EFFECTIVELY CLARIFY CONFUSION VIA VISUALIZED AGGREGATION AND SEPARATION OF DEEP REPRE-SENTATION

Abstract

Clarifying confusion is the most critical issue for improving classification performance. The current mainstream research mainly focuses on solving the confusion in a specific case, such as data insufficiency and class imbalance. 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.

1. INTRODUCTION

Aggregating Aggregated Aggregated Clarifying confusion is the most critical issue for improving classification performance. 



Figure 1: Schematic of Aggregation Separation Loss.

The vast majority of samples belong to a small number of categories. Samples from unimpressive categories will be confused by the model into fat categoriesCui et al. (2019). In addition, the classification boundaries of some problems are not clearLin et al. (2022). Models will always confuse samples into similar classes. More seriously, many real-world problems simultaneously have more than one case confusing the models.

