paper-with-me

Papers

Exploring Token-Level Augmentation in Vision Transformer for Semi-Supervised Semantic Segmentation

2025-03-04 · Dengke Zhang, Quan Tang, Fagui Liu, C. L. Philip Chen, Haiqing Mei

Semi-supervised semantic segmentation has witnessed remarkable advancements in recent years. However, existing algorithms are based on convolutional neural networks and directly applying them to Vision Transformers poses certain limitations due to conceptual disparities. To this end, we propose TokenMix, a data augmentation technique specifically designed for semi-supervised semantic segmentation with Vision Transformers. TokenMix aligns well with the global attention mechanism by mixing images at the token level, enhancing learning capability for contexutual information among image patches. We further incorporate image augmentation and feature augmentation to promote the diversity of augmentation. Moreover, to enhance consistency regularization, we propose a dual-branch framework where each branch applies both image augmentation and feature augmentation to the input image. We conduct extensive experiments across multiple benchmark datasets, including Pascal VOC 2012, Cityscapes, and COCO. Results suggest that the proposed method outperforms state-of-the-art algorithms with notably observed accuracy improvement, especially under the circumstance of limited fine annotations.

📄 PDF Abstract BibTeX arXiv:2503.02459

Code (1)

zdk258/TokenSwap 공식 구현 pytorch

Tasks

Data AugmentationDiversityImage AugmentationSemantic SegmentationSemi-Supervised Semantic Segmentation

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers

2022-07-18 · Jihao Liu, Boxiao Liu, Hang Zhou, Hongsheng Li 외

CutMix is a popular augmentation technique commonly used for training modern convolutional and transformer vision networks. It was originally designed to encourage Convolution Neural Networks (CNNs) to focus more on an i…

Data Augmentation

TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformers

2022-10-14 · Hyeong Kyu Choi, Joonmyung Choi, Hyunwoo J. Kim

Mixup is a commonly adopted data augmentation technique for image classification. Recent advances in mixup methods primarily focus on mixing based on saliency. However, many saliency detectors require intense computation…

Data Augmentationimage-classificationImage Classification

RaViTT: Random Vision Transformer Tokens

2023-06-19 · Felipe A. Quezada, Carlos F. Navarro, Cristian Muñoz, Manuel Zamorano 외

Vision Transformers (ViTs) have successfully been applied to image classification problems where large annotated datasets are available. On the other hand, when fewer annotations are available, such as in biomedical appl…

Image Augmentationimage-classificationImage Classification

PViT-6D: Overclocking Vision Transformers for 6D Pose Estimation with Confidence-Level Prediction and Pose Tokens

2023-11-29 · Sebastian Stapf, Tobias Bauernfeind, Marco Riboldi

In the current state of 6D pose estimation, top-performing techniques depend on complex intermediate correspondences, specialized architectures, and non-end-to-end algorithms. In contrast, our research reframes the probl…

6D Pose EstimationPose Estimation

THAT: Token-wise High-frequency Augmentation Transformer for Hyperspectral Pansharpening

2025-08-11 · Hongkun Jin, Hongcheng Jiang, Zejun Zhang, Yuan Zhang 외 arxiv

Transformer-based methods have demonstrated strong potential in hyperspectral pansharpening by modeling long-range dependencies. However, their effectiveness is often limited by redundant token representations and a lack…