{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T16:38:25Z","timestamp":1792514305258,"version":"4.5.0"},"reference-count":96,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T00:00:00Z","timestamp":1725494400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T00:00:00Z","timestamp":1725494400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1007\/s11263-024-02224-2","type":"journal-article","created":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T07:02:20Z","timestamp":1725519740000},"page":"1085-1105","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":56,"title":["WeakCLIP: Adapting CLIP for Weakly-Supervised Semantic Segmentation"],"prefix":"10.1007","volume":"133","author":[{"given":"Lianghui","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6732-7823","authenticated-orcid":false,"given":"Xinggang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiapei","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianheng","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingyue","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dingwen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junwei","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,5]]},"reference":[{"key":"2224_CR1","doi-asserted-by":"publisher","unstructured":"Ahn, J., & Kwak, S. (2018). Learning pixel-level semantic affinity with image-level supervision for weakly supervised semantic segmentation. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR.2018.00523","DOI":"10.1109\/CVPR.2018.00523"},{"key":"2224_CR2","doi-asserted-by":"publisher","unstructured":"Ahn, J., Cho, S., & Kwak, S. (2019). Weakly supervised learning of instance segmentation with inter-pixel relations. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR.2019.00231","DOI":"10.1109\/CVPR.2019.00231"},{"key":"2224_CR3","doi-asserted-by":"crossref","unstructured":"Bearman, A., Russakovsky, O., Ferrari, V., Fei-Fei, L. (2016). What\u2019s the point: Semantic segmentation with point supervision. In: Proc. of ECCV.","DOI":"10.1007\/978-3-319-46478-7_34"},{"key":"2224_CR4","doi-asserted-by":"publisher","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021). Emerging properties in self-supervised vision transformers. In: Proc. of ICCV. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00951","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"2224_CR5","doi-asserted-by":"publisher","unstructured":"Carreira, J., & Zisserman, A. (2017). Quo vadis, action recognition? A new model and the kinetics dataset. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR.2017.502","DOI":"10.1109\/CVPR.2017.502"},{"key":"2224_CR6","doi-asserted-by":"publisher","unstructured":"Chang, Y., Wang, Q., Hung, W., Piramuthu, R., Tsai, Y., & Yang, M. (2020). Weakly-supervised semantic segmentation via sub-category exploration. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00901","DOI":"10.1109\/CVPR42600.2020.00901"},{"key":"2224_CR7","unstructured":"Chen, L., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A. L. (2015) Semantic image segmentation with deep convolutional nets and fully connected crfs. In: Proc. of ICLR."},{"key":"2224_CR8","doi-asserted-by":"crossref","unstructured":"Chen, L., Wu, W., Fu, C., Han, X., Zhang, Y. (2020a). Weakly supervised semantic segmentation with boundary exploration. In: Proc. of ECCV.","DOI":"10.1007\/978-3-030-58574-7_21"},{"issue":"4","key":"2224_CR9","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L. C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2017). Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. TPAMI, 40(4), 834\u2013848.","journal-title":"TPAMI"},{"key":"2224_CR10","doi-asserted-by":"publisher","unstructured":"Chen, Q., Yang, L., Lai, J., & Xie, X. (2022). Self-supervised image-specific prototype exploration for weakly supervised semantic segmentation. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00425","DOI":"10.1109\/CVPR52688.2022.00425"},{"key":"2224_CR11","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G. E. (2020b). A simple framework for contrastive learning of visual representations. In: Proc. of ICML."},{"key":"2224_CR12","unstructured":"Chen, T., Mai, Z., Li, R., Chao, W. l. (2023). Segment anything model (sam) enhanced pseudo labels for weakly supervised semantic segmentation. Proc of NeurIPS-W."},{"key":"2224_CR13","doi-asserted-by":"publisher","unstructured":"Chen, Z., Wang, T., Wu, X., Hua, X., Zhang, H., & Sun, Q. (2022). Class re-activation maps for weakly-supervised semantic segmentation. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00104","DOI":"10.1109\/CVPR52688.2022.00104"},{"key":"2224_CR14","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Qiao, P., Li, K., Li, S., Wei, P., Ji, X., Yuan, L., Liu, C., Chen, J. (2023). Out-of-candidate rectification for weakly supervised semantic segmentation. In: Proc. of CVPR.","DOI":"10.1109\/CVPR52729.2023.02267"},{"key":"2224_CR15","doi-asserted-by":"publisher","unstructured":"Dai, J., He, K., & Sun, J. (2015). Boxsup: Exploiting bounding boxes to supervise convolutional networks for semantic segmentation. In: Proc. of ICCV. https:\/\/doi.org\/10.1109\/ICCV.2015.191","DOI":"10.1109\/ICCV.2015.191"},{"key":"2224_CR16","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N. (2021). An image is worth 16 x 16 words: Transformers for image recognition at scale. In: Proc. of ICLR."},{"key":"2224_CR17","doi-asserted-by":"publisher","unstructured":"Du, Y., Fu, Z., Liu, Q., & Wang, Y. (2022). Weakly supervised semantic segmentation by pixel-to-prototype contrast. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00428","DOI":"10.1109\/CVPR52688.2022.00428"},{"key":"2224_CR18","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2010). The pascal visual object classes (voc) challenge. International Journal of Computer Vision, 88, 303\u2013338.","journal-title":"International Journal of Computer Vision"},{"key":"2224_CR19","doi-asserted-by":"publisher","unstructured":"Fan, J., Zhang, Z., Song, C., & Tan, T. (2020). Learning integral objects with intra-class discriminator for weakly-supervised semantic segmentation. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00434","DOI":"10.1109\/CVPR42600.2020.00434"},{"key":"2224_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11432-020-3065-4","volume":"64","author":"J Feng","year":"2021","unstructured":"Feng, J., Wang, X., & Liu, W. (2021). Deep graph cut network for weakly-supervised semantic segmentation. Science China Information Sciences, 64, 1\u201312.","journal-title":"Science China Information Sciences"},{"issue":"2","key":"2224_CR21","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/s11263-023-01891-x","volume":"132","author":"P Gao","year":"2024","unstructured":"Gao, P., Geng, S., Zhang, R., Ma, T., Fang, R., Zhang, Y., Li, H., & Qiao, Y. (2024). Clip-adapter: Better vision-language models with feature adapters. International Journal of Computer Vision, 132(2), 581\u2013595.","journal-title":"International Journal of Computer Vision"},{"key":"2224_CR22","doi-asserted-by":"publisher","unstructured":"Hariharan, B., Arbelaez, P., Bourdev, L. D., Maji, S., & Malik, J. (2011). Semantic contours from inverse detectors. In: Proc. of ICCV. https:\/\/doi.org\/10.1109\/ICCV.2011.6126343","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"2224_CR23","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"2224_CR24","doi-asserted-by":"publisher","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. B. (2020). Momentum contrast for unsupervised visual representation learning. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00975","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"2224_CR25","unstructured":"Houlsby, N., Giurgiu, A., Jastrzebski, S., Morrone, B., De\u00a0Laroussilhe, Q., Gesmundo, A., Attariyan, M., Gelly, S. (2019). Parameter-efficient transfer learning for NLP. In: Proc. of ICML."},{"key":"2224_CR26","doi-asserted-by":"publisher","unstructured":"Hoyer, L., Dai, D., & Gool, L. V. (2022). Daformer: Improving network architectures and training strategies for domain-adaptive semantic segmentation. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00969","DOI":"10.1109\/CVPR52688.2022.00969"},{"key":"2224_CR27","doi-asserted-by":"publisher","unstructured":"Huang, Z., Wang, X., Wang, J., Liu, W., & Wang, J. (2018). Weakly-supervised semantic segmentation network with deep seeded region growing. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR.2018.00733","DOI":"10.1109\/CVPR.2018.00733"},{"key":"2224_CR28","doi-asserted-by":"publisher","unstructured":"Jiang, P., Hou, Q., Cao, Y., Cheng, M., Wei, Y., & Xiong, H. (2019). Integral object mining via online attention accumulation. In: Proc. of ICCV. https:\/\/doi.org\/10.1109\/ICCV.2019.00216","DOI":"10.1109\/ICCV.2019.00216"},{"key":"2224_CR29","doi-asserted-by":"publisher","unstructured":"Jiang, P., Yang, Y., Hou, Q., & Wei, Y. (2022). L2G: A simple local-to-global knowledge transfer framework for weakly supervised semantic segmentation. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR52688.2022.01638","DOI":"10.1109\/CVPR52688.2022.01638"},{"key":"2224_CR30","doi-asserted-by":"publisher","unstructured":"Khoreva, A., Benenson, R., Hosang, J. H., Hein, M., & Schiele, B. (2017). Simple does it: Weakly supervised instance and semantic segmentation. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR.2017.181","DOI":"10.1109\/CVPR.2017.181"},{"key":"2224_CR31","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland C, Gustafson L, Xiao T, Whitehead S, Berg AC, Lo WY, et al. (2023) Segment anything. In: Proc. of ICCV.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"2224_CR32","doi-asserted-by":"crossref","unstructured":"Kolesnikov, A., Lampert, C. H. (2016). Seed, expand and constrain: Three principles for weakly-supervised image segmentation. In: Proc. of ECCV.","DOI":"10.1007\/978-3-319-46493-0_42"},{"key":"2224_CR33","unstructured":"Kr\u00e4henb\u00fchl, P., Koltun, V. (2011). Efficient inference in fully connected crfs with gaussian edge potentials. In: Proc. of NeurIPS."},{"key":"2224_CR34","doi-asserted-by":"publisher","unstructured":"Kweon, H., Yoon, S., Kim, H., Park, D., & Yoon, K. (2021). Unlocking the potential of ordinary classifier: Class-specific adversarial erasing framework for weakly supervised semantic segmentation. In: Proc. of ICCV. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00691","DOI":"10.1109\/ICCV48922.2021.00691"},{"key":"2224_CR35","doi-asserted-by":"crossref","unstructured":"Kweon, H., Yoon, S.H., Yoon, K. J. (2023). Weakly supervised semantic segmentation via adversarial learning of classifier and reconstructor. In: Proc. of CVPR.","DOI":"10.1109\/CVPR52729.2023.01090"},{"key":"2224_CR36","doi-asserted-by":"publisher","unstructured":"Lee, J., Kim, E., Lee, S., Lee, J., & Yoon, S. (2019). Ficklenet: Weakly and semi-supervised semantic image segmentation using stochastic inference. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR.2019.00541","DOI":"10.1109\/CVPR.2019.00541"},{"key":"2224_CR37","doi-asserted-by":"publisher","unstructured":"Lee, J., Kim, E., Lee, S., Lee, J., & Yoon, S. (2019). Frame-to-frame aggregation of active regions in web videos for weakly supervised semantic segmentation. In: Proc. of ICCV. https:\/\/doi.org\/10.1109\/ICCV.2019.00691","DOI":"10.1109\/ICCV.2019.00691"},{"key":"2224_CR38","unstructured":"Lee, J., Choi, J., Mok, J., Yoon, S. (2021a). Reducing information bottleneck for weakly supervised semantic segmentation. In: Proc. of NeurIPS."},{"key":"2224_CR39","doi-asserted-by":"publisher","unstructured":"Lee, J., Kim, E., & Yoon, S. (2021). Anti-adversarially manipulated attributions for weakly and semi-supervised semantic segmentation. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00406","DOI":"10.1109\/CVPR46437.2021.00406"},{"key":"2224_CR40","doi-asserted-by":"publisher","unstructured":"Lee, J., Yi, J., Shin, C., & Yoon, S. (2021). BBAM: bounding box attribution map for weakly supervised semantic and instance segmentation. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00267","DOI":"10.1109\/CVPR46437.2021.00267"},{"key":"2224_CR41","doi-asserted-by":"publisher","unstructured":"Lee, J., Oh, S. J., Yun, S., Choe, J., Kim, E., & Yoon, S. (2022). Weakly supervised semantic segmentation using out-of-distribution data. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR52688.2022.01639","DOI":"10.1109\/CVPR52688.2022.01639"},{"key":"2224_CR42","doi-asserted-by":"publisher","unstructured":"Lee, M., Kim, D., & Shim, H. (2022). Threshold matters in WSSS: manipulating the activation for the robust and accurate segmentation model against thresholds. Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00429","DOI":"10.1109\/CVPR52688.2022.00429"},{"key":"2224_CR43","doi-asserted-by":"publisher","unstructured":"Lee, S., Lee, M., Lee, J., & Shim, H. (2021). Railroad is not a train: Saliency as pseudo-pixel supervision for weakly supervised semantic segmentation. Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00545","DOI":"10.1109\/CVPR46437.2021.00545"},{"key":"2224_CR44","doi-asserted-by":"publisher","unstructured":"Lei, J., Li, L., Zhou, L., Gan, Z., Berg, T. L., Bansal, M., & Liu, J. (2021). Less is more: Clipbert for video-and-language learning via sparse sampling. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00725","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"2224_CR45","doi-asserted-by":"publisher","unstructured":"Li, J., Fan, J., & Zhang, Z. (2022). Towards noiseless object contours for weakly supervised semantic segmentation. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR52688.2022.01635","DOI":"10.1109\/CVPR52688.2022.01635"},{"key":"2224_CR46","doi-asserted-by":"publisher","unstructured":"Li, Y., Kuang, Z., Liu, L., Chen, Y., & Zhang, W. (2021). Pseudo-mask matters in weakly-supervised semantic segmentation. In: Proc. of ICCV. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00688","DOI":"10.1109\/ICCV48922.2021.00688"},{"key":"2224_CR47","doi-asserted-by":"crossref","unstructured":"Li, Y., Duan, Y., Kuang, Z., Chen, Y., Zhang, W., Li, X. (2022b). Uncertainty estimation via response scaling for pseudo-mask noise mitigation in weakly-supervised semantic segmentation. In: Proc. of AAAI.","DOI":"10.1609\/aaai.v36i2.20034"},{"key":"2224_CR48","doi-asserted-by":"publisher","unstructured":"Lin, D., Dai, J., Jia, J., He, K., & Sun, J. (2016). Scribblesup: Scribble-supervised convolutional networks for semantic segmentation. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR.2016.344","DOI":"10.1109\/CVPR.2016.344"},{"key":"2224_CR49","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C. L. (2014). Microsoft coco: Common objects in context. In: Proc. of ECCV.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2224_CR50","doi-asserted-by":"crossref","unstructured":"Lin, Y., Chen, M., Wang, W., Wu, B., Li, K., Lin, B., Liu, H., He. X. (2023). Clip is also an efficient segmenter: A text-driven approach for weakly supervised semantic segmentation. In: Proc. of CVPR.","DOI":"10.1109\/CVPR52729.2023.01469"},{"key":"2224_CR51","unstructured":"Loshchilov, I., Hutter, F. (2019). Decoupled weight decay regularization. In: Proc. of ICLR."},{"key":"2224_CR52","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S. (2019). Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Proc. of NeurIPS."},{"key":"2224_CR53","doi-asserted-by":"publisher","unstructured":"Pathak, D., Kr\u00e4henb\u00fchl, P., & Darrell, T. (2015). Constrained convolutional neural networks for weakly supervised segmentation. In: Proc. of ICCV. https:\/\/doi.org\/10.1109\/ICCV.2015.209","DOI":"10.1109\/ICCV.2015.209"},{"key":"2224_CR54","doi-asserted-by":"publisher","unstructured":"Pinheiro, P. H. O., & Collobert, R. (2015). From image-level to pixel-level labeling with convolutional networks. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR.2015.7298780","DOI":"10.1109\/CVPR.2015.7298780"},{"key":"2224_CR55","doi-asserted-by":"crossref","unstructured":"Qin, J., Wu, J., Xiao, X., Li, L., Wang, X. (2022). Activation modulation and recalibration scheme for weakly supervised semantic segmentation. In: Proc. of AAAI.","DOI":"10.1609\/aaai.v36i2.20108"},{"key":"2224_CR56","unstructured":"Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., Sutskever, I. (2021). Learning transferable visual models from natural language supervision. In: Proc. of ICML."},{"key":"2224_CR57","doi-asserted-by":"crossref","unstructured":"Rao, Y., Zhao, W., Chen, G., Tang, Y., Zhu, Z., Huang, G., Zhou, J., Lu, J. (2022). Denseclip: Language-guided dense prediction with context-aware prompting. In: Proc. of CVPR.","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"2224_CR58","doi-asserted-by":"crossref","unstructured":"Rong, S., Tu, B., Wang, Z., Li, J. (2023). Boundary-enhanced co-training for weakly supervised semantic segmentation. In: Proc. of CVPR.","DOI":"10.1109\/CVPR52729.2023.01875"},{"key":"2224_CR59","doi-asserted-by":"crossref","unstructured":"Rossetti S, Zappia D, Sanzari M, Schaerf M, Pirri F (2022) Max pooling with vision transformers reconciles class and shape in weakly supervised semantic segmentation. In: Proc. of ECCV","DOI":"10.1007\/978-3-031-20056-4_26"},{"issue":"4","key":"2224_CR60","doi-asserted-by":"publisher","first-page":"1127","DOI":"10.1007\/s11263-022-01586-9","volume":"130","author":"L Ru","year":"2022","unstructured":"Ru, L., Du, B., Zhan, Y., & Wu, C. (2022). Weakly-supervised semantic segmentation with visual words learning and hybrid pooling. International Journal of Computer Vision, 130(4), 1127\u20131144.","journal-title":"International Journal of Computer Vision"},{"key":"2224_CR61","doi-asserted-by":"crossref","unstructured":"Ru, L., Zheng, H., Zhan, Y., Du, B. (2023). Token contrast for weakly-supervised semantic segmentation. In: Proc. of CVPR.","DOI":"10.1109\/CVPR52729.2023.00302"},{"key":"2224_CR62","doi-asserted-by":"publisher","unstructured":"Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proc. of ICCV. https:\/\/doi.org\/10.1109\/ICCV.2017.74","DOI":"10.1109\/ICCV.2017.74"},{"key":"2224_CR63","doi-asserted-by":"crossref","unstructured":"Shen, T., Lin, G., Liu, L., Shen, C., Reid, I. (2017). Weakly supervised semantic segmentation based on co-segmentation. In: Proc. of BMVC.","DOI":"10.5244\/C.31.17"},{"key":"2224_CR64","doi-asserted-by":"publisher","unstructured":"Song, C., Huang, Y., Ouyang, W., & Wang, L. (2019). Box-driven class-wise region masking and filling rate guided loss for weakly supervised semantic segmentation. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR.2019.00325","DOI":"10.1109\/CVPR.2019.00325"},{"key":"2224_CR65","doi-asserted-by":"publisher","unstructured":"Strudel, R., Pinel, R. G., Laptev, I., & Schmid, C. (2021). Segmenter: Transformer for semantic segmentation. In: Proc. of ICCV. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00717","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"2224_CR66","unstructured":"Su, W., Zhu, X., Cao, Y., Li, B., Lu, L., Wei, F., Dai, J. (2020). VL-BERT: pre-training of generic visual-linguistic representations. In: Proc. of ICLR."},{"key":"2224_CR67","doi-asserted-by":"publisher","unstructured":"Su, Y., Sun, R., Lin, G., & Wu, Q. (2021). Context decoupling augmentation for weakly supervised semantic segmentation. In: Proc. of ICCV. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00692","DOI":"10.1109\/ICCV48922.2021.00692"},{"key":"2224_CR68","doi-asserted-by":"publisher","unstructured":"Sun, C., Shrivastava, A., Singh, S., & Gupta, A. (2017). Revisiting unreasonable effectiveness of data in deep learning era. In: Proc. of ICCV. https:\/\/doi.org\/10.1109\/ICCV.2017.97","DOI":"10.1109\/ICCV.2017.97"},{"key":"2224_CR69","doi-asserted-by":"publisher","unstructured":"Sun, K., Shi, H., Zhang, Z., & Huang, Y. (2021). Ecs-net: Improving weakly supervised semantic segmentation by using connections between class activation maps. In: Proc. of ICCV. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00719","DOI":"10.1109\/ICCV48922.2021.00719"},{"key":"2224_CR70","unstructured":"Sun, W., Liu, Z., Zhang, Y., Zhong, Y., Barnes, N. (2023). An alternative to wsss? an empirical study of the segment anything model (sam) on weakly-supervised semantic segmentation problems. ArXiv preprint."},{"key":"2224_CR71","doi-asserted-by":"publisher","unstructured":"Tang, M., Djelouah, A., Perazzi, F., Boykov, Y., & Schroers, C. (2018). Normalized cut loss for weakly-supervised CNN segmentation. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR.2018.00195","DOI":"10.1109\/CVPR.2018.00195"},{"key":"2224_CR72","doi-asserted-by":"publisher","unstructured":"Vernaza, P., & Chandraker, M. (2017). Learning random-walk label propagation for weakly-supervised semantic segmentation. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR.2017.315","DOI":"10.1109\/CVPR.2017.315"},{"key":"2224_CR73","doi-asserted-by":"publisher","unstructured":"Wang, Y., Zhang, J., Kan, M., Shan, S., Chen, X. (2020). Self-supervised equivariant attention mechanism for weakly supervised semantic segmentation. In: Proc. of CVPR, https:\/\/doi.org\/10.1109\/CVPR42600.2020.01229","DOI":"10.1109\/CVPR42600.2020.01229"},{"issue":"11","key":"2224_CR74","doi-asserted-by":"publisher","first-page":"2314","DOI":"10.1109\/TPAMI.2016.2636150","volume":"39","author":"Y Wei","year":"2016","unstructured":"Wei, Y., Liang, X., Chen, Y., Shen, X., Cheng, M. M., Feng, J., Zhao, Y., & Yan, S. (2016). Stc: A simple to complex framework for weakly-supervised semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(11), 2314\u20132320.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2224_CR75","doi-asserted-by":"publisher","unstructured":"Wei, Y., Feng, J., Liang, X., Cheng, M., Zhao, Y., & Yan, S. (2017). Object region mining with adversarial erasing: A simple classification to semantic segmentation approach. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR.2017.687","DOI":"10.1109\/CVPR.2017.687"},{"key":"2224_CR76","doi-asserted-by":"publisher","unstructured":"Wei, Y., Xiao, H., Shi, H., Jie, Z., Feng, J., & Huang, T. S. (2018). Revisiting dilated convolution: A simple approach for weakly- and semi-supervised semantic segmentation. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR.2018.00759","DOI":"10.1109\/CVPR.2018.00759"},{"key":"2224_CR77","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/j.patcog.2019.01.006","volume":"90","author":"Z Wu","year":"2019","unstructured":"Wu, Z., Shen, C., & Van Den Hengel, A. (2019). Wider or deeper: Revisiting the resnet model for visual recognition. Pattern Recognition, 90, 119\u2013133.","journal-title":"Pattern Recognition"},{"key":"2224_CR78","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J. M., Luo, P. (2021). Segformer: Simple and efficient design for semantic segmentation with transformers. In: Proc. of NeurIPS."},{"key":"2224_CR79","doi-asserted-by":"crossref","unstructured":"Xie, J., Hou, X., Ye, K., Shen, L. (2022). Clims: Cross language image matching for weakly supervised semantic segmentation. In: Proc. of CVPR.","DOI":"10.1109\/CVPR52688.2022.00444"},{"key":"2224_CR80","doi-asserted-by":"publisher","unstructured":"Xu, J., Schwing, A. G., & Urtasun, R. (2015). Learning to segment under various forms of weak supervision. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR.2015.7299002","DOI":"10.1109\/CVPR.2015.7299002"},{"key":"2224_CR81","doi-asserted-by":"publisher","unstructured":"Xu, L., Ouyang, W., Bennamoun, M., Boussa\u00efd, F., Sohel, F., & Xu, D. (2021). Leveraging auxiliary tasks with affinity learning for weakly supervised semantic segmentation. In: Proc. of ICCV. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00690","DOI":"10.1109\/ICCV48922.2021.00690"},{"key":"2224_CR82","doi-asserted-by":"publisher","unstructured":"Xu, L., Ouyang, W., Bennamoun, M., Boussa\u00efd, F., Sohel, F., & Xu, D. (2021). Leveraging auxiliary tasks with affinity learning for weakly supervised semantic segmentation. In: Proc. of ICCV. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00690","DOI":"10.1109\/ICCV48922.2021.00690"},{"key":"2224_CR83","doi-asserted-by":"crossref","unstructured":"Xu, L., Ouyang, W., Bennamoun, M., Boussaid, F., Xu, D. (2022). Multi-class token transformer for weakly supervised semantic segmentation. In: Proc. of CVPR.","DOI":"10.1109\/CVPR52688.2022.00427"},{"issue":"11","key":"2224_CR84","doi-asserted-by":"publisher","first-page":"5303","DOI":"10.1109\/TIP.2018.2855449","volume":"27","author":"J Yang","year":"2018","unstructured":"Yang, J., Sun, X., Lai, Y. K., Zheng, L., & Cheng, M. M. (2018). Recognition from web data: A progressive filtering approach. IEEE Transactions on Image Processing, 27(11), 5303\u20135315.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2224_CR85","doi-asserted-by":"crossref","unstructured":"Yang, X., Gong, X. (2024). Foundation model assisted weakly supervised semantic segmentation. In: Proc. of WACV.","DOI":"10.1109\/WACV57701.2024.00058"},{"key":"2224_CR86","doi-asserted-by":"publisher","unstructured":"Yao, Y., Chen, T., Xie, G., Zhang, C., Shen, F., Wu, Q., Tang, Z., & Zhang, J. (2021). Non-salient region object mining for weakly supervised semantic segmentation. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00265","DOI":"10.1109\/CVPR46437.2021.00265"},{"key":"2224_CR87","doi-asserted-by":"crossref","unstructured":"Yoon, S. H., Kweon, H., Cho, J., Kim, S., Yoon, K. J. (2022). Adversarial erasing framework via triplet with gated pyramid pooling layer for weakly supervised semantic segmentation. In: Proc. of ECCV.","DOI":"10.1007\/978-3-031-19818-2_19"},{"key":"2224_CR88","doi-asserted-by":"publisher","unstructured":"Zeiler, M. D., Krishnan, D., Taylor, G. W., & Fergus, R. (2010). Deconvolutional networks. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR.2010.5539957","DOI":"10.1109\/CVPR.2010.5539957"},{"key":"2224_CR89","doi-asserted-by":"crossref","unstructured":"Zhang, B,. Xiao, J., Wei, Y., Sun, M., Huang, K. (2020a). Reliability does matter: An end-to-end weakly supervised semantic segmentation approach. In: Proc. of AAAI.","DOI":"10.1609\/aaai.v34i07.6971"},{"key":"2224_CR90","unstructured":"Zhang, D., Zhang, H., Tang, J., Hua, X., Sun, Q. (2020b). Causal intervention for weakly-supervised semantic segmentation. In: Proc. of NeurIPS."},{"key":"2224_CR91","doi-asserted-by":"publisher","unstructured":"Zhang, F., Gu, C., Zhang, C., & Dai, Y. (2021). Complementary patch for weakly supervised semantic segmentation. In: Proc. of ICCV. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00715","DOI":"10.1109\/ICCV48922.2021.00715"},{"key":"2224_CR92","unstructured":"Zhang, R., Fang, R., Gao, P., Zhang, W., Li, K., Dai, J., Qiao, Y., Li, H. (2021b). Tip-adapter: Training-free clip-adapter for better vision-language modeling. ArXiv preprint."},{"key":"2224_CR93","doi-asserted-by":"publisher","unstructured":"Zhou, B., Khosla, A., Lapedriza, \u00c0., Oliva, A., & Torralba, A. (2016). Learning deep features for discriminative localization. In: Proc. of CVPR. https:\/\/doi.org\/10.1109\/CVPR.2016.319","DOI":"10.1109\/CVPR.2016.319"},{"key":"2224_CR94","doi-asserted-by":"crossref","unstructured":"Zhou, C., Loy, C. C., Dai, B. (2022a). Extract free dense labels from clip. In: Proc. of ECCV.","DOI":"10.1007\/978-3-031-19815-1_40"},{"issue":"9","key":"2224_CR95","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C. C., & Liu, Z. (2022). Learning to prompt for vision-language models. International Journal of Computer Vision, 130(9), 2337\u20132348.","journal-title":"International Journal of Computer Vision"},{"key":"2224_CR96","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 preprint."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02224-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02224-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02224-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T05:04:31Z","timestamp":1740373471000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02224-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,5]]},"references-count":96,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["2224"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02224-2","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,5]]},"assertion":[{"value":"29 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 August 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 September 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}