Compositional Attribute Imbalance in Vision Datasets
Yanbiao Ma, Jiayi Chen, Wei Dai, Dong Zhao, Zeyu Zhang, Yuting Yang, Bowei Liu, Jiaxuan Zhao
Abstract
Visual attribute imbalance is a common yet underexplored issue in image classification, significantly impacting model performance and generalization. In this work, we first define the first-level and second-level attributes of images and then introduce a CLIP-based framework to construct a visual attribute dictionary, enabling automatic evaluation of image attributes. By systematically analyzing both single-attribute imbalance and compositional attribute imbalance, we reveal how the rarity of attributes affects model performance. To tackle these challenges, we propose adjusting the sampling probability of samples based on the rarity of their compositional attributes. This strategy is further integrated with various data augmentation techniques (such as CutMix, Fmix, and SaliencyMix) to enhance the model
BibTeX
@inproceedings{aaai2026_compositionalatt,
title = {Compositional Attribute Imbalance in Vision Datasets},
author = {Yanbiao Ma and Jiayi Chen and Wei Dai and Dong Zhao and Zeyu Zhang and Yuting Yang and Bowei Liu and Jiaxuan Zhao and Andi Zhang},
booktitle = {AAAI 2026},
year = {2026}
}