Effectively Clarify Confusion via Visualized Aggregation and Separation of Deep Representation

Yi Lin, Jingchi Jiang, Dongxin Chen, Zhaoyang Ma, Yi Guan, Xiguang Liu, Haiyan You, Jing Yang

Keywords: Data Insufficiency, Class Imbalance, Evidience Unclearity, Confusion, Representation Learning

Abstract:

Clarifying confusion is the most critical issue for improving classification performance. Confusion occurs with almost all classification models but tends to be ignored in excellent-performing models. The current mainstream research mainly focuses on solving the confusion in a specific case, such as data insufficiency and class imbalance. We believe that mining the commonalities of the same class and the gaps among different classes will effectively clarify the confusion. In this paper, we propose a novel, simple and intuitive Aggregation Separation Loss (ASLoss), as an adjunct for classification loss to clarify the confusion in some common cases. The ASLoss aggregates the representations of the same class samples as near as possible and separates the representations of different classes as far as possible.
We use two image classification tasks with three simultaneous confounding characteristics i.e. data insufficiency, class imbalance, and unclear class evidence to demonstrate ASLoss. Representation visualization, confusion comparison and detailed comparison experiments are conducted. The results show that representations in deep spaces extracted by ASLoss are sufficiently clear and distinguishable, the confusion among different classes is significantly clarified and the optimal network using ASLoss reaches the state-of-the-art level.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning