Mitigating Context Bias in Domain Adaptation for Object Detection using Mask Pooling

• URL: http://arxiv.org/abs/2505.18446v1
• Date: Sat, 24 May 2025 01:05:20 GMT
• Title: Mitigating Context Bias in Domain Adaptation for Object Detection using Mask Pooling
• Authors: Hojun Son, Asma Almutairi, Arpan Kusari,
• Abstract summary: Context bias refers to the association between the foreground objects and background during the object detection training process.<n>We provide a causal view of the context bias, pointing towards the pooling operation in the convolution network architecture as the possible source of this bias.<n>We present an alternative, Mask Pooling, which uses an additional input of foreground masks, to separate the pooling process in the respective foreground and background regions.
• Score: 1.1060425537315088
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Context bias refers to the association between the foreground objects and background during the object detection training process. Various methods have been proposed to minimize the context bias when applying the trained model to an unseen domain, known as domain adaptation for object detection (DAOD). But a principled approach to understand why the context bias occurs and how to remove it has been missing. In this work, we provide a causal view of the context bias, pointing towards the pooling operation in the convolution network architecture as the possible source of this bias. We present an alternative, Mask Pooling, which uses an additional input of foreground masks, to separate the pooling process in the respective foreground and background regions and show that this process leads the trained model to detect objects in a more robust manner under different domains. We also provide a benchmark designed to create an ultimate test for DAOD, using foregrounds in the presence of absolute random backgrounds, to analyze the robustness of the intended trained models. Through these experiments, we hope to provide a principled approach for minimizing context bias under domain shift.

Related papers

• EraseLoRA: MLLM-Driven Foreground Exclusion and Background Subtype Aggregation for Dataset-Free Object Removal [10.015328934927062]
  We propose EraseLoRA, a dataset-free framework that replaces attention surgery with background-aware reasoning and test-time adaptation.<n>First, Background-aware Foreground Exclusion (BFE), uses a multimodal large-language models to separate target foreground, non-target foregrounds, and clean background from a single image-mask pair without paired supervision.<n>Second, Background-aware Reconstruction with Subtype Aggregation (BRSA), performs test-time optimization that treats inferred background subtypes as complementary pieces.
  arXiv  Detail & Related papers  (2025-12-25T07:34:38Z)
• ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition [52.537021302246664]
  Action recognition models often suffer from background bias (i.e., inferring actions based on background cues) and foreground bias (i.e., relying on subject appearance)<n>We propose ALBAR, a novel adversarial training method that mitigates foreground and background biases without requiring specialized knowledge of the bias attributes.<n>We evaluate our method on established background and foreground bias protocols, setting a new state-of-the-art and strongly improving combined debiasing performance by over 12% absolute on HMDB51.
  arXiv  Detail & Related papers  (2025-01-31T20:47:06Z)
• Differential Alignment for Domain Adaptive Object Detection [13.664876152118165]
  Domain adaptive object detection (DAOD) aims to generalize an object detector trained on labeled source-domain data to a target domain without annotations.<n>Existing approaches employ adversarial learning to align the distributions of the source and target domains as a whole.<n>We propose a differential feature alignment strategy to overcome the shortcoming.
  arXiv  Detail & Related papers  (2024-12-17T11:52:10Z)
• Quantifying Context Bias in Domain Adaptation for Object Detection [1.1060425537315088]
  Domain adaptation for object detection (DAOD) seeks to transfer a trained model from a source to a target domain.<n>We analyze changes in background features during adaptation and how context bias is represented in different domains.<n>We find that state-of-the-art domain adaptation methods exhibit some form of context bias and apply a potentially simple way to alleviate the context bias.
  arXiv  Detail & Related papers  (2024-09-23T03:01:50Z)
• Consistency Regularisation for Unsupervised Domain Adaptation in Monocular Depth Estimation [15.285720572043678]
  We formulate unsupervised domain adaptation for monocular depth estimation as a consistency-based semi-supervised learning problem. We introduce a pairwise loss function that regularises predictions on the source domain while enforcing consistency across multiple augmented views. In our experiments, we rely on the standard depth estimation benchmarks KITTI and NYUv2 to demonstrate state-of-the-art results.
  arXiv  Detail & Related papers  (2024-05-27T23:32:06Z)
• Diffusion-Based Particle-DETR for BEV Perception [94.88305708174796]
  Bird-Eye-View (BEV) is one of the most widely-used scene representations for visual perception in Autonomous Vehicles (AVs) Recent diffusion-based methods offer a promising approach to uncertainty modeling for visual perception but fail to effectively detect small objects in the large coverage of the BEV. Here, we address this problem by combining the diffusion paradigm with current state-of-the-art 3D object detectors in BEV.
  arXiv  Detail & Related papers  (2023-12-18T09:52:14Z)
• Proposal-Level Unsupervised Domain Adaptation for Open World Unbiased Detector [35.334125159092025]
  We build an unbiased foreground predictor by re-formulating the task under Unsupervised Domain Adaptation. We adopt the simple and effective self-training method to learn a predictor based on the domain-invariant foreground features. Our approach's pipeline can adapt to various detection frameworks and UDA methods, empirically validated by OWOD evaluation.
  arXiv  Detail & Related papers  (2023-11-04T07:46:45Z)
• RAIN: RegulArization on Input and Network for Black-Box Domain Adaptation [80.03883315743715]
  Source-free domain adaptation transits the source-trained model towards target domain without exposing the source data. This paradigm is still at risk of data leakage due to adversarial attacks on the source model. We propose a novel approach named RAIN (RegulArization on Input and Network) for Black-Box domain adaptation from both input-level and network-level regularization.
  arXiv  Detail & Related papers  (2022-08-22T18:18:47Z)
• Self-Supervised Training with Autoencoders for Visual Anomaly Detection [61.62861063776813]
  We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. We adapt a self-supervised learning regime that exploits discriminative information during training but focuses on the submanifold of normal examples. We achieve a new state-of-the-art result on the MVTec AD dataset -- a challenging benchmark for visual anomaly detection in the manufacturing domain.
  arXiv  Detail & Related papers  (2022-06-23T14:16:30Z)
• 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)
• Deep Semantic Matching with Foreground Detection and Cycle-Consistency [103.22976097225457]
  We address weakly supervised semantic matching based on a deep network. We explicitly estimate the foreground regions to suppress the effect of background clutter. We develop cycle-consistent losses to enforce the predicted transformations across multiple images to be geometrically plausible and consistent.
  arXiv  Detail & Related papers  (2020-03-31T22:38:09Z)
• Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation [102.67010690592011]
  Unsupervised adaptationUDA (UDA) aims to leverage the knowledge learned from a labeled source dataset to solve similar tasks in a new unlabeled domain. Prior UDA methods typically require to access the source data when learning to adapt the model. This work tackles a practical setting where only a trained source model is available and how we can effectively utilize such a model without source data to solve UDA problems.
  arXiv  Detail & Related papers  (2020-02-20T03:13:58Z)
• Unsupervised Domain Adaptive Object Detection using Forward-Backward Cyclic Adaptation [13.163271874039191]
  We present a novel approach to perform the unsupervised domain adaptation for object detection through forward-backward cyclic (FBC) training. Recent adversarial training based domain adaptation methods have shown their effectiveness on minimizing domain discrepancy via marginal feature distributions alignment. We propose Forward-Backward Cyclic Adaptation, which iteratively computes adaptation from source to target via backward hopping and from target to source via forward passing.
  arXiv  Detail & Related papers  (2020-02-03T06:24:58Z)

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.