paper-with-me

홈 › Papers

Training Vision Transformers for Semi-Supervised Semantic Segmentation

2024-01-01 · CVPR 2024 1 · Xinting Hu, Li Jiang, Bernt Schiele

We present S4Former a novel approach to training Vision Transformers for Semi-Supervised Semantic Segmentation (S4). At its core S4Former employs a Vision Transformer within a classic teacher-student framework and then leverages three novel technical ingredients: PatchShuffle as a parameter-free perturbation technique Patch-Adaptive Self-Attention (PASA) as a fine-grained feature modulation method and the innovative Negative Class Ranking (NCR) regularization loss. Based on these regularization modules aligned with Transformer-specific characteristics across the image input feature and output dimensions S4Former exploits the Transformer's ability to capture and differentiate consistent global contextual information in unlabeled images. Overall S4Former not only defines a new state of the art in S4 but also maintains a streamlined and scalable architecture. Being readily compatible with existing frameworks S4Former achieves strong improvements (up to 4.9%) on benchmarks like Pascal VOC 2012 COCO and Cityscapes with varying numbers of labeled data. The code is at https://github.com/JoyHuYY1412/S4Former.

📄 PDF Abstract BibTeX

Code (1)

joyhuyy1412/s4former 공식 구현

Tasks

Semantic SegmentationSemi-Supervised Semantic Segmentation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Residual Connection 설명 없음
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 $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Adam 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

Semi-Supervised Vision Transformers

2021-11-22 · Zejia Weng, Xitong Yang, Ang Li, Zuxuan Wu 외

We study the training of Vision Transformers for semi-supervised image classification. Transformers have recently demonstrated impressive performance on a multitude of supervised learning tasks. Surprisingly, we show Vis…

image-classificationImage ClassificationInductive BiasSemi-Supervised Image Classification

Semi-supervised Vision Transformers at Scale

2022-08-11 · Zhaowei Cai, Avinash Ravichandran, Paolo Favaro, Manchen Wang 외

We study semi-supervised learning (SSL) for vision transformers (ViT), an under-explored topic despite the wide adoption of the ViT architectures to different tasks. To tackle this problem, we propose a new SSL pipeline,…

Inductive BiasSemi-Supervised Image Classification

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 외

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…

Data AugmentationDiversityImage AugmentationSemantic Segmentation+1

On the Surprising Effectiveness of Transformers in Low-Labeled Video Recognition

2022-09-15 · Farrukh Rahman, Ömer Mubarek, Zsolt Kira

Recently vision transformers have been shown to be competitive with convolution-based methods (CNNs) broadly across multiple vision tasks. The less restrictive inductive bias of transformers endows greater representation…

image-classificationImage ClassificationInductive BiasVideo Classification+1

Lexico-semantic and affective modelling of Spanish poetry: A semi-supervised learning approach

2021-09-09 · Alberto Barbado, María Dolores González, Débora Carrera

Text classification tasks have improved substantially during the last years by the usage of transformers. However, the majority of researches focus on prose texts, with poetry receiving less attention, specially for Span…

SentenceSentence Embeddingstext-classificationText Classification