ACE: Adaptive Confusion Energy for Natural World Data Distribution

With the development of deep learning, standard classification problems have achieved good results. However, conventional classification problems are often too idealistic. Most data in the natural world usually have imbalanced distribution and fine-grained characteristics. Recently, many state-of-th...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2021-03
Main Authors: Yen-Chi, Hsu, Cheng-Yao, Hong, Wan-Cyuan Fan, Ming-Sui, Lee, Geiger, Davi, Liu, Tyng-Luh
Format: Article
Language:English
Subjects:
Ablation
Confusion
Feature extraction
Learning
Regularization
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With the development of deep learning, standard classification problems have achieved good results. However, conventional classification problems are often too idealistic. Most data in the natural world usually have imbalanced distribution and fine-grained characteristics. Recently, many state-of-the-art approaches tend to focus on one or another separately, but rarely on both. In this paper, we introduce a novel and adaptive batch-wise regularization based on the proposed Adaptive Confusion Energy (ACE) to flexibly address the nature world distribution, which usually involves fine-grained and long-tailed properties at the same time. ACE increases the difficulty of the training process and further alleviates the overfitting problem. Through the datasets with the technical issue in fine-grained (CUB, CAR, AIR) and long-tailed (ImageNet-LT), or comprehensive issues (CUB-LT, iNaturalist), the result shows that the ACE is not only competitive to some state-of-the-art on performance but also demonstrates the effectiveness of training.
ISSN:2331-8422