Domain-Specific Block Selection and Paired-View Pseudo-Labeling for Online Test-Time Adaptation

• URL: http://arxiv.org/abs/2404.10966v3
• Date: Tue, 7 May 2024 08:09:13 GMT
• Title: Domain-Specific Block Selection and Paired-View Pseudo-Labeling for Online Test-Time Adaptation
• Authors: Yeonguk Yu, Sungho Shin, Seunghyeok Back, Minhwan Ko, Sangjun Noh, Kyoobin Lee,
• Abstract summary: Test-time adaptation (TTA) aims to adapt a pre-trained model to a new test domain without access to source data after deployment. Existing approaches rely on self-training with pseudo-labels since ground-truth cannot be obtained from test data. We propose DPLOT, a simple yet effective TTA framework that consists of two components: (1) domain-specific block selection and (2) pseudo-label generation using paired-view images.
• Score: 6.64353332639395
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Test-time adaptation (TTA) aims to adapt a pre-trained model to a new test domain without access to source data after deployment. Existing approaches typically rely on self-training with pseudo-labels since ground-truth cannot be obtained from test data. Although the quality of pseudo labels is important for stable and accurate long-term adaptation, it has not been previously addressed. In this work, we propose DPLOT, a simple yet effective TTA framework that consists of two components: (1) domain-specific block selection and (2) pseudo-label generation using paired-view images. Specifically, we select blocks that involve domain-specific feature extraction and train these blocks by entropy minimization. After blocks are adjusted for current test domain, we generate pseudo-labels by averaging given test images and corresponding flipped counterparts. By simply using flip augmentation, we prevent a decrease in the quality of the pseudo-labels, which can be caused by the domain gap resulting from strong augmentation. Our experimental results demonstrate that DPLOT outperforms previous TTA methods in CIFAR10-C, CIFAR100-C, and ImageNet-C benchmarks, reducing error by up to 5.4%, 9.1%, and 2.9%, respectively. Also, we provide an extensive analysis to demonstrate effectiveness of our framework. Code is available at https://github.com/gist-ailab/domain-specific-block-selection-and-paired-view-pseudo-labeling-for-on line-TTA.

Related papers

• Trust And Balance: Few Trusted Samples Pseudo-Labeling and Temperature Scaled Loss for Effective Source-Free Unsupervised Domain Adaptation [16.5799094981322]
  We introduce Few Trusted Samples Pseudo-labeling (FTSP) and Temperature Scaled Adaptive Loss (TSAL) FTSP employs a limited subset of trusted samples from the target data to construct a classifier to infer pseudo-labels for the entire domain. TSAL is designed with a unique dual temperature scheduling, adeptly balance diversity, discriminability, and the incorporation of pseudo-labels.
  arXiv  Detail & Related papers  (2024-09-01T15:09:14Z)
• Less is More: Pseudo-Label Filtering for Continual Test-Time Adaptation [13.486951040331899]
  Continual Test-Time Adaptation (CTTA) aims to adapt a pre-trained model to a sequence of target domains during the test phase without accessing the source data. Existing methods rely on constructing pseudo-labels for all samples and updating the model through self-training. We propose Pseudo Labeling Filter (PLF) to improve the quality of pseudo-labels.
  arXiv  Detail & Related papers  (2024-06-03T04:09:36Z)
• Decoupled Prototype Learning for Reliable Test-Time Adaptation [50.779896759106784]
  Test-time adaptation (TTA) is a task that continually adapts a pre-trained source model to the target domain during inference. One popular approach involves fine-tuning model with cross-entropy loss according to estimated pseudo-labels. This study reveals that minimizing the classification error of each sample causes the cross-entropy loss's vulnerability to label noise. We propose a novel Decoupled Prototype Learning (DPL) method that features prototype-centric loss computation.
  arXiv  Detail & Related papers  (2024-01-15T03:33:39Z)
• Feature Alignment and Uniformity for Test Time Adaptation [8.209137567840811]
  Test time adaptation aims to adapt deep neural networks when receiving out of distribution test domain samples. In this setting, the model can only access online unlabeled test samples and pre-trained models on the training domains.
  arXiv  Detail & Related papers  (2023-03-20T06:44:49Z)
• Test-time Adaptation vs. Training-time Generalization: A Case Study in Human Instance Segmentation using Keypoints Estimation [48.30744831719513]
  We consider the problem of improving the human instance segmentation mask quality for a given test image using keypoints estimation. The first approach is a test-time adaptation (TTA) method, where we allow test-time modification of the segmentation network's weights using a single unlabeled test image. The second approach is a training-time generalization (TTG) method, where we permit offline access to the labeled source dataset but not the test-time modification of weights.
  arXiv  Detail & Related papers  (2022-12-12T20:56:25Z)
• Cycle Label-Consistent Networks for Unsupervised Domain Adaptation [57.29464116557734]
  Domain adaptation aims to leverage a labeled source domain to learn a classifier for the unlabeled target domain with a different distribution. We propose a simple yet efficient domain adaptation method, i.e. Cycle Label-Consistent Network (CLCN), by exploiting the cycle consistency of classification label. We demonstrate the effectiveness of our approach on MNIST-USPS-SVHN, Office-31, Office-Home and Image CLEF-DA benchmarks.
  arXiv  Detail & Related papers  (2022-05-27T13:09:08Z)
• Target and Task specific Source-Free Domain Adaptive Image Segmentation [73.78898054277538]
  We propose a two-stage approach for source-free domain adaptive image segmentation. We focus on generating target-specific pseudo labels while suppressing high entropy regions. In the second stage, we focus on adapting the network for task-specific representation.
  arXiv  Detail & Related papers  (2022-03-29T17:50:22Z)
• A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data [69.091485888121]
  Unsupervised domain adaptation assumes that source and target domain data are freely available and usually trained together to reduce the domain gap. We propose a source data-free domain adaptive object detection (SFOD) framework via modeling it into a problem of learning with noisy labels.
  arXiv  Detail & Related papers  (2020-12-10T01:42:35Z)
• Coping with Label Shift via Distributionally Robust Optimisation [72.80971421083937]
  We propose a model that minimises an objective based on distributionally robust optimisation (DRO) We then design and analyse a gradient descent-proximal mirror ascent algorithm tailored for large-scale problems to optimise the proposed objective.
  arXiv  Detail & Related papers  (2020-10-23T08:33:04Z)

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.