Timezone: »
Learning representations with diversified information remains as an open problem. Towards learning diversified representations, a new approach, termed Information Competing Process (ICP), is proposed in this paper. Aiming to enrich the information carried by feature representations, ICP separates a representation into two parts with different mutual information constraints. The separated parts are forced to accomplish the downstream task independently in a competitive environment which prevents the two parts from learning what each other learned for the downstream task. Such competing parts are then combined synergistically to complete the task. By fusing representation parts learned competitively under different conditions, ICP facilitates obtaining diversified representations which contain rich information. Experiments on image classification and image reconstruction tasks demonstrate the great potential of ICP to learn discriminative and disentangled representations in both supervised and self-supervised learning settings.
Author Information
Jie Hu (Xiamen University)
Rongrong Ji (Xiamen University, China)
ShengChuan Zhang (Xiamen University)
Xiaoshuai Sun (Xiamen University)
Qixiang Ye (University of Chinese Academy of Sciences, China)
Chia-Wen Lin (National Tsing Hua University)
Qi Tian (Huawei Noah’s Ark Lab)
More from the Same Authors
-
2022 Poster: Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach »
Peng Mi · Li Shen · Tianhe Ren · Yiyi Zhou · Xiaoshuai Sun · Rongrong Ji · Dacheng Tao -
2022 Poster: PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining »
Yuting Gao · Jinfeng Liu · Zihan Xu · Jun Zhang · Ke Li · Rongrong Ji · Chunhua Shen -
2023 Poster: Discover and Align Taxonomic Context Priors for Open-world Semi-Supervised Learning »
Yu Wang · Zhun Zhong · Pengchong Qiao · Xuxin Cheng · Xiawu Zheng · Chang Liu · Nicu Sebe · Rongrong Ji · Jie Chen -
2023 Poster: Improving Adversarial Robustness via Information Bottleneck Distillation »
Huafeng Kuang · Hong Liu · Shin'ichi Satoh · Yongjian Wu · Rongrong Ji -
2023 Poster: Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models »
Gen Luo · Yiyi Zhou · Tianhe Ren · Shengxin Chen · Xiaoshuai Sun · Rongrong Ji -
2023 Poster: Mode Approximation Makes Good Multimodal Prompts »
Haixin Wang · Xinlong Yang · Jianlong Chang · Dian Jin · Jinan Sun · Shikun Zhang · Xiao Luo · Qi Tian -
2023 Poster: Parameter and Computation Efficient Transfer Learning for Vision-Language Pre-trained Models »
Qiong Wu · Wei Yu · Yiyi Zhou · Shubin Huang · Xiaoshuai Sun · Rongrong Ji -
2023 Poster: Learning to Parameterize Visual Attributes for Open-set Fine-grained Retrieval »
Shijie Wang · Jianlong Chang · Haojie Li · Zhihui Wang · Wanli Ouyang · Qi Tian -
2023 Poster: AiluRus: A Scalable ViT Framework for Dense Prediction »
Jin Li · Yaoming Wang · XIAOPENG ZHANG · Bowen Shi · Dongsheng Jiang · Chenglin Li · Wenrui Dai · Hongkai Xiong · Qi Tian -
2023 Poster: Segment Anything in 3D with NeRFs »
Jiazhong Cen · Zanwei Zhou · Jiemin Fang · chen yang · Wei Shen · Lingxi Xie · Dongsheng Jiang · XIAOPENG ZHANG · Qi Tian -
2023 Poster: CAPro: Webly Supervised Learning with Cross-modality Aligned Prototypes »
Yulei Qin · Xingyu Chen · Yunhang Shen · Chaoyou Fu · Yun Gu · Ke Li · Xing Sun · Rongrong Ji -
2022 Spotlight: Fine-Grained Semantically Aligned Vision-Language Pre-Training »
Juncheng Li · XIN HE · Longhui Wei · Long Qian · Linchao Zhu · Lingxi Xie · Yueting Zhuang · Qi Tian · Siliang Tang -
2022 Poster: Learning Best Combination for Efficient N:M Sparsity »
Yuxin Zhang · Mingbao Lin · ZhiHang Lin · Yiting Luo · Ke Li · Fei Chao · Yongjian Wu · Rongrong Ji -
2022 Poster: Fine-Grained Semantically Aligned Vision-Language Pre-Training »
Juncheng Li · XIN HE · Longhui Wei · Long Qian · Linchao Zhu · Lingxi Xie · Yueting Zhuang · Qi Tian · Siliang Tang -
2021 Poster: Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence »
Xue Yang · Xiaojiang Yang · Jirui Yang · Qi Ming · Wentao Wang · Qi Tian · Junchi Yan -
2020 Poster: Rotated Binary Neural Network »
Mingbao Lin · Rongrong Ji · Zihan Xu · Baochang Zhang · Yan Wang · Yongjian Wu · Feiyue Huang · Chia-Wen Lin -
2020 Poster: Self-Adaptively Learning to Demoiré from Focused and Defocused Image Pairs »
Lin Liu · Shanxin Yuan · Jianzhuang Liu · Liping Bao · Gregory Slabaugh · Qi Tian -
2020 Poster: UWSOD: Toward Fully-Supervised-Level Capacity Weakly Supervised Object Detection »
Yunhang Shen · Rongrong Ji · Zhiwei Chen · Yongjian Wu · Feiyue Huang -
2020 Poster: One-bit Supervision for Image Classification »
Hengtong Hu · Lingxi Xie · Zewei Du · Richang Hong · Qi Tian -
2019 Poster: Variational Structured Semantic Inference for Diverse Image Captioning »
Fuhai Chen · Rongrong Ji · Jiayi Ji · Xiaoshuai Sun · Baochang Zhang · Xuri Ge · Yongjian Wu · Feiyue Huang · Yan Wang -
2019 Poster: FreeAnchor: Learning to Match Anchors for Visual Object Detection »
Xiaosong Zhang · Fang Wan · Chang Liu · Rongrong Ji · Qixiang Ye