TITAN: Query-Token based Domain Adaptive Adversarial Learning
- URL: http://arxiv.org/abs/2506.21484v1
- Date: Thu, 26 Jun 2025 17:12:58 GMT
- Title: TITAN: Query-Token based Domain Adaptive Adversarial Learning
- Authors: Tajamul Ashraf, Janibul Bashir,
- Abstract summary: We focus on the source-free domain adaptive object detection (SF-DAOD) problem when source data is unavailable during adaptation and the model must adapt to an unlabeled target domain.<n>The majority of approaches for the problem employ a self-supervised approach using a student-teacher (ST) framework where pseudo-labels are generated via a source-pretrained model for further fine-tuning.<n>We observe that the performance of a student model often degrades drastically, due to the collapse of the teacher model, primarily caused by high noise in pseudo-labels.<n>To obtain reliable pseudo-labels, we propose
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We focus on the source-free domain adaptive object detection (SF-DAOD) problem when source data is unavailable during adaptation and the model must adapt to an unlabeled target domain. The majority of approaches for the problem employ a self-supervised approach using a student-teacher (ST) framework where pseudo-labels are generated via a source-pretrained model for further fine-tuning. We observe that the performance of a student model often degrades drastically, due to the collapse of the teacher model, primarily caused by high noise in pseudo-labels, resulting from domain bias, discrepancies, and a significant domain shift across domains. To obtain reliable pseudo-labels, we propose a Target-based Iterative Query-Token Adversarial Network (TITAN), which separates the target images into two subsets: those similar to the source (easy) and those dissimilar (hard). We propose a strategy to estimate variance to partition the target domain. This approach leverages the insight that higher detection variances correspond to higher recall and greater similarity to the source domain. Also, we incorporate query-token-based adversarial modules into a student-teacher baseline framework to reduce the domain gaps between two feature representations. Experiments conducted on four natural imaging datasets and two challenging medical datasets have substantiated the superior performance of TITAN compared to existing state-of-the-art (SOTA) methodologies. We report an mAP improvement of +22.7, +22.2, +21.1, and +3.7 percent over the current SOTA on C2F, C2B, S2C, and K2C benchmarks, respectively.
Related papers
- Unsupervised Domain Adaptive Person Search via Dual Self-Calibration [12.158126976694488]
Unsupervised Domain Adaptive (UDA) person search focuses on employing the model trained on a labeled source domain dataset to a target domain dataset without any additional annotations.<n>Most effective UDA person search methods typically utilize the ground truth of the source domain and pseudo-labels derived from clustering.<n>We propose a Dual Self-Calibration (DSCA) framework for UDA person search that effectively eliminates the interference of noisy pseudo-labels.
arXiv Detail & Related papers (2024-12-21T06:54:00Z) - Focus on Your Target: A Dual Teacher-Student Framework for
Domain-adaptive Semantic Segmentation [210.46684938698485]
We study unsupervised domain adaptation (UDA) for semantic segmentation.
We find that, by decreasing/increasing the proportion of training samples from the target domain, the 'learning ability' is strengthened/weakened.
We propose a novel dual teacher-student (DTS) framework and equip it with a bidirectional learning strategy.
arXiv Detail & Related papers (2023-03-16T05:04:10Z) - Adapting the Mean Teacher for keypoint-based lung registration under
geometric domain shifts [75.51482952586773]
deep neural networks generally require plenty of labeled training data and are vulnerable to domain shifts between training and test data.
We present a novel approach to geometric domain adaptation for image registration, adapting a model from a labeled source to an unlabeled target domain.
Our method consistently improves on the baseline model by 50%/47% while even matching the accuracy of models trained on target data.
arXiv Detail & Related papers (2022-07-01T12:16:42Z) - 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) - Low-confidence Samples Matter for Domain Adaptation [47.552605279925736]
Domain adaptation (DA) aims to transfer knowledge from a label-rich source domain to a related but label-scarce target domain.
We propose a novel contrastive learning method by processing low-confidence samples.
We evaluate the proposed method in both unsupervised and semi-supervised DA settings.
arXiv Detail & Related papers (2022-02-06T15:45:45Z) - Cross-Domain Object Detection via Adaptive Self-Training [45.48690932743266]
We propose a self-training framework called Adaptive Unbiased Teacher (AUT)
AUT uses adversarial learning and weak-strong data augmentation to address domain shift.
We show AUT demonstrates superiority over all existing approaches and even Oracle (fully supervised) models by a large margin.
arXiv Detail & Related papers (2021-11-25T18:50:15Z) - Source-Free Open Compound Domain Adaptation in Semantic Segmentation [99.82890571842603]
In SF-OCDA, only the source pre-trained model and the target data are available to learn the target model.
We propose the Cross-Patch Style Swap (CPSS) to diversify samples with various patch styles in the feature-level.
Our method produces state-of-the-art results on the C-Driving dataset.
arXiv Detail & Related papers (2021-06-07T08:38:41Z) - On Universal Black-Box Domain Adaptation [53.7611757926922]
We study an arguably least restrictive setting of domain adaptation in a sense of practical deployment.
Only the interface of source model is available to the target domain, and where the label-space relations between the two domains are allowed to be different and unknown.
We propose to unify them into a self-training framework, regularized by consistency of predictions in local neighborhoods of target samples.
arXiv Detail & Related papers (2021-04-10T02:21:09Z) - Teacher-Student Consistency For Multi-Source Domain Adaptation [28.576613317253035]
In Multi-Source Domain Adaptation (MSDA), models are trained on samples from multiple source domains and used for inference on a different, target, domain.
We propose Multi-source Student Teacher (MUST), a novel procedure designed to alleviate these issues.
arXiv Detail & Related papers (2020-10-20T06:17:40Z) - Adversarial Bipartite Graph Learning for Video Domain Adaptation [50.68420708387015]
Domain adaptation techniques, which focus on adapting models between distributionally different domains, are rarely explored in the video recognition area.
Recent works on visual domain adaptation which leverage adversarial learning to unify the source and target video representations are not highly effective on the videos.
This paper proposes an Adversarial Bipartite Graph (ABG) learning framework which directly models the source-target interactions.
arXiv Detail & Related papers (2020-07-31T03:48:41Z)
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.