{"type":"ScholarlyArticle","title":"Delve into Base-Novel Confusion: Redundancy Exploration for Few-Shot Class-Incremental Learning","authors":[{"name":"Haichen Zhou","slug":"haichen-zhou","given":"Haichen","family":"Zhou","affiliation":"Huazhong University of Science and Technology"},{"name":"Yixiong Zou","slug":"yixiong-zou","given":"Yixiong","family":"Zou","affiliation":"Huazhong University of Science and Technology"},{"name":"Ruixuan Li","slug":"ruixuan-li","given":"Ruixuan","family":"Li","affiliation":"Huazhong University of Science and Technology"},{"name":"Yuhua Li","slug":"yuhua-li","given":"Yuhua","family":"Li","affiliation":"Huazhong University of Science and Technology"},{"name":"Kui Xiao","slug":"kui-xiao","given":"Kui","family":"Xiao","affiliation":"Hubei University"}],"abstract":"Few-shot class-incremental learning (FSCIL) aims to acquire knowledge from novel classes with limited samples while retaining information about base classes. Existing methods address catastrophic forgetting and overfitting by freezing the feature extractor during novel-class learning. However, these methods usually tend to cause the confusion between base and novel classes, i.e., classifying novel-class samples into base classes.In this paper, we delve into this phenomenon to study its cause and solution. We first interpret the confusion as the collision between the novel-class and the base-class region in the feature space.Then, we find the collision is caused by the label-irrelevant redundancies within the base-class feature and pixel space. Through qualitative and quantitative experiments, we identify this redundancy as the shortcut in the base-class training, which can be decoupled to alleviate the collision. Based on this analysis, to alleviate the collision between base and novel classes, we propose a method for FSCIL named Redundancy Decoupling and Integration (RDI). RDI first decouples redundancies from base-class space to shrink the intra-base-class feature space. Then, it integrates the redundancies as a dummy class to enlarge the inter-base-class feature space. This process effectively compresses the base-class feature space, creating buffer space for novel classes and alleviating the model's confusion between the base and novel classes. Extensive experiments across benchmark datasets, including CIFAR-100, miniImageNet, and CUB-200-2011 demonstrate that our method achieves state-of-the-art performance.","doi":"10.24963/ijcai.2024/623","url":"https://ijcai.org/proceedings/2024/623","pdf":"https://ijcai.org/proceedings/2024/0623.pdf","markdown":"https://ijcai.org/proceedings/2024/623.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/623","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Machine Learning","track":"Main Track","number":623,"pages":{"first":5635,"last":5643},"keywords":["Machine Learning: ML: Incremental learning","Machine Learning: ML: Few-shot learning"],"videos":[],"references":[{"position":1,"raw":"[Aljundi et al., 2018] Rahaf Aljundi, Francesca Babiloni, Mohamed Elhoseiny, Marcus Rohrbach, and Tinne Tuyte- laars. Memory aware synapses: Learning what (not) to forget. In Proceedings of the European conference on com- puter vision (ECCV), pages 139-154, 2018.","title":"Memory aware synapses: Learning what (not) to forget","authors":"Rahaf Aljundi, Francesca Babiloni, Mohamed Elhoseiny, Marcus Rohrbach, Tinne Tuytelaars","year":"2018","venue":"Proceedings of the European conference on computer vision (ECCV)","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chen et al., 2019] Wei-Yu Chen, Yen-Cheng Liu, Zsolt Kira, Yu-Chiang Frank Wang, and Jia-Bin Huang. A closer look at few-shot classification. arXiv preprint arXiv:1904.04232, 2019.","title":"A closer look at few-shot classification","authors":"Wei-Yu Chen, Yen-Cheng Liu, Zsolt Kira, Yu-Chiang Frank, Wang, Jia-Bin Huang","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chi et al., 2022] Zhixiang Chi, Li Gu, Huan Liu, Yang Wang, Yuanhao Yu, and Jin Tang. Metafscil: a meta- learning approach for few-shot class incremental learn- ing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14166- 14175, 2022.","title":"Metafscil: a metalearning approach for few-shot class incremental learning","authors":"Zhixiang Chi, Li Gu, Huan Liu, Yang Wang, Yuanhao Yu, Jin Tang","year":"2022","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Daihong et al., 2022] Jiang Daihong, Zhang Sai, Dai Lei, and Dai Yueming. Multi-scale generative adversarial network for image super-resolution. Soft Computing, 26(8):3631-3641, 2022.","title":"Multi-scale generative adversarial network for image super-resolution","authors":"Jiang Daihong, Zhang Sai, Dai Lei, Dai Yueming","year":"2022","venue":"Soft Computing","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Deng et al., 2009] Jia Deng, Wei Dong, Richard Socher, Li- Jia Li, Kai Li, and Li Fei-Fei. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248-255.","title":"Imagenet: A large-scale hierarchical image database","authors":"Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, Li Fei-Fei","year":"2009","venue":"IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Dong et al., 2021] Songlin Dong, Xiaopeng Hong, Xiaoyu Tao, Xinyuan Chang, Xing Wei, and Yihong Gong. Few- shot class-incremental learning via relation knowledge dis- tillation. In Proceedings of the AAAI Conference on Arti- ficial Intelligence, volume 35, pages 1255-1263, 2021.","title":"Fewshot class-incremental learning via relation knowledge distillation","authors":"Songlin Dong, Xiaopeng Hong, Xiaoyu Tao, Xinyuan Chang, Xing Wei, Yihong Gong","year":"2021","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Hou et al., 2019] Saihui Hou, Xinyu Pan, Chen Change Loy, Zilei Wang, and Dahua Lin. Learning a unified clas- sifier incrementally via rebalancing. In Proceedings of the IEEE/CVF conference on Computer Vision and Pattern Recognition, pages 831-839, 2019.","title":"Learning a unified classifier incrementally via rebalancing","authors":"Hou","year":"2019","venue":"Proceedings of the IEEE/CVF conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hu et al., 2019] Wenpeng Hu, Zhou Lin, Bing Liu, Chongyang Tao, Zhengwei Tao Tao, Dongyan Zhao, Jin- wen Ma, and Rui Yan. Overcoming catastrophic forgetting for continual learning via model adaptation. In Interna- tional conference on learning representations, 2019.","title":"Overcoming catastrophic forgetting for continual learning via model adaptation","authors":"Wenpeng Hu, Zhou Lin, Bing Liu, Chongyang Tao, Zhengwei Tao Tao, Dongyan Zhao, Jinwen Ma, Rui Yan","year":"2019","venue":"International conference on learning representations","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Krizhevsky et al., 2009] Alex Krizhevsky, Geoffrey Hinton, et al. Learning multiple layers of features from tiny im- ages. 2009.","title":"Learning multiple layers of features from tiny images","authors":"Alex Krizhevsky, Geoffrey Hinton","year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Li et al., 2022] Ruibo Li, Chi Zhang, Guosheng Lin, Zhe Wang, and Chunhua Shen. Rigidflow: Self-supervised scene flow learning on point clouds by local rigidity prior. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 16959- 16968, 2022.","title":"Rigidflow: Self-supervised scene flow learning on point clouds by local rigidity prior","authors":"Li","year":"2022","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Liu et al., 2020] Weide Liu, Chi Zhang, Guosheng Lin, Tzu-Yi Hung, and Chunyan Miao. Weakly supervised segmentation with maximum bipartite graph matching. In Proceedings of the 28th ACM International Conference on Multimedia, pages 2085-2094, 2020.","title":"Weakly supervised segmentation with maximum bipartite graph matching","authors":"Weide Liu, Chi Zhang, Guosheng Lin, Tzu-Yi Hung, Chunyan Miao","year":"2020","venue":"Proceedings of the 28th ACM International Conference on Multimedia","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Liu et al., 2022] Huan Liu, Li Gu, Zhixiang Chi, Yang Wang, Yuanhao Yu, Jun Chen, and Jin Tang. Few-shot class-incremental learning via entropy-regularized data- free replay. In Computer Vision-ECCV 2022: 17th Eu- ropean Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXIV, pages 146-162. Springer, 2022.","title":"Few-shot class-incremental learning via entropy-regularized datafree replay","authors":"Huan Liu, Li Gu, Zhixiang Chi, Yang Wang, Yuanhao Yu, Jun Chen, Jin Tang","year":"2022","venue":"Computer Vision-ECCV 2022: 17th European Conference","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Peng et al., 2022] Can Peng, Kun Zhao, Tianren Wang, Meng Li, and Brian C Lovell. Few-shot class-incremental learning from an open-set perspective. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXV, pages 382-397. Springer, 2022.","title":"Few-shot class-incremental learning from an open-set perspective","authors":"Peng","year":"2022","venue":"Computer Vision-ECCV 2022: 17th European Conference","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Rebuffi et al., 2017] Sylvestre-Alvise Rebuffi, Alexander Kolesnikov, Georg Sperl, and Christoph H Lampert. icarl: Incremental classifier and representation learning. In Pro- ceedings of the IEEE conference on Computer Vision and Pattern Recognition, pages 2001-2010, 2017.","title":"icarl: Incremental classifier and representation learning","authors":"Sylvestre-Alvise, Alexander Rebuffi, Georg Kolesnikov, Christoph H Sperl, Lampert","year":"2017","venue":"Proceedings of the IEEE conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Russakovsky et al., 2015] Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, et al. Imagenet large scale visual recogni- tion challenge. International journal of computer vision, 115:211-252, 2015.","title":"Imagenet large scale visual recognition challenge","authors":"Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein","year":"2015","venue":"International journal of computer vision","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Snell et al., 2017] Jake Snell, Kevin Swersky, and Richard Zemel. Prototypical networks for few-shot learning. Advances in neural information processing systems, 30, 2017.","title":"Prototypical networks for few-shot learning","authors":"Jake Snell, Kevin Swersky, Richard Zemel","year":"2017","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Sung et al., 2018] Flood Sung, Yongxin Yang, Li Zhang, Tao Xiang, Philip HS Torr, and Timothy M Hospedales. Learning to compare: Relation network for few-shot learn- ing. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1199-1208, 2018.","title":"Learning to compare: Relation network for few-shot learning","authors":"Sung","year":"2018","venue":"Proceedings of the IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Tao et al., 2020] Xiaoyu Tao, Xiaopeng Hong, Xinyuan Chang, Songlin Dong, Xing Wei, and Yihong Gong. Few- shot class-incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12183-12192, 2020.","title":"Fewshot class-incremental learning","authors":"Xiaoyu Tao, Xiaopeng Hong, Xinyuan Chang, Songlin Dong, Xing Wei, Yihong Gong","year":"2020","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Van der Maaten and Hinton, 2008] Laurens Van der Maaten and Geoffrey Hinton. Visualizing data using t-sne. Journal of machine learning research, 9(11), 2008.","title":"Visualizing data using t-sne","authors":"Van Der Maaten, Laurens Hinton, Geoffrey Van Der Maaten, Hinton","year":"2008","venue":"Journal of machine learning research","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Wah et al., 2011] Catherine Wah, Steve Branson, Peter Welinder, Pietro Perona, and Serge Belongie. The caltech- ucsd birds-200-2011 dataset. 2011.","title":"The caltechucsd birds-200-2011 dataset","authors":"Catherine Wah, Steve Branson, Peter Welinder, Pietro Perona, Serge Belongie","year":"2011","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Wang et al., 2020] Haofan Wang, Zifan Wang, Mengnan Du, Fan Yang, Zijian Zhang, Sirui Ding, Piotr Mardziel, and Xia Hu. Score-cam: Score-weighted visual explana- tions for convolutional neural networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops, pages 24-25, 2020.","title":"Score-cam: Score-weighted visual explanations for convolutional neural networks","authors":"Wang","year":"2020","venue":"Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wang et al., 2022] Zifeng Wang, Zizhao Zhang, Chen-Yu Lee, Han Zhang, Ruoxi Sun, Xiaoqi Ren, Guolong Su, Vincent Perot, Jennifer Dy, and Tomas Pfister. Learning to prompt for continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 139-149, 2022.","title":"Learning to prompt for continual learning","authors":"Wang","year":"2022","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wang et al., 2023] Qi-Wei Wang, Da-Wei Zhou, Yi-Kai Zhang, De-Chuan Zhan, and Han-Jia Ye. Few-shot class- incremental learning via training-free prototype calibra- tion. arXiv preprint arXiv:2312.05229, 2023.","title":"Few-shot classincremental learning via training-free prototype calibration","authors":"Qi-Wei Wang, Da-Wei Zhou, Yi-Kai Zhang, Han-Jia De-Chuan Zhan, Ye","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wu et al., 2019] Yue Wu, Yinpeng Chen, Lijuan Wang, Yuancheng Ye, Zicheng Liu, Yandong Guo, and Yun Fu. Large scale incremental learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 374-382, 2019.","title":"Large scale incremental learning","authors":"Yue Wu, Yinpeng Chen, Lijuan Wang, Yuancheng Ye, Zicheng Liu, Yandong Guo, Yun Fu","year":"2019","venue":"Proceedings of the IEEE/CVF conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Yang et al., 2023] Yibo Yang, Haobo Yuan, Xiangtai Li, Zhouchen Lin, Philip Torr, and Dacheng Tao. Neu- ral collapse inspired feature-classifier alignment for few-shot class incremental learning. arXiv preprint arXiv:2302.03004, 2023.","title":"Neural collapse inspired feature-classifier alignment for few-shot class incremental learning","authors":"Yibo Yang, Haobo Yuan, Xiangtai Li, Zhouchen Lin, Philip Torr, Dacheng Tao","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zhang et al., 2021] Chi Zhang, Nan Song, Guosheng Lin, Yun Zheng, Pan Pan, and Yinghui Xu. Few-shot incre- mental learning with continually evolved classifiers. In Proceedings of the IEEE/CVF conference on computer vi- sion and pattern recognition, pages 12455-12464, 2021.","title":"Few-shot incremental learning with continually evolved classifiers","authors":"Zhang","year":"2021","venue":"Proceedings of the IEEE/CVF conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zhou et al., 2022a] Da-Wei Zhou, Fu-Yun Wang, Han-Jia Ye, Liang Ma, Shiliang Pu, and De-Chuan Zhan. For- ward compatible few-shot class-incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9046-9056, 2022.","title":"Forward compatible few-shot class-incremental learning","authors":"Zhou","year":"2022","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhou et al., 2022b] Da-Wei Zhou, Han-Jia Ye, Liang Ma, Di Xie, Shiliang Pu, and De-Chuan Zhan. Few-shot class-incremental learning by sampling multi-phase tasks. IEEE Transactions on Pattern Analysis and Machine In- telligence, 2022.","title":"Few-shot class-incremental learning by sampling multi-phase tasks","authors":"Zhou","year":"2022","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Zhu et al., 2021] Kai Zhu, Yang Cao, Wei Zhai, Jie Cheng, and Zheng-Jun Zha. Self-promoted prototype refinement for few-shot class-incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pat- tern Recognition, pages 6801-6810, 2021.","title":"Self-promoted prototype refinement for few-shot class-incremental learning","authors":"Kai Zhu, Yang Cao, Wei Zhai, Jie Cheng, Zheng-Jun Zha","year":"2021","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}