paper-with-me

홈 › Papers

Feature Fusion Transferability Aware Transformer for Unsupervised Domain Adaptation

2024-11-10 · Xiaowei Yu, Zhe Huang, Zao Zhang

Unsupervised domain adaptation (UDA) aims to leverage the knowledge learned from labeled source domains to improve performance on the unlabeled target domains. While Convolutional Neural Networks (CNNs) have been dominant in previous UDA methods, recent research has shown promise in applying Vision Transformers (ViTs) to this task. In this study, we propose a novel Feature Fusion Transferability Aware Transformer (FFTAT) to enhance ViT performance in UDA tasks. Our method introduces two key innovations: First, we introduce a patch discriminator to evaluate the transferability of patches, generating a transferability matrix. We integrate this matrix into self-attention, directing the model to focus on transferable patches. Second, we propose a feature fusion technique to fuse embeddings in the latent space, enabling each embedding to incorporate information from all others, thereby improving generalization. These two components work in synergy to enhance feature representation learning. Extensive experiments on widely used benchmarks demonstrate that our method significantly improves UDA performance, achieving state-of-the-art (SOTA) results.

📄 PDF Abstract BibTeX arXiv:2411.07794

Code (2)

Shawey94/WACV2025-FFTAT 공식 구현 pytorch
Shawey94/NoisyNN pytorch

Tasks

Domain AdaptationRepresentation LearningUnsupervised Domain Adaptation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
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…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation

2021-08-12 · Jinyu Yang, Jingjing Liu, Ning Xu, Junzhou Huang

Unsupervised domain adaptation (UDA) aims to transfer the knowledge learnt from a labeled source domain to an unlabeled target domain. Previous work is mainly built upon convolutional neural networks (CNNs) to learn doma…

Domain AdaptationTransfer LearningUnsupervised Domain Adaptation

Transferable-guided Attention Is All You Need for Video Domain Adaptation

2024-07-01 · André Sacilotti, Samuel Felipe dos Santos, Nicu Sebe, Jurandy Almeida

Unsupervised domain adaptation (UDA) in videos is a challenging task that remains not well explored compared to image-based UDA techniques. Although vision transformers (ViT) achieve state-of-the-art performance in many …

AllDomain AdaptationUnsupervised Domain Adaptation

Foreground Guidance and Multi-Layer Feature Fusion for Unsupervised Object Discovery with Transformers

2022-10-24 · Zhiwei Lin, Zengyu Yang, Yongtao Wang

Unsupervised object discovery (UOD) has recently shown encouraging progress with the adoption of pre-trained Transformer features. However, current methods based on Transformers mainly focus on designing the localization…

Objectobject-detectionObject DetectionObject Discovery

Revisiting the Transferability of Supervised Pretraining: an MLP Perspective

2021-12-01 · CVPR 2022 1 · Yizhou Wang, Shixiang Tang, Feng Zhu, Lei Bai 외

The pretrain-finetune paradigm is a classical pipeline in visual learning. Recent progress on unsupervised pretraining methods shows superior transfer performance to their supervised counterparts. This paper revisits thi…

domain classificationimage-classificationImage ClassificationLinear evaluation+3

Improving the Transferability of Supervised Pretraining with an MLP Projector

2021-09-29 · Yizhou Wang, Shixiang Tang, Feng Zhu, Lei Bai 외

The pretrain-finetune paradigm is a classical pipeline in visual learning. Recent progress on unsupervised pretraining methods showed superior transfer performance to their supervised counterparts. While a few works atte…

domain classification