nun, T., Hubara, I., Giladi, N., Hoefler, T., & Soudry, D. (2019). Augment your batch: Better training with larger batches. arXiv: 1901.09335."},{"key":"10.1016\/j.neunet.2026.108768_bib0034","article-title":"Self-erasing network for integral object attention","volume":"31","author":"Hou","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"4","key":"10.1016\/j.neunet.2026.108768_bib0035","article-title":"Mix-hybrid convolutional neural network framework with explainable artificial intelligence for fig leaves disease detection","volume":"18","author":"Jebur","year":"2025","journal-title":"International Journal of Intelligent Engineering & Systems"},{"key":"10.1016\/j.neunet.2026.108768_bib0036","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"11863","article-title":"Sp-nas: Serial-to-parallel backbone search for object detection","author":"Jiang","year":"2020"},{"issue":"10","key":"10.1016\/j.neunet.2026.108768_bib0037","doi-asserted-by":"crossref","first-page":"7062","DOI":"10.1109\/TPAMI.2021.3092573","article-title":"Online attention accumulation for weakly supervised semantic segmentation","volume":"44","author":"Jiang","year":"2021","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.108768_bib0038","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"16886","article-title":"L2g: A simple local-to-global knowledge transfer framework for weakly supervised semantic segmentation","author":"Jiang","year":"2022"},{"key":"10.1016\/j.neunet.2026.108768_bib0039","unstructured":"Ke, T.-W., Hwang, J.-J., & Yu, S. X. (2021). Universal weakly supervised segmentation by pixel-to-segment contrastive learning. arXiv: 2105.00957."},{"issue":"10s","key":"10.1016\/j.neunet.2026.108768_bib0040","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3505244","article-title":"Transformers in vision: A survey","volume":"54","author":"Khan","year":"2022","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"10.1016\/j.neunet.2026.108768_bib0041","series-title":"Computer vision\u2013ECCV 2016: 14th European conference, Amsterdam, the Netherlands, October 11\u201314, 2016, proceedings, part IV 14","first-page":"695","article-title":"Seed, expand and constrain: Three principles for weakly-supervised image segmentation","author":"Kolesnikov","year":"2016"},{"key":"10.1016\/j.neunet.2026.108768_bib0042","article-title":"Efficient inference in fully connected crfs with gaussian edge potentials","volume":"24","author":"Kr\u00e4henb\u00fchl","year":"2011","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108768_bib0043","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"3524","article-title":"Hide-and-seek: Forcing a network to be meticulous for weakly-supervised object and action localization","author":"Kumar Singh","year":"2017"},{"key":"10.1016\/j.neunet.2026.108768_bib0044","series-title":"Proceedings of the international conference on computer vision (ICCV)","first-page":"6994","article-title":"Unlocking the potential of ordinary classifier: Class-specific adversarial erasing framework for weakly supervised semantic segmentation","author":"Kweon","year":"2021"},{"key":"10.1016\/j.neunet.2026.108768_bib0045","series-title":"Advances in neural information processing systems (NeurIPS)","first-page":"27408","article-title":"Reducing information bottleneck for weakly supervised semantic segmentation","volume":"vol. 34","author":"Lee","year":"2021"},{"key":"10.1016\/j.neunet.2026.108768_bib0046","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4071","article-title":"Anti-adversarially manipulated attributions for weakly and semi-supervised semantic segmentation","author":"Lee","year":"2021"},{"key":"10.1016\/j.neunet.2026.108768_bib0047","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"16897","article-title":"Weakly supervised semantic segmentation using out-of-distribution data","author":"Lee","year":"2022"},{"issue":"7","key":"10.1016\/j.neunet.2026.108768_bib0048","doi-asserted-by":"crossref","first-page":"752","DOI":"10.1587\/transinf.2024EDP7125","article-title":"Structural relation multi-class token transformer for weakly supervised semantic segmentation","volume":"E108.D","author":"Peng","year":"2025","journal-title":"IEICE Transactions on Information and Systems"},{"key":"10.1016\/j.neunet.2026.108768_bib0049","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4330","article-title":"Threshold matters in wsss: Manipulating the activation for the robust and accurate segmentation model against thresholds","author":"Lee","year":"2022"},{"key":"10.1016\/j.neunet.2026.108768_bib0050","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5495","article-title":"Railroad is not a train: Saliency as pseudo-pixel supervision for weakly supervised semantic segmentation","author":"Lee","year":"2021"},{"key":"10.1016\/j.neunet.2026.108768_bib0051","unstructured":"Lei Ba, J., Kiros, J. R., & Hinton, G. E. (2016). Layer normalization. ArXiv e-prints, arXiv\u20131607."},{"key":"10.1016\/j.neunet.2026.108768_bib0052","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"12281","article-title":"Bossnas: Exploring hybrid cnn-transformers with block-wisely self-supervised neural architecture search","author":"Li","year":"2021"},{"key":"10.1016\/j.neunet.2026.108768_bib0053","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"16856","article-title":"Towards noiseless object contours for weakly supervised semantic segmentation","author":"Li","year":"2022"},{"key":"10.1016\/j.neunet.2026.108768_bib0054","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"9215","article-title":"Tell me where to look: Guided attention inference network","author":"Li","year":"2018"},{"key":"10.1016\/j.neunet.2026.108768_bib0055","series-title":"Uncertainty in artificial intelligence","first-page":"367","article-title":"Random search and reproducibility for neural architecture search","author":"Li","year":"2020"},{"key":"10.1016\/j.neunet.2026.108768_bib0056","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2023.103800","article-title":"TransCAM: Transformer attention-based CAM refinement for weakly supervised semantic segmentation","volume":"92","author":"Li","year":"2023","journal-title":"Journal of Visual Communication and Image Representation"},{"key":"10.1016\/j.neunet.2026.108768_bib0057","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1016\/j.neunet.2023.09.040","article-title":"Eqnas: Evolutionary quantum neural architecture search for image classification","volume":"168","author":"Li","year":"2023","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108768_bib0058","unstructured":"Liao, Y.-L., Karaman, S., & Sze, V. (2021). Searching for efficient multi-stage vision transformers. arXiv: 2109.00642."},{"key":"10.1016\/j.neunet.2026.108768_bib0059","series-title":"Computer vision\u2013ECCV 2014: 13th European conference, Zurich, Switzerland, September 6\u201312, 2014, proceedings, part v 13","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.neunet.2026.108768_bib0060","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"15305","article-title":"Clip is also an efficient segmenter: A text-driven approach for weakly supervised semantic segmentation","author":"Lin","year":"2023"},{"issue":"3","key":"10.1016\/j.neunet.2026.108768_bib0061","doi-asserted-by":"crossref","DOI":"10.1111\/exsy.13495","article-title":"Wegformer: Transformers for weakly supervised semantic segmentation","volume":"41","author":"Liu","year":"2024","journal-title":"Expert Systems"},{"key":"10.1016\/j.neunet.2026.108768_bib0062","series-title":"Proceedings of the european conference on computer vision (ECCV)","first-page":"19","article-title":"Progressive neural architecture search","author":"Liu","year":"2018"},{"key":"10.1016\/j.neunet.2026.108768_bib0063","unstructured":"Liu, H., Simonyan, K., & Yang, Y. (2018b). Darts: Differentiable architecture search. arXiv: 1806.09055."},{"issue":"6","key":"10.1016\/j.neunet.2026.108768_bib0064","doi-asserted-by":"crossref","first-page":"7478","DOI":"10.1109\/TNNLS.2022.3227717","article-title":"A survey of visual transformers","volume":"35","author":"Liu","year":"2023","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.108768_bib0065","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106892","article-title":"Weakly supervised label learning flows","volume":"182","author":"Lu","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108768_bib0066","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"11717","article-title":"Learning saliency-free model with generic features for weakly-supervised semantic segmentation","volume":"vol. 34","author":"Luo","year":"2020"},{"key":"10.1016\/j.neunet.2026.108768_bib0067","doi-asserted-by":"crossref","first-page":"553","DOI":"10.1016\/j.neunet.2021.09.002","article-title":"Disturbance-immune weight sharing for neural architecture search","volume":"144","author":"Niu","year":"2021","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108768_bib0068","series-title":"Proceedings of the IEEE\/cvf international conference on computer vision","first-page":"377","article-title":"Scalable vision transformers with hierarchical pooling","author":"Pan","year":"2021"},{"key":"10.1016\/j.neunet.2026.108768_bib0069","unstructured":"Park, W., Kim, C., Kim, J., Kim, D., Kim, T., Song, M.-S., & Park, J. (2024). Cobra: Complementary branch fusing class and semantic knowledge for robust weakly supervised semantic segmentation. arXiv: 2403.08801."},{"key":"10.1016\/j.neunet.2026.108768_bib0070","series-title":"International conference on machine learning","first-page":"4095","article-title":"Efficient neural architecture search via parameters sharing","author":"Pham","year":"2018"},{"issue":"2","key":"10.1016\/j.neunet.2026.108768_bib0071","doi-asserted-by":"crossref","first-page":"2117","DOI":"10.1609\/aaai.v36i2.20108","article-title":"Activation modulation and recalibration scheme for weakly supervised semantic segmentation","volume":"36","author":"Qin","year":"2022","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.1016\/j.neunet.2026.108768_bib0072","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"4780","article-title":"Regularized evolution for image classifier architecture search","volume":"vol. 33","author":"Real","year":"2019"},{"key":"10.1016\/j.neunet.2026.108768_bib0073","series-title":"European conference on computer vision (ECCV)","article-title":"Max pooling with vision transformers reconciles class and shape in weakly supervised semantic segmentation","author":"Rossetti","year":"2022"},{"key":"10.1016\/j.neunet.2026.108768_bib0074","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"16846","article-title":"Learning affinity from attention: End-to-end weakly-supervised semantic segmentation with transformers","author":"Ru","year":"2022"},{"key":"10.1016\/j.neunet.2026.108768_bib0075","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"3093","article-title":"Token contrast for weakly-supervised semantic segmentation","author":"Ru","year":"2023"},{"key":"10.1016\/j.neunet.2026.108768_bib0076","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111966","article-title":"A new optimization approach based on neural architecture search to enhance deep u-net for efficient road segmentation","volume":"296","author":"Saeedizadeh","year":"2024","journal-title":"Knowledge-Based Systems"},{"issue":"4","key":"10.1016\/j.neunet.2026.108768_bib0077","doi-asserted-by":"crossref","DOI":"10.1111\/exsy.70020","article-title":"Cutting-edge deep learning methods for image-based object detection in autonomous driving: In-depth survey","volume":"42","author":"Saeedizadeh","year":"2025","journal-title":"Expert Systems"},{"key":"10.1016\/j.neunet.2026.108768_bib0078","series-title":"International conference on machine learning","first-page":"5877","article-title":"The evolved transformer","author":"So","year":"2019"},{"key":"10.1016\/j.neunet.2026.108768_bib0079","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"7004","article-title":"Context decoupling augmentation for weakly supervised semantic segmentation","author":"Su","year":"2021"},{"key":"10.1016\/j.neunet.2026.108768_bib0080","series-title":"Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, proceedings, part II 16","first-page":"347","article-title":"Mining cross-image semantics for weakly supervised semantic segmentation","author":"Sun","year":"2020"},{"key":"10.1016\/j.neunet.2026.108768_bib0081","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","first-page":"7283","article-title":"Ecs-net: Improving weakly supervised semantic segmentation by using connections between class activation maps","author":"Sun","year":"2021"},{"key":"10.1016\/j.neunet.2026.108768_bib0082","unstructured":"Sun, W., Zhang, J., Liu, Z., Zhong, Y., & Barnes, N. (2021b). Getam: Gradient-weighted element-wise transformer attention map for weakly-supervised semantic segmentation. arXiv: 2112.02841."},{"key":"10.1016\/j.neunet.2026.108768_bib0083","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"826","article-title":"All-pairs consistency learning forweakly supervised semantic segmentation","author":"Sun","year":"2023"},{"key":"10.1016\/j.neunet.2026.108768_bib0084","series-title":"International conference on machine learning","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2021"},{"key":"10.1016\/j.neunet.2026.108768_bib0085","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is All You Need. In Advances in Neural Information Processing Systems, 30."},{"key":"10.1016\/j.neunet.2026.108768_bib0086","series-title":"International conference on machine learning","first-page":"35642","article-title":"Prenas: Preferred one-shot learning towards efficient neural architecture search","author":"Wang","year":"2023"},{"key":"10.1016\/j.neunet.2026.108768_bib0087","doi-asserted-by":"crossref","unstructured":"Wang, H., Wu, Z., Liu, Z., Cai, H., Zhu, L., Gan, C., & Han, S. (2020a). Hat: Hardware-aware transformers for efficient natural language processing. arXiv: 2005.14187.","DOI":"10.18653\/v1\/2020.acl-main.686"},{"key":"10.1016\/j.neunet.2026.108768_bib0088","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"12275","article-title":"Self-supervised equivariant attention mechanism for weakly supervised semantic segmentation","author":"Wang","year":"2020"},{"key":"10.1016\/j.neunet.2026.108768_bib0089","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"1568","article-title":"Object region mining with adversarial erasing: A simple classification to semantic segmentation approach","author":"Wei","year":"2017"},{"key":"10.1016\/j.neunet.2026.108768_bib0090","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"7268","article-title":"Revisiting dilated convolution: A simple approach for weakly-and semi-supervised semantic segmentation","author":"Wei","year":"2018"},{"key":"10.1016\/j.neunet.2026.108768_bib0091","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10734","article-title":"Fbnet: Hardware-aware efficient convnet design via differentiable neural architecture search","author":"Wu","year":"2019"},{"key":"10.1016\/j.neunet.2026.108768_bib0092","series-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision","first-page":"862","article-title":"Masked collaborative contrast for weakly supervised semantic segmentation","author":"Wu","year":"2024"},{"key":"10.1016\/j.neunet.2026.108768_bib0093","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"22","article-title":"Cvt: Introducing convolutions to vision transformers","author":"Wu","year":"2021"},{"key":"10.1016\/j.neunet.2026.108768_bib0094","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"16765","article-title":"Embedded discriminative attention mechanism for weakly supervised semantic segmentation","author":"Wu","year":"2021"},{"key":"10.1016\/j.neunet.2026.108768_bib0095","doi-asserted-by":"crossref","unstructured":"Wu, W., Dai, T., Chen, Z., Huang, X., Ma, F., & Xiao, J. (2024b). Apc: Adaptive patch contrast for weakly supervised semantic segmentation. arXiv: 2407.10649.","DOI":"10.2139\/ssrn.5033159"},{"key":"10.1016\/j.neunet.2026.108768_bib0096","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4483","article-title":"Clims: Cross language image matching for weakly supervised semantic segmentation","author":"Xie","year":"2022"},{"issue":"12","key":"10.1016\/j.neunet.2026.108768_bib0097","doi-asserted-by":"crossref","first-page":"8380","DOI":"10.1109\/TPAMI.2024.3404422","article-title":"Mctformer+: Multi-class token transformer for weakly supervised semantic segmentation","volume":"46","author":"Xu","year":"2024","journal-title":"IEEE Transactions on Pattern Analysis and Machine intelligence"},{"key":"10.1016\/j.neunet.2026.108768_bib0098","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"6984","article-title":"Leveraging auxiliary tasks with affinity learning for weakly supervised semantic segmentation","author":"Xu","year":"2021"},{"key":"10.1016\/j.neunet.2026.108768_bib0099","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4310","article-title":"Multi-class token transformer for weakly supervised semantic segmentation","author":"Xu","year":"2022"},{"key":"10.1016\/j.neunet.2026.108768_bib0100","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"19596","article-title":"Learning multi-modal class-specific tokens for weakly supervised dense object localization","author":"Xu","year":"2023"},{"key":"10.1016\/j.neunet.2026.108768_bib0101","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2623","article-title":"Non-salient region object mining for weakly supervised semantic segmentation","author":"Yao","year":"2021"},{"key":"10.1016\/j.neunet.2026.108768_bib0102","series-title":"Computer vision \u2013 ECCV 2022: 17th European conference, Tel Aviv, Israel, October 23\u201327, 2022, proceedings, part XXIX","first-page":"326","article-title":"Adversarial erasing framework via triplet with gated pyramid pooling layer for weakly supervised semantic segmentation","author":"Yoon","year":"2022"},{"key":"10.1016\/j.neunet.2026.108768_bib0103","doi-asserted-by":"crossref","unstructured":"Yu, J., Jin, P., Liu, H., Bender, G., Kindermans, P.-J., Tan, M., & Le, Q. (2020). Bignas: Scaling up neural architecture search with big single-stage models. (pp. 702\u2013717).","DOI":"10.1007\/978-3-030-58571-6_41"},{"key":"10.1016\/j.neunet.2026.108768_bib0104","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"558","article-title":"Tokens-to-token vit: Training vision transformers from scratch on imagenet","author":"Yuan","year":"2021"},{"key":"10.1016\/j.neunet.2026.108768_bib0105","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"6023","article-title":"Cutmix: Regularization strategy to train strong classifiers with localizable features","author":"Yun","year":"2019"},{"key":"10.1016\/j.neunet.2026.108768_bib0106","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"12765","article-title":"Reliability does matter: An end-to-end weakly supervised semantic segmentation approach","volume":"vol. 34","author":"Zhang","year":"2020"},{"key":"10.1016\/j.neunet.2026.108768_bib0107","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","first-page":"14290","article-title":"Context decoupling augmentation for weakly supervised semantic segmentation","author":"Zhang","year":"2021"},{"key":"10.1016\/j.neunet.2026.108768_bib0108","series-title":"Advances in neural information processing systems (NeurIPS)","first-page":"655","article-title":"Causal intervention for weakly-supervised semantic segmentation","volume":"vol. 33","author":"Zhang","year":"2020"},{"key":"10.1016\/j.neunet.2026.108768_bib0109","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"7242","article-title":"Complementary patch for weakly supervised semantic segmentation","author":"Zhang","year":"2021"},{"key":"10.1016\/j.neunet.2026.108768_bib0110","doi-asserted-by":"crossref","unstructured":"Zhang, H. (2017). Mixup: Beyond empirical risk minimization. arXiv: 1710.09412.","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"10.1016\/j.neunet.2026.108768_bib0111","series-title":"Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, proceedings, part XXII 16","first-page":"663","article-title":"Splitting vs. merging: Mining object regions with discrepancy and intersection loss for weakly supervised semantic segmentation","author":"Zhang","year":"2020"},{"key":"10.1016\/j.neunet.2026.108768_bib0112","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"2921","article-title":"Learning deep features for discriminative localization","author":"Zhou","year":"2016"},{"key":"10.1016\/j.neunet.2026.108768_bib0113","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4299","article-title":"Regional semantic contrast and aggregation for weakly supervised semantic segmentation","author":"Zhou","year":"2022"},{"key":"10.1016\/j.neunet.2026.108768_bib0114","unstructured":"Zhu, L., Li, Y., Fang, J., Liu, Y., Xin, H., Liu, W., & Wang, X. (2023). Weaktr: Exploring plain vision transformer for weakly-supervised semantic segmentation. arXiv: 2304.01184."}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026002303?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026002303?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T06:43:43Z","timestamp":1779691423000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026002303"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":114,"alternative-id":["S0893608026002303"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108768","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"WEViT: weight-entangled vision transformers with class-specific attention for weakly supervised semantic segmentation","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108768","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"108768"}}