Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection

• URL: http://arxiv.org/abs/2110.00249v1
• Date: Fri, 1 Oct 2021 08:10:00 GMT
• Title: Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection
• Authors: Muhammad Akhtar Munir, Muhammad Haris Khan, M. Saquib Sarfraz, Mohsen Ali
• Abstract summary: We study adapting trained object detectors to unseen domains manifesting significant variations of object appearance, viewpoints and backgrounds. We propose to leverage model predictive uncertainty to strike the right balance between adversarial feature alignment and class-level alignment.
• Score: 11.091890625685298
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study adapting trained object detectors to unseen domains manifesting significant variations of object appearance, viewpoints and backgrounds. Most current methods align domains by either using image or instance-level feature alignment in an adversarial fashion. This often suffers due to the presence of unwanted background and as such lacks class-specific alignment. A common remedy to promote class-level alignment is to use high confidence predictions on the unlabelled domain as pseudo labels. These high confidence predictions are often fallacious since the model is poorly calibrated under domain shift. In this paper, we propose to leverage model predictive uncertainty to strike the right balance between adversarial feature alignment and class-level alignment. Specifically, we measure predictive uncertainty on class assignments and the bounding box predictions. Model predictions with low uncertainty are used to generate pseudo-labels for self-supervision, whereas the ones with higher uncertainty are used to generate tiles for an adversarial feature alignment stage. This synergy between tiling around the uncertain object regions and generating pseudo-labels from highly certain object regions allows us to capture both the image and instance level context during the model adaptation stage. We perform extensive experiments covering various domain shift scenarios. Our approach improves upon existing state-of-the-art methods with visible margins.

Related papers

• GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Features [68.14842693208465]
  GeneralAD is an anomaly detection framework designed to operate in semantic, near-distribution, and industrial settings. We propose a novel self-supervised anomaly generation module that employs straightforward operations like noise addition and shuffling to patch features. We extensively evaluated our approach on ten datasets, achieving state-of-the-art results in six and on-par performance in the remaining.
  arXiv  Detail & Related papers  (2024-07-17T09:27:41Z)
• Cross Domain Object Detection via Multi-Granularity Confidence Alignment based Mean Teacher [14.715398100791559]
  Cross domain object detection learns an object detector for an unlabeled target domain by transferring knowledge from an annotated source domain. In this study, we find that confidence misalignment of the predictions, including category-level overconfidence, instance-level task confidence inconsistency, and image-level confidence misfocusing, will bring suboptimal performance on the target domain.
  arXiv  Detail & Related papers  (2024-07-10T15:56:24Z)
• Domain Adaptive Object Detection via Balancing Between Self-Training and Adversarial Learning [19.81071116581342]
  Deep learning based object detectors struggle generalizing to a new target domain bearing significant variations in object and background. Current methods align domains by using image or instance-level adversarial feature alignment. We propose to leverage model's predictive uncertainty to strike the right balance between adversarial feature alignment and class-level alignment.
  arXiv  Detail & Related papers  (2023-11-08T16:40:53Z)
• Bi-discriminator Domain Adversarial Neural Networks with Class-Level Gradient Alignment [87.8301166955305]
  We propose a novel bi-discriminator domain adversarial neural network with class-level gradient alignment. BACG resorts to gradient signals and second-order probability estimation for better alignment of domain distributions. In addition, inspired by contrastive learning, we develop a memory bank-based variant, i.e. Fast-BACG, which can greatly shorten the training process.
  arXiv  Detail & Related papers  (2023-10-21T09:53:17Z)
• Digging Into Uncertainty-based Pseudo-label for Robust Stereo Matching [39.959000340261625]
  We propose to dig into uncertainty estimation for robust stereo matching. An uncertainty-based pseudo-label is proposed to adapt the pre-trained model to the new domain. Our method shows strong cross-domain, adapt, and joint generalization and obtains textbf1st place on the stereo task of Robust Vision Challenge 2020.
  arXiv  Detail & Related papers  (2023-07-31T09:11:31Z)
• Adaptive Face Recognition Using Adversarial Information Network [57.29464116557734]
  Face recognition models often degenerate when training data are different from testing data. We propose a novel adversarial information network (AIN) to address it.
  arXiv  Detail & Related papers  (2023-05-23T02:14:11Z)
• Predicting Class Distribution Shift for Reliable Domain Adaptive Object Detection [2.5193191501662144]
  Unsupervised Domain Adaptive Object Detection (UDA-OD) uses unlabelled data to improve the reliability of robotic vision systems in open-world environments. Previous approaches to UDA-OD based on self-training have been effective in overcoming changes in the general appearance of images. We propose a framework for explicitly addressing class distribution shift to improve pseudo-label reliability in self-training.
  arXiv  Detail & Related papers  (2023-02-13T00:46:34Z)
• Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection [34.18382705952121]
  Unlabelled domain adaptive object detection aims to adapt detectors from a labelled source domain to an unsupervised target domain. adversarial learning may impair the alignment of well-aligned samples as it merely aligns the global distributions across domains. We design an uncertainty-aware domain adaptation network (UaDAN) that introduces conditional adversarial learning to align well-aligned and poorly-aligned samples separately.
  arXiv  Detail & Related papers  (2021-02-27T15:04:07Z)
• Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-Identification [64.37745443119942]
  This paper jointly enforces visual and temporal consistency in the combination of a local one-hot classification and a global multi-class classification. Experimental results on three large-scale ReID datasets demonstrate the superiority of proposed method in both unsupervised and unsupervised domain adaptive ReID tasks.
  arXiv  Detail & Related papers  (2020-07-21T14:31:27Z)
• Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation [49.295165476818866]
  This paper focuses on the unsupervised domain adaptation of transferring the knowledge from the source domain to the target domain in the context of semantic segmentation. Existing approaches usually regard the pseudo label as the ground truth to fully exploit the unlabeled target-domain data. This paper proposes to explicitly estimate the prediction uncertainty during training to rectify the pseudo label learning.
  arXiv  Detail & Related papers  (2020-03-08T12:37:19Z)
• A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation [142.31610972922067]
  This work addresses the unsupervised domain adaptation problem, especially in the case of class labels in the target domain being only a subset of those in the source domain. We build on domain adversarial learning and propose a novel domain adaptation method BA$3$US with two new techniques termed Balanced Adversarial Alignment (BAA) and Adaptive Uncertainty Suppression (AUS) Experimental results on multiple benchmarks demonstrate our BA$3$US surpasses state-of-the-arts for partial domain adaptation tasks.
  arXiv  Detail & Related papers  (2020-03-05T11:37:06Z)

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.