{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T20:12:25Z","timestamp":1777407145698,"version":"3.51.4"},"reference-count":73,"publisher":"Springer Science and Business Media LLC","issue":"8-9","license":[{"start":{"date-parts":[[2019,11,18]],"date-time":"2019-11-18T00:00:00Z","timestamp":1574035200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,11,18]],"date-time":"2019-11-18T00:00:00Z","timestamp":1574035200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2020,9]]},"DOI":"10.1007\/s11263-019-01264-3","type":"journal-article","created":{"date-parts":[[2019,11,18]],"date-time":"2019-11-18T13:01:43Z","timestamp":1574082103000},"page":"2068-2088","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["HetConv: Beyond Homogeneous Convolution Kernels for Deep CNNs"],"prefix":"10.1007","volume":"128","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1001-2219","authenticated-orcid":false,"given":"Pravendra","family":"Singh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vinay Kumar","family":"Verma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Piyush","family":"Rai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vinay P.","family":"Namboodiri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,11,18]]},"reference":[{"key":"1264_CR1","unstructured":"Abbasi-Asl, R., & Yu, B. (2017). Structural compression of convolutional neural networks based on greedy filter pruning. arXiv preprint arXiv:1705.07356."},{"key":"1264_CR2","unstructured":"Alvarez, J. M., & Salzmann, M. (2016). Learning the number of neurons in deep networks. In NIPS (pp. 2270\u20132278)."},{"key":"1264_CR3","unstructured":"Brock, A., Lim, T., Ritchie, J. M., & Weston, N. (2018). Smash: One-shot model architecture search through hypernetworks. In ICLR."},{"key":"1264_CR4","doi-asserted-by":"crossref","unstructured":"Cai, H., Chen, T., Zhang, W., Yu, Y., & Wang, J. (2018a). Efficient architecture search by network transformation. In Thirty-second AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v32i1.11709"},{"key":"1264_CR5","unstructured":"Cai, H., Yang, J., Zhang, W., Han, S., & Yu, Y. (2018b). Path-level network transformation for efficient architecture search. In ICML."},{"key":"1264_CR6","unstructured":"Chen, W., Wilson, J., Tyree, S., Weinberger, K., & Chen, Y. (2015). Compressing neural networks with the hashing trick. In ICML (pp. 2285\u20132294)."},{"key":"1264_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y., Fang, H., Xu, B., Yan, Z., Kalantidis, Y., Rohrbach, M., et al. (2019). Drop an octave: Reducing spatial redundancy in convolutional neural networks with octave convolution. arXiv preprint arXiv:1904.05049","DOI":"10.1109\/ICCV.2019.00353"},{"key":"1264_CR8","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In CVPR.","DOI":"10.1109\/CVPR.2017.195"},{"key":"1264_CR9","unstructured":"Denton, E. L., Zaremba, W., Bruna, J., LeCun, Y., & Fergus, R. (2014). Exploiting linear structure within convolutional networks for efficient evaluation. In NIPS."},{"key":"1264_CR10","doi-asserted-by":"crossref","unstructured":"Ding, X., Ding, G., Han, J., & Tang, S. (2018). Auto-balanced filter pruning for efficient convolutional neural networks. In AAAI.","DOI":"10.1609\/aaai.v32i1.12262"},{"issue":"1","key":"1264_CR11","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S. A., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2015). The pascal visual object classes challenge: A retrospective. International Journal of Computer Vision, 111(1), 98\u2013136.","journal-title":"International Journal of Computer Vision"},{"key":"1264_CR12","unstructured":"Finn, C., Abbeel, P., & Levine, S. (2017). Model-agnostic meta-learning for fast adaptation of deep networks. In ICML."},{"key":"1264_CR13","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y. (2014). Generative adversarial nets. In Advances in neural information processing systems (pp. 2672\u20132680)."},{"key":"1264_CR14","unstructured":"Han, S., Mao, H., & Dally, W. J. (2016). Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding. In ICLR."},{"key":"1264_CR15","unstructured":"Hassibi, B., & Stork, D. G. (1993). Second order derivatives for network pruning: Optimal brain surgeon. In NIPS."},{"key":"1264_CR16","doi-asserted-by":"crossref","unstructured":"He, K., & Sun, J. (2015). Convolutional neural networks at constrained time cost. In 2015 IEEE conference on computer vision and pattern recognition (CVPR) (pp. 5353\u20135360). IEEE.","DOI":"10.1109\/CVPR.2015.7299173"},{"key":"1264_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016a). Deep residual learning for image recognition. In CVPR (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"1264_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016b). Identity mappings in deep residual networks. In European conference on computer vision (pp. 630\u2013645). Springer.","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"1264_CR19","doi-asserted-by":"crossref","unstructured":"He, Y., Kang, G., Dong, X., Fu, Y., & Yang, Y. (2018). Soft filter pruning for accelerating deep convolutional neural networks. In IJCAI.","DOI":"10.24963\/ijcai.2018\/309"},{"key":"1264_CR20","doi-asserted-by":"crossref","unstructured":"He, Y., Zhang, X., Sun, J. (2017). Channel pruning for accelerating very deep neural networks. In ICCV (p. 6).","DOI":"10.1109\/ICCV.2017.155"},{"key":"1264_CR21","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., et al. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861."},{"key":"1264_CR22","unstructured":"Hu, H., Peng, R., Tai, Y. W., & Tang, C. K. (2016). Network trimming: A data-driven neuron pruning approach towards efficient deep architectures. arXiv preprint arXiv:1607.03250."},{"key":"1264_CR23","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., & Sun, G. (2018). Squeeze-and-excitation networks. In CVPR.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1264_CR24","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In CVPR.","DOI":"10.1109\/CVPR.2017.243"},{"key":"1264_CR25","unstructured":"Iandola, F. N., Han, S., Moskewicz, M. W., Ashraf, K., Dally, W. J., & Keutzer, K. (2016). Squeezenet: Alexnet-level accuracy with 50$$\\,\\times $$ fewer parameters and $$<$$ 0.5 mb model size. arXiv preprint arXiv:1602.07360."},{"key":"1264_CR26","doi-asserted-by":"crossref","unstructured":"Ioannou, Y., Robertson, D., Cipolla, R., & Criminisi, A. (2017). Deep roots: Improving cnn efficiency with hierarchical filter groups. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1231\u20131240).","DOI":"10.1109\/CVPR.2017.633"},{"key":"1264_CR27","unstructured":"Ioannou, Y., Robertson, D., Shotton, J., Cipolla, R., & Criminisi, A. (2015). Training CNNs with low-rank filters for efficient image classification. arXiv preprint arXiv:1511.06744."},{"key":"1264_CR28","unstructured":"Jaderberg, M., Vedaldi, A., & Zisserman, A. (2014). Speeding up convolutional neural networks with low rank expansions. arXiv preprint arXiv:1405.3866."},{"key":"1264_CR29","unstructured":"Kamath, P., Singh, A., & Dutta, D. (2018). Neural architecture construction using envelopenets. arXiv preprint arXiv:1803.06744."},{"key":"1264_CR30","unstructured":"Krizhevsky, A., & Hinton, G. (2009). Learning multiple layers of features from tiny images."},{"key":"1264_CR31","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In NIPS (pp. 1097\u20131105)."},{"key":"1264_CR32","doi-asserted-by":"crossref","unstructured":"Lebedev, V., Lempitsky, V. (2016). Fast convnets using group-wise brain damage. In CVPR (pp. 2554\u20132564).","DOI":"10.1109\/CVPR.2016.280"},{"key":"1264_CR33","unstructured":"LeCun, Y., Denker, J. S., & Solla, S. A. (1990). Optimal brain damage. In NIPS (pp. 598\u2013605)."},{"key":"1264_CR34","unstructured":"Li, H., Kadav, A., Durdanovic, I., Samet, H., & Graf, H. P. (2016). Pruning filters for efficient convnets. arXiv preprint arXiv:1608.08710."},{"key":"1264_CR35","unstructured":"Li, H., Kadav, A., Durdanovic, I., Samet, H., & Graf, H. P. (2017). Pruning filters for efficient convnets. . In ICLR."},{"key":"1264_CR36","doi-asserted-by":"crossref","unstructured":"Li, Y., Kuang, Z., Chen, Y., & Zhang, W. (2019). Data-driven neuron allocation for scale aggregation networks. In Proceedings of the ieee conference on computer vision and pattern recognition (pp. 11,526\u201311,534).","DOI":"10.1109\/CVPR.2019.01179"},{"key":"1264_CR37","unstructured":"Lin, J., Rao, Y., Lu, J., & Zhou, J. (2017a). Runtime neural pruning. In Advances in neural information processing systems (pp. 2181\u20132191)."},{"key":"1264_CR38","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Doll\u00e1r, P., Girshick, R. B., He, K., Hariharan, B., & Belongie, S. J. (2017b). Feature pyramid networks for object detection. In CVPR (p. 4).","DOI":"10.1109\/CVPR.2017.106"},{"key":"1264_CR39","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., et al. (2014). Microsoft coco: Common objects in context. In ECCV (pp. 740\u2013755). Springer.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1264_CR40","doi-asserted-by":"crossref","unstructured":"Liu, C., Zoph, B., Neumann, M., Shlens, J., Hua, W., Li, L. J., et al. (2018). Progressive neural architecture search. In Proceedings of the European conference on computer vision (ECCV) (pp. 19\u201334).","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"1264_CR41","unstructured":"Liu, H., Simonyan, K., Vinyals, O., Fernando, C., & Kavukcuoglu, K. (2017a). Hierarchical representations for efficient architecture search. arXiv preprint arXiv:1711.00436."},{"key":"1264_CR42","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., et al. (2016). Ssd: Single shot multibox detector. In ECCV (pp. 21\u201337). Springer.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1264_CR43","doi-asserted-by":"crossref","unstructured":"Liu, Z., Li, J., Shen, Z., Huang, G., Yan, S., & Zhang, C. (2017b). Learning efficient convolutional networks through network slimming. In ICCV (pp. 2755\u20132763). IEEE.","DOI":"10.1109\/ICCV.2017.298"},{"key":"1264_CR44","unstructured":"Louizos, C., Ullrich, K., & Welling, M. (2017). Bayesian compression for deep learning. In NIPS (pp. 3288\u20133298)."},{"key":"1264_CR45","doi-asserted-by":"crossref","unstructured":"Luo, J. H., Wu, J., Lin, W. (2017). Thinet: A filter level pruning method for deep neural network compression. In CVPR (pp. 5058\u20135066).","DOI":"10.1109\/ICCV.2017.541"},{"key":"1264_CR46","doi-asserted-by":"crossref","unstructured":"Miao, H., Li, A., Davis, L. S., & Deshpande, A. (2017). Towards unified data and lifecycle management for deep learning. In ICDE (pp. 571\u2013582). IEEE.","DOI":"10.1109\/ICDE.2017.112"},{"key":"1264_CR47","unstructured":"Molchanov, P., Tyree, S., Karras, T., Aila, T., & Kautz, J. (2017). Pruning convolutional neural networks for resource efficient inference. In ICLR."},{"key":"1264_CR48","unstructured":"Neklyudov, K., Molchanov, D., Ashukha, A., & Vetrov, D. P. (2017). Structured bayesian pruning via log-normal multiplicative noise. In NIPS (pp. 6775\u20136784)."},{"key":"1264_CR49","doi-asserted-by":"crossref","unstructured":"Noroozi, M., & Favaro, P. (2016). Unsupervised learning of visual representations by solving jigsaw puzzles. In European conference on computer vision (pp. 69\u201384). Springer.","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"1264_CR50","unstructured":"Pham, H., Guan, M. Y., Zoph, B., Le, Q. V., & Dean, J. (2018). Efficient neural architecture search via parameter sharing. In ICML."},{"key":"1264_CR51","doi-asserted-by":"crossref","unstructured":"Rastegari, M., Ordonez, V., Redmon, J., & Farhadi, A. (2016). Xnor-net: Imagenet classification using binary convolutional neural networks. In ECCV (pp. 525\u2013542). Springer.","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"1264_CR52","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. In NIPS (pp. 91\u201399)."},{"issue":"3","key":"1264_CR53","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., et al. (2015). Imagenet large scale visual recognition challenge. IJCV, 115(3), 211\u2013252.","journal-title":"IJCV"},{"key":"1264_CR54","unstructured":"Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. In ICLR."},{"key":"1264_CR55","doi-asserted-by":"crossref","unstructured":"Singh, P., Verma, V. K., Rai, P., & Namboodiri, V. P. (2019). Hetconv: Heterogeneous kernel-based convolutions for deep CNNs. In The IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2019.00497"},{"key":"1264_CR56","unstructured":"Snell, J., Swersky, K., & Zemel, R. (2017). Prototypical networks for few-shot learning. In Advances in neural information processing systems (pp. 4077\u20134087)."},{"key":"1264_CR57","unstructured":"Stamoulis, D., Ding, R., Wang, D., Lymberopoulos, D., Priyantha, B., Liu, J., et al. (2019). Single-path nas: Designing hardware-efficient convnets in less than 4 hours. arXiv preprint arXiv:1904.02877."},{"key":"1264_CR58","unstructured":"Sun, K., Li, M., Liu, D., & Wang, J. (2018). Igcv3: Interleaved low-rank group convolutions for efficient deep neural networks. arXiv preprint arXiv:1806.00178."},{"key":"1264_CR59","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. A. (2017). Inception-v4, inception-resnet and the impact of residual connections on learning. In AAAI (vol. 4, p. 12).","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"1264_CR60","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., et al. (2015). Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1\u20139).","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"1264_CR61","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2818\u20132826).","DOI":"10.1109\/CVPR.2016.308"},{"key":"1264_CR62","unstructured":"Vanhoucke, V. (2014) Learning visual representations at scale. In ICLR invited talk."},{"key":"1264_CR63","doi-asserted-by":"crossref","unstructured":"Verma, V. K., Arora, G., Mishra, A., Rai, P. (2018). Generalized zero-shot learning via synthesized examples. In The IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00450"},{"key":"1264_CR64","unstructured":"Wen, W., Wu, C., Wang, Y., Chen, Y., Li, H. (2016). Learning structured sparsity in deep neural networks. In NIPS (pp. 2074\u20132082)."},{"key":"1264_CR65","doi-asserted-by":"crossref","unstructured":"Wu, Z., Nagarajan, T., Kumar, A., Rennie, S., Davis, L. S., Grauman, K., et al. (2018). Blockdrop: Dynamic inference paths in residual networks. In CVPR (pp. 8817\u20138826).","DOI":"10.1109\/CVPR.2018.00919"},{"key":"1264_CR66","doi-asserted-by":"crossref","unstructured":"Xie, G., Wang, J., Zhang, T., Lai, J., Hong, R., & Qi, G. J. (2018). Interleaved structured sparse convolutional neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 8847\u20138856).","DOI":"10.1109\/CVPR.2018.00922"},{"key":"1264_CR67","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K. (2017). Aggregated residual transformations for deep neural networks. In 2017 IEEE conference on computer vision and pattern recognition (CVPR) (pp. 5987\u20135995). IEEE.","DOI":"10.1109\/CVPR.2017.634"},{"key":"1264_CR68","doi-asserted-by":"crossref","unstructured":"Yu, R., Li, A., Chen, C. F., Lai, J. H., Morariu, V. I., Han, X., et al. (2018). Nisp: Pruning networks using neuron importance score propagation. In CVPR.","DOI":"10.1109\/CVPR.2018.00958"},{"key":"1264_CR69","doi-asserted-by":"crossref","unstructured":"Zhang, T., Qi, G. J., Xiao, B., & Wang, J. (2017). Interleaved group convolutions. In Proceedings of the IEEE international conference on computer vision (pp. 4373\u20134382).","DOI":"10.1109\/ICCV.2017.469"},{"key":"1264_CR70","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., Sun, J. (2018). Shufflenet: An extremely efficient convolutional neural network for mobile devices.","DOI":"10.1109\/CVPR.2018.00716"},{"key":"1264_CR71","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zou, J., Ming, X., He, K., & Sun, J. (2015). Efficient and accurate approximations of nonlinear convolutional networks. In NIPS (pp. 1984\u20131992).","DOI":"10.1109\/CVPR.2015.7298809"},{"key":"1264_CR72","doi-asserted-by":"crossref","unstructured":"Zhou, H., Alvarez, J. M., & Porikli, F. (2016). Less is more: Towards compact cnns. In ECCV (pp. 662\u2013677). Springer.","DOI":"10.1007\/978-3-319-46493-0_40"},{"key":"1264_CR73","unstructured":"Zoph, B., & Le, Q.V. (2017). Neural architecture search with reinforcement learning. In ICLR."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-019-01264-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-019-01264-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-019-01264-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,5]],"date-time":"2022-10-05T22:54:23Z","timestamp":1665010463000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-019-01264-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11,18]]},"references-count":73,"journal-issue":{"issue":"8-9","published-print":{"date-parts":[[2020,9]]}},"alternative-id":["1264"],"URL":"https:\/\/doi.org\/10.1007\/s11263-019-01264-3","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,11,18]]},"assertion":[{"value":"20 April 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 November 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 November 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}