CLDA-YOLO: Visual Contrastive Learning Based Domain Adaptive YOLO Detector

• URL: http://arxiv.org/abs/2412.11812v1
• Date: Mon, 16 Dec 2024 14:25:52 GMT
• Title: CLDA-YOLO: Visual Contrastive Learning Based Domain Adaptive YOLO Detector
• Authors: Tianheng Qiu, Ka Lung Law, Guanghua Pan, Jufei Wang, Xin Gao, Xuan Huang, Hu Wei,
• Abstract summary: Unsupervised domain adaptive (UDA) algorithms can markedly enhance the performance of object detectors under conditions of domain shifts. We present an unsupervised domain adaptive YOLO detector based on visual contrastive learning (CLDA-YOLO)
• Score: 10.419327930845922
• License:
• Abstract: Unsupervised domain adaptive (UDA) algorithms can markedly enhance the performance of object detectors under conditions of domain shifts, thereby reducing the necessity for extensive labeling and retraining. Current domain adaptive object detection algorithms primarily cater to two-stage detectors, which tend to offer minimal improvements when directly applied to single-stage detectors such as YOLO. Intending to benefit the YOLO detector from UDA, we build a comprehensive domain adaptive architecture using a teacher-student cooperative system for the YOLO detector. In this process, we propose uncertainty learning to cope with pseudo-labeling generated by the teacher model with extreme uncertainty and leverage dynamic data augmentation to asymptotically adapt the teacher-student system to the environment. To address the inability of single-stage object detectors to align at multiple stages, we utilize a unified visual contrastive learning paradigm that aligns instance at backbone and head respectively, which steadily improves the robustness of the detectors in cross-domain tasks. In summary, we present an unsupervised domain adaptive YOLO detector based on visual contrastive learning (CLDA-YOLO), which achieves highly competitive results across multiple domain adaptive datasets without any reduction in inference speed.

Related papers

• Source-Free Domain Adaptation for YOLO Object Detection [12.998403995812298]
  This paper focuses on domain adaptation techniques for real-world vision systems, particularly for the YOLO family of single-shot detectors. Our proposed SFDA method - Source-Free YOLO (SF-YOLO) - relies on a teacher-student framework in which the student receives images with a learned, target domain-specific augmentation. A challenge with self-training using a mean-teacher architecture in the absence of labels is the rapid decline of accuracy due to noisy or drifting pseudo-labels.
  arXiv  Detail & Related papers  (2024-09-25T01:22:10Z)
• DATR: Unsupervised Domain Adaptive Detection Transformer with Dataset-Level Adaptation and Prototypical Alignment [7.768332621617199]
  We introduce a strong DETR-based detector named Domain Adaptive detection TRansformer ( DATR) for unsupervised domain adaptation of object detection. Our proposed DATR incorporates a mean-teacher based self-training framework, utilizing pseudo-labels generated by the teacher model to further mitigate domain bias. Experiments demonstrate superior performance and generalization capabilities of our proposed DATR in multiple domain adaptation scenarios.
  arXiv  Detail & Related papers  (2024-05-20T03:48:45Z)
• Efficient Teacher: Semi-Supervised Object Detection for YOLOv5 [2.2290171169275492]
  One-stage anchor-based detectors lack the structure to generate high-quality or flexible pseudo labels. Dense Detector is a baseline model that extends RetinaNet with dense sampling techniques inspired by YOLOv5. Pseudo Label Assigner makes more refined use of pseudo labels from Dense Detector. Epoch Adaptor is a method that enables a stable and efficient end-to-end semi-supervised training schedule.
  arXiv  Detail & Related papers  (2023-02-15T10:40:19Z)
• SSDA-YOLO: Semi-supervised Domain Adaptive YOLO for Cross-Domain Object Detection [27.02391566687007]
  Domain adaptive object detection (DAD) aims to alleviate transfer performance degradation caused by the cross-domain discrepancy. We propose a novel semi-supervised domain adaptive YOLO (SSDA-YOLO) based method to improve cross-domain detection performance.
  arXiv  Detail & Related papers  (2022-11-04T01:50:13Z)
• Frequency Spectrum Augmentation Consistency for Domain Adaptive Object Detection [107.52026281057343]
  We introduce a Frequency Spectrum Augmentation Consistency (FSAC) framework with four different low-frequency filter operations. In the first stage, we utilize all the original and augmented source data to train an object detector. In the second stage, augmented source and target data with pseudo labels are adopted to perform the self-training for prediction consistency.
  arXiv  Detail & Related papers  (2021-12-16T04:07:01Z)
• UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimation [84.16372642822495]
  We propose an unsupervised domain adaptation (UDA) for category-level object pose estimation, called textbfUDA-COPE. Inspired by the recent multi-modal UDA techniques, the proposed method exploits a teacher-student self-supervised learning scheme to train a pose estimation network without using target domain labels.
  arXiv  Detail & Related papers  (2021-11-24T16:00:48Z)
• Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency [90.71745178767203]
  Deep learning-based 3D object detection has achieved unprecedented success with the advent of large-scale autonomous driving datasets. Existing 3D domain adaptive detection methods often assume prior access to the target domain annotations, which is rarely feasible in the real world. We study a more realistic setting, unsupervised 3D domain adaptive detection, which only utilizes source domain annotations.
  arXiv  Detail & Related papers  (2021-07-23T17:19:23Z)
• Domain Adaptive YOLO for One-Stage Cross-Domain Detection [4.596221278839825]
  Domain Adaptive YOLO (DA-YOLO) is proposed to improve cross-domain performance for one-stage detectors. We evaluate our proposed method on popular datasets like Cityscapes, KITTI, SIM10K and etc.
  arXiv  Detail & Related papers  (2021-06-26T04:17:42Z)
• 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)
• Unsupervised Domain Adaptation in Person re-ID via k-Reciprocal Clustering and Large-Scale Heterogeneous Environment Synthesis [76.46004354572956]
  We introduce an unsupervised domain adaptation approach for person re-identification. Experimental results show that the proposed ktCUDA and SHRED approach achieves an average improvement of +5.7 mAP in re-identification performance.
  arXiv  Detail & Related papers  (2020-01-14T17:43:52Z)

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.