SMMix: Self-Motivated Image Mixing for Vision Transformers

TL;DR

SMMix is a novel image augmentation technique for vision transformers that self-motivates image and label enhancement, improving accuracy with less training overhead compared to existing methods.

Contribution

It introduces a self-motivated image mixing approach with attention region mixing, fine-grained label assignment, and feature consistency constraints, reducing training overhead and enhancing performance.

Findings

Improves DeiT, CaiT, and PVT models by over 1% on ImageNet-1k.

Demonstrates better performance than other CutMix variants.

Shows strong generalization on downstream and out-of-distribution datasets.

Abstract

CutMix is a vital augmentation strategy that determines the performance and generalization ability of vision transformers (ViTs). However, the inconsistency between the mixed images and the corresponding labels harms its efficacy. Existing CutMix variants tackle this problem by generating more consistent mixed images or more precise mixed labels, but inevitably introduce heavy training overhead or require extra information, undermining ease of use. To this end, we propose an novel and effective Self-Motivated image Mixing method (SMMix), which motivates both image and label enhancement by the model under training itself. Specifically, we propose a max-min attention region mixing approach that enriches the attention-focused objects in the mixed images. Then, we introduce a fine-grained label assignment technique that co-trains the output tokens of mixed images with fine-grained supervision. Moreover, we devise a novel feature consistency constraint to align features from mixed and unmixed images. Due to the subtle designs of the self-motivated paradigm, our SMMix is significant in its smaller training overhead and better performance than other CutMix variants. In particular, SMMix improves the accuracy of DeiT-T/S/B, CaiT-XXS-24/36, and PVT-T/S/M/L by more than +1% on ImageNet-1k. The generalization capability of our method is also demonstrated on downstream tasks and out-of-distribution datasets. Our project is anonymously available at https://github.com/ChenMnZ/SMMix.