Domain-Conditioned Transformer for Fully Test-time Adaptation

• URL: http://arxiv.org/abs/2410.10442v1
• Date: Mon, 14 Oct 2024 12:36:27 GMT
• Title: Domain-Conditioned Transformer for Fully Test-time Adaptation
• Authors: Yushun Tang, Shuoshuo Chen, Jiyuan Jia, Yi Zhang, Zhihai He,
• Abstract summary: fully test-time adaptation aims to adapt a network model online based on sequential analysis of input samples during the inference stage. We observe that, when applying a transformer network model into a new domain, the self-attention profiles of image samples in the target domain deviate significantly from those in the source domain. We propose a new structure for the self-attention modules in the transformer. Specifically, we incorporate three domain-conditioning vectors, called domain conditioners, into the query, key, and value components of the self-attention module.
• Score: 18.51468880167399
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fully test-time adaptation aims to adapt a network model online based on sequential analysis of input samples during the inference stage. We observe that, when applying a transformer network model into a new domain, the self-attention profiles of image samples in the target domain deviate significantly from those in the source domain, which results in large performance degradation during domain changes. To address this important issue, we propose a new structure for the self-attention modules in the transformer. Specifically, we incorporate three domain-conditioning vectors, called domain conditioners, into the query, key, and value components of the self-attention module. We learn a network to generate these three domain conditioners from the class token at each transformer network layer. We find that, during fully online test-time adaptation, these domain conditioners at each transform network layer are able to gradually remove the impact of domain shift and largely recover the original self-attention profile. Our extensive experimental results demonstrate that the proposed domain-conditioned transformer significantly improves the online fully test-time domain adaptation performance and outperforms existing state-of-the-art methods by large margins.

Related papers

• DAPoinTr: Domain Adaptive Point Transformer for Point Cloud Completion [18.964211071984856]
  We propose a pioneering Domain Adaptive Point Transformer (DAPoinTr) framework for point cloud completion. DAPoinTr consists of three key components: Domain Query-based Feature Alignment (DQFA), Point Token-wise Feature alignment (PTFA), and Voted Prediction Consistency (VPC)
  arXiv  Detail & Related papers  (2024-12-26T05:16:54Z)
• TransAdapter: Vision Transformer for Feature-Centric Unsupervised Domain Adaptation [0.3277163122167433]
  Unsupervised Domain Adaptation (UDA) aims to utilize labeled data from a source domain to solve tasks in an unlabeled target domain. Traditional CNN-based methods struggle to fully capture complex domain relationships. We propose a novel UDA approach leveraging the Swin Transformer with three key modules.
  arXiv  Detail & Related papers  (2024-12-05T11:11:39Z)
• ExpPoint-MAE: Better interpretability and performance for self-supervised point cloud transformers [7.725095281624494]
  We evaluate the effectiveness of Masked Autoencoding as a pretraining scheme, and explore Momentum Contrast as an alternative. We observe that the transformer learns to attend to semantically meaningful regions, indicating that pretraining leads to a better understanding of the underlying geometry.
  arXiv  Detail & Related papers  (2023-06-19T09:38:21Z)
• Exploring Consistency in Cross-Domain Transformer for Domain Adaptive Semantic Segmentation [51.10389829070684]
  Domain gap can cause discrepancies in self-attention. Due to this gap, the transformer attends to spurious regions or pixels, which deteriorates accuracy on the target domain. We propose adaptation on attention maps with cross-domain attention layers.
  arXiv  Detail & Related papers  (2022-11-27T02:40:33Z)
• UniDAformer: Unified Domain Adaptive Panoptic Segmentation Transformer via Hierarchical Mask Calibration [49.16591283724376]
  We design UniDAformer, a unified domain adaptive panoptic segmentation transformer that is simple but can achieve domain adaptive instance segmentation and semantic segmentation simultaneously within a single network. UniDAformer introduces Hierarchical Mask (HMC) that rectifies inaccurate predictions at the level of regions, superpixels and annotated pixels via online self-training on the fly. It has three unique features: 1) it enables unified domain adaptive panoptic adaptation; 2) it mitigates false predictions and improves domain adaptive panoptic segmentation effectively; 3) it is end-to-end trainable with a much simpler training and inference pipeline.
  arXiv  Detail & Related papers  (2022-06-30T07:32:23Z)
• Safe Self-Refinement for Transformer-based Domain Adaptation [73.8480218879]
  Unsupervised Domain Adaptation (UDA) aims to leverage a label-rich source domain to solve tasks on a related unlabeled target domain. It is a challenging problem especially when a large domain gap lies between the source and target domains. We propose a novel solution named SSRT (Safe Self-Refinement for Transformer-based domain adaptation), which brings improvement from two aspects.
  arXiv  Detail & Related papers  (2022-04-16T00:15:46Z)
• Towards Unsupervised Domain Adaptation via Domain-Transformer [0.0]
  We propose the Domain-Transformer (DoT) for Unsupervised Domain Adaptation (UDA) DoT integrates the CNN-backbones and the core attention mechanism of Transformers from a new perspective. It achieves the local semantic consistency across domains, where the domain-level attention and manifold regularization are explored.
  arXiv  Detail & Related papers  (2022-02-24T02:30:15Z)
• Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers [141.70707071815653]
  We propose a novel Sequence Feature Alignment (SFA) method that is specially designed for the adaptation of detection transformers. SFA consists of a domain query-based feature alignment (DQFA) module and a token-wise feature alignment (TDA) module. Experiments on three challenging benchmarks show that SFA outperforms state-of-the-art domain adaptive object detection methods.
  arXiv  Detail & Related papers  (2021-07-27T07:17:12Z)
• AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection [90.18752912204778]
  Unsupervised domain adaptation for object detection is a challenging problem with many real-world applications. We propose a novel augmented feature alignment network (AFAN) which integrates intermediate domain image generation and domain-adversarial training. Our approach significantly outperforms the state-of-the-art methods on standard benchmarks for both similar and dissimilar domain adaptations.
  arXiv  Detail & Related papers  (2021-06-10T05:01:20Z)
• Unsupervised Domain Adaptation for Spatio-Temporal Action Localization [69.12982544509427]
  S-temporal action localization is an important problem in computer vision. We propose an end-to-end unsupervised domain adaptation algorithm. We show that significant performance gain can be achieved when spatial and temporal features are adapted separately or jointly.
  arXiv  Detail & Related papers  (2020-10-19T04:25:10Z)

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.