Information Competing Process for Learning Diversified Representations
Jie Hu · Rongrong Ji · ShengChuan Zhang · Xiaoshuai Sun · Qixiang Ye · Chia-Wen Lin · Qi Tian

Tue Dec 10th 10:45 AM -- 12:45 PM @ East Exhibition Hall B + C #68

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