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

• URL: http://arxiv.org/abs/2503.02459v2
• Date: Mon, 10 Mar 2025 12:48:54 GMT
• Title: Exploring Token-Level Augmentation in Vision Transformer for Semi-Supervised Semantic Segmentation
• Authors: Dengke Zhang, Quan Tang, Fagui Liu, Haiqing Mei, C. L. Philip Chen,
• Abstract summary: TokenMix is a data augmentation technique specifically designed for semi-supervised semantic segmentation with Vision Transformers.<n>We propose a dual-branch framework where each branch applies image and feature augmentation to the input image.<n>Results suggest that the proposed method outperforms state-of-the-art algorithms with notably observed accuracy improvement.
• Score: 47.36641636596741
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 contextual 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 image 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 limited fine annotations.

Related papers

• Semi-supervised Semantic Segmentation with Multi-Constraint Consistency Learning [81.02648336552421]
  We propose a Multi-Constraint Consistency Learning approach to facilitate the staged enhancement of the encoder and decoder. Self-adaptive feature masking and noise injection are designed in an instance-specific manner to perturb the features for robust learning of the decoder. Experimental results on Pascal VOC2012 and Cityscapes datasets demonstrate that our proposed MCCL achieves new state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-03-23T03:21:33Z)
• A Spitting Image: Modular Superpixel Tokenization in Vision Transformers [0.0]
  Vision Transformer (ViT) architectures traditionally employ a grid-based approach to tokenization independent of the semantic content of an image. We propose a modular superpixel tokenization strategy which decouples tokenization and feature extraction.
  arXiv  Detail & Related papers  (2024-08-14T17:28:58Z)
• DynaSeg: A Deep Dynamic Fusion Method for Unsupervised Image Segmentation Incorporating Feature Similarity and Spatial Continuity [0.5755004576310334]
  We introduce DynaSeg, an innovative unsupervised image segmentation approach. Unlike traditional methods, DynaSeg employs a dynamic weighting scheme that adapts flexibly to image characteristics. DynaSeg prevents undersegmentation failures where the number of predicted clusters might converge to one.
  arXiv  Detail & Related papers  (2024-05-09T00:30:45Z)
• Masked Image Modeling with Denoising Contrast [30.31920660487222]
  Masked image modeling dominates this line of research with state-of-the-art performance on vision Transformers. We introduce a new pre-training method, ConMIM, to produce simple intra-image inter-patch contrastive constraints. ConMIM-pretrained vision Transformers with various scales achieve promising results on downstream image classification, semantic segmentation, object detection, and instance segmentation tasks.
  arXiv  Detail & Related papers  (2022-05-19T15:22:29Z)
• In-N-Out Generative Learning for Dense Unsupervised Video Segmentation [89.21483504654282]
  In this paper, we focus on the unsupervised Video Object (VOS) task which learns visual correspondence from unlabeled videos. We propose the In-aNd-Out (INO) generative learning from a purely generative perspective, which captures both high-level and fine-grained semantics. Our INO outperforms previous state-of-the-art methods by significant margins.
  arXiv  Detail & Related papers  (2022-03-29T07:56:21Z)
• Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations [61.95114821573875]
  We introduce Plug-In Inversion, which relies on a simple set of augmentations and does not require excessive hyper- parameter tuning. We illustrate the practicality of our approach by inverting Vision Transformers (ViTs) and Multi-Layer Perceptrons (MLPs) trained on the ImageNet dataset.
  arXiv  Detail & Related papers  (2022-01-31T02:12:45Z)
• SeMask: Semantically Masked Transformers for Semantic Segmentation [10.15763397352378]
  SeMask is a framework that incorporates semantic information into the encoder with the help of a semantic attention operation. Our framework achieves a new state-of-the-art of 58.22% mIoU on the ADE20K dataset and improvements of over 3% in the mIoU metric on the Cityscapes dataset.
  arXiv  Detail & Related papers  (2021-12-23T18:56:02Z)
• PSViT: Better Vision Transformer via Token Pooling and Attention Sharing [114.8051035856023]
  We propose a PSViT: a ViT with token Pooling and attention Sharing to reduce the redundancy. Experimental results show that the proposed scheme can achieve up to 6.6% accuracy improvement in ImageNet classification.
  arXiv  Detail & Related papers  (2021-08-07T11:30:54Z)
• Less is More: Pay Less Attention in Vision Transformers [61.05787583247392]
  Less attention vIsion Transformer builds upon the fact that convolutions, fully-connected layers, and self-attentions have almost equivalent mathematical expressions for processing image patch sequences. The proposed LIT achieves promising performance on image recognition tasks, including image classification, object detection and instance segmentation.
  arXiv  Detail & Related papers  (2021-05-29T05:26:07Z)
• Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation [93.83369981759996]
  We propose a self-supervised equivariant attention mechanism (SEAM) to discover additional supervision and narrow the gap. Our method is based on the observation that equivariance is an implicit constraint in fully supervised semantic segmentation. We propose consistency regularization on predicted CAMs from various transformed images to provide self-supervision for network learning.
  arXiv  Detail & Related papers  (2020-04-09T14:57:57Z)
• Unsupervised Bidirectional Cross-Modality Adaptation via Deeply Synergistic Image and Feature Alignment for Medical Image Segmentation [73.84166499988443]
  We present a novel unsupervised domain adaptation framework, named as Synergistic Image and Feature Alignment (SIFA) Our proposed SIFA conducts synergistic alignment of domains from both image and feature perspectives. Experimental results on two different tasks demonstrate that our SIFA method is effective in improving segmentation performance on unlabeled target images.
  arXiv  Detail & Related papers  (2020-02-06T13:49:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.