STFAR: Improving Object Detection Robustness at Test-Time by Self-Training with Feature Alignment Regularization

• URL: http://arxiv.org/abs/2303.17937v1
• Date: Fri, 31 Mar 2023 10:04:44 GMT
• Title: STFAR: Improving Object Detection Robustness at Test-Time by Self-Training with Feature Alignment Regularization
• Authors: Yijin Chen, Xun Xu, Yongyi Su, Kui Jia
• Abstract summary: Domain adaptation helps generalizing object detection models to target domain data with distribution shift. We explore adapting an object detection model at test-time, a.k.a. test-time adaptation (TTAOD) Our proposed method sets the state-of-the-art on test-time adaptive object detection task.
• Score: 35.16122933158808
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Domain adaptation helps generalizing object detection models to target domain data with distribution shift. It is often achieved by adapting with access to the whole target domain data. In a more realistic scenario, target distribution is often unpredictable until inference stage. This motivates us to explore adapting an object detection model at test-time, a.k.a. test-time adaptation (TTA). In this work, we approach test-time adaptive object detection (TTAOD) from two perspective. First, we adopt a self-training paradigm to generate pseudo labeled objects with an exponential moving average model. The pseudo labels are further used to supervise adapting source domain model. As self-training is prone to incorrect pseudo labels, we further incorporate aligning feature distributions at two output levels as regularizations to self-training. To validate the performance on TTAOD, we create benchmarks based on three standard object detection datasets and adapt generic TTA methods to object detection task. Extensive evaluations suggest our proposed method sets the state-of-the-art on test-time adaptive object detection task.

Related papers

• Weakly Supervised Test-Time Domain Adaptation for Object Detection [23.89166024655107]
  In some applications such as surveillance, there is usually a human operator overseeing the system's operation. We propose to involve the operator in test-time domain adaptation to raise the performance of object detection beyond what is achievable by fully automated adaptation. We show that the proposed method outperforms existing works, demonstrating a great benefit of human-in-the-loop test-time domain adaptation.
  arXiv  Detail & Related papers  (2024-07-08T04:44:42Z)
• What, How, and When Should Object Detectors Update in Continually Changing Test Domains? [34.13756022890991]
  Test-time adaptation algorithms have been proposed to adapt the model online while inferring test data. We propose a novel online adaption approach for object detection in continually changing test domains. Our approach surpasses baselines on widely used benchmarks, achieving improvements of up to 4.9%p and 7.9%p in mAP.
  arXiv  Detail & Related papers  (2023-12-12T07:13:08Z)
• TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation [86.80589902825196]
  We propose a method of test-time adaptation for category-level object pose estimation called TTA-COPE. We design a pose ensemble approach with a self-training loss using pose-aware confidence. Our approach processes the test data in a sequential, online manner, and it does not require access to the source domain at runtime.
  arXiv  Detail & Related papers  (2023-03-29T14:34:54Z)
• D2DF2WOD: Learning Object Proposals for Weakly-Supervised Object Detection via Progressive Domain Adaptation [25.41133780678981]
  D2DF2WOD is a Fully-to-Weakly Supervised Object Detection framework. It uses synthetic data, annotated with precise object localization, to supplement a natural image target domain. Our method results in consistently improved object detection and localization compared with state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-12-02T18:58:03Z)
• CAFA: Class-Aware Feature Alignment for Test-Time Adaptation [50.26963784271912]
  Test-time adaptation (TTA) aims to address this challenge by adapting a model to unlabeled data at test time. We propose a simple yet effective feature alignment loss, termed as Class-Aware Feature Alignment (CAFA), which simultaneously encourages a model to learn target representations in a class-discriminative manner.
  arXiv  Detail & Related papers  (2022-06-01T03:02:07Z)
• Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection [79.89082006155135]
  Unsupervised Domain Adaptation (UDA) is an effective approach to tackle the issue of domain shift. UDA methods try to align the source and target representations to improve the generalization on the target domain. The Source-Free Adaptation Domain (SFDA) setting aims to alleviate these concerns by adapting a source-trained model for the target domain without requiring access to the source data.
  arXiv  Detail & Related papers  (2022-03-29T17:50:43Z)
• Interactron: Embodied Adaptive Object Detection [18.644357684104662]
  We propose Interactron, a method for adaptive object detection in an interactive setting. Our idea is to continue training during inference and adapt the model at test time without any explicit supervision via interacting with the environment.
  arXiv  Detail & Related papers  (2022-02-01T18:56:14Z)
• Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection [85.11649974840758]
  3D object detection networks tend to be biased towards the data they are trained on. We propose a single-frame approach for source-free, unsupervised domain adaptation of lidar-based 3D object detectors.
  arXiv  Detail & Related papers  (2021-11-30T18:42:42Z)
• Robust Object Detection via Instance-Level Temporal Cycle Confusion [89.1027433760578]
  We study the effectiveness of auxiliary self-supervised tasks to improve the out-of-distribution generalization of object detectors. Inspired by the principle of maximum entropy, we introduce a novel self-supervised task, instance-level temporal cycle confusion (CycConf) For each object, the task is to find the most different object proposals in the adjacent frame in a video and then cycle back to itself for self-supervision.
  arXiv  Detail & Related papers  (2021-04-16T21:35:08Z)
• 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.