paper-with-me

홈 › Papers

SMMix: Self-Motivated Image Mixing for Vision Transformers

2022-12-26 · ICCV 2023 1 · Mengzhao Chen, Mingbao Lin, Zhihang Lin, Yuxin Zhang, Fei Chao, Rongrong Ji

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.

📄 PDF Abstract BibTeX arXiv:2212.12977

Code (1)

chenmnz/smmix 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
CutMix CutMix is an image data augmentation strategy. Instead of simply removing pixels as in Cutout, we replace the removed regions with…

Similar Papers 제목 키워드 기반

Hard Negative Mixing for Contrastive Learning

2020-10-02 · NeurIPS 2020 12 · Yannis Kalantidis, Mert Bulent Sariyildiz, Noe Pion, Philippe Weinzaepfel 외

Contrastive learning has become a key component of self-supervised learning approaches for computer vision. By learning to embed two augmented versions of the same image close to each other and to push the embeddings of …

Contrastive LearningData AugmentationInstance Segmentationobject-detection+3

Twice Mixing: A Rank Learning based Quality Assessment Approach for Underwater Image Enhancement

2021-02-01 · Zhenqi Fu, Xueyang Fu, Yue Huang, Xinghao Ding

To improve the quality of underwater images, various kinds of underwater image enhancement (UIE) operators have been proposed during the past few years. However, the lack of effective objective evaluation methods limits …

Image EnhancementUIE

A Simple Data Mixing Prior for Improving Self-Supervised Learning

2022-06-15 · CVPR 2022 1 · Sucheng Ren, Huiyu Wang, Zhengqi Gao, Shengfeng He 외

Data mixing (e.g., Mixup, Cutmix, ResizeMix) is an essential component for advancing recognition models. In this paper, we focus on studying its effectiveness in the self-supervised setting. By noticing the mixed images …

Representation LearningSelf-Supervised Learning

Mixing and Shifting: Exploiting Global and Local Dependencies in Vision MLPs

2022-02-14 · Huangjie Zheng, Pengcheng He, Weizhu Chen, Mingyuan Zhou

Token-mixing multi-layer perceptron (MLP) models have shown competitive performance in computer vision tasks with a simple architecture and relatively small computational cost. Their success in maintaining computation ef…

Self-Remixing: Unsupervised Speech Separation via Separation and Remixing

2022-11-18 · Kohei Saijo, Tetsuji Ogawa

We present Self-Remixing, a novel self-supervised speech separation method, which refines a pre-trained separation model in an unsupervised manner. The proposed method consists of a shuffler module and a solver module, a…

Domain AdaptationSemi-supervised Domain AdaptationSpeech Separation