Related papers: Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification

Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification

URL: http://arxiv.org/abs/2112.07928v1
Date: Wed, 15 Dec 2021 07:14:39 GMT
Title: Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification
Authors: Xiaohua Chen, Yucan Zhou, Dayan Wu, Wanqian Zhang, Yu Zhou, Bo Li, Weiping Wang
Abstract summary: Real-world data often follows a long-tailed distribution, which makes the performance of existing classification algorithms degrade heavily. We propose a novel reasoning-based implicit semantic data augmentation method to borrow transformation directions from other classes. Experimental results on CIFAR-100-LT, ImageNet-LT, and iNaturalist 2018 have demonstrated the effectiveness of our proposed method.
Score: 17.08583412899347
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Real-world data often follows a long-tailed distribution, which makes the performance of existing classification algorithms degrade heavily. A key issue is that samples in tail categories fail to depict their intra-class diversity. Humans can imagine a sample in new poses, scenes, and view angles with their prior knowledge even if it is the first time to see this category. Inspired by this, we propose a novel reasoning-based implicit semantic data augmentation method to borrow transformation directions from other classes. Since the covariance matrix of each category represents the feature transformation directions, we can sample new directions from similar categories to generate definitely different instances. Specifically, the long-tailed distributed data is first adopted to train a backbone and a classifier. Then, a covariance matrix for each category is estimated, and a knowledge graph is constructed to store the relations of any two categories. Finally, tail samples are adaptively enhanced via propagating information from all the similar categories in the knowledge graph. Experimental results on CIFAR-100-LT, ImageNet-LT, and iNaturalist 2018 have demonstrated the effectiveness of our proposed method compared with the state-of-the-art methods.