Attention-based Class-Conditioned Alignment for Multi-Source Domain Adaptation of Object Detectors
- URL: http://arxiv.org/abs/2403.09918v5
- Date: Wed, 11 Dec 2024 19:55:33 GMT
- Title: Attention-based Class-Conditioned Alignment for Multi-Source Domain Adaptation of Object Detectors
- Authors: Atif Belal, Akhil Meethal, Francisco Perdigon Romero, Marco Pedersoli, Eric Granger,
- Abstract summary: Domain adaptation methods for object detection (OD) strive to mitigate the impact of distribution shifts by promoting feature alignment across source and target domains.
MSDA allows leveraging multiple annotated source datasets and unlabeled target data to improve the accuracy and robustness of the detection model.
Most state-of-the-art MSDA methods for OD perform feature alignment in a class-agnostic manner.
We propose an attention-based class-conditioned alignment method for MSDA, designed to align instances of each object category across domains.
- Score: 11.616494893839757
- License:
- Abstract: Domain adaptation methods for object detection (OD) strive to mitigate the impact of distribution shifts by promoting feature alignment across source and target domains. Multi-source domain adaptation (MSDA) allows leveraging multiple annotated source datasets and unlabeled target data to improve the accuracy and robustness of the detection model. Most state-of-the-art MSDA methods for OD perform feature alignment in a class-agnostic manner. This is challenging since the objects have unique modality information due to variations in object appearance across domains. A recent prototype-based approach proposed a class-wise alignment, yet it suffers from error accumulation caused by noisy pseudo-labels that can negatively affect adaptation with imbalanced data. To overcome these limitations, we propose an attention-based class-conditioned alignment method for MSDA, designed to align instances of each object category across domains. In particular, an attention module combined with an adversarial domain classifier allows learning domain-invariant and class-specific instance representations. Experimental results on multiple benchmarking MSDA datasets indicate that our method outperforms state-of-the-art methods and exhibits robustness to class imbalance, achieved through a conceptually simple class-conditioning strategy. Our code is available at: https://github.com/imatif17/ACIA.
Related papers
- 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.
Existing approaches employ adversarial learning to align the distributions of the source and target domains as a whole.
We propose a differential feature alignment strategy to overcome the shortcoming.
arXiv Detail & Related papers (2024-12-17T11:52:10Z) - 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) - Domain Attention Consistency for Multi-Source Domain Adaptation [100.25573559447551]
Key design is a feature channel attention module, which aims to identify transferable features (attributes)
Experiments on three MSDA benchmarks show that our DAC-Net achieves new state of the art performance on all of them.
arXiv Detail & Related papers (2021-11-06T15:56:53Z) - Seeking Similarities over Differences: Similarity-based Domain Alignment
for Adaptive Object Detection [86.98573522894961]
We propose a framework that generalizes the components commonly used by Unsupervised Domain Adaptation (UDA) algorithms for detection.
Specifically, we propose a novel UDA algorithm, ViSGA, that leverages the best design choices and introduces a simple but effective method to aggregate features at instance-level.
We show that both similarity-based grouping and adversarial training allows our model to focus on coarsely aligning feature groups, without being forced to match all instances across loosely aligned domains.
arXiv Detail & Related papers (2021-10-04T13:09:56Z) - Semantic Concentration for Domain Adaptation [23.706231329913113]
Domain adaptation (DA) paves the way for label annotation and dataset bias issues by the knowledge transfer from a label-rich source domain to a related but unlabeled target domain.
A mainstream of DA methods is to align the feature distributions of the two domains.
We propose Semantic Concentration for Domain Adaptation to encourage the model to concentrate on the most principal features.
arXiv Detail & Related papers (2021-08-12T13:04:36Z) - Semi-Supervised Domain Adaptation with Prototypical Alignment and
Consistency Learning [86.6929930921905]
This paper studies how much it can help address domain shifts if we further have a few target samples labeled.
To explore the full potential of landmarks, we incorporate a prototypical alignment (PA) module which calculates a target prototype for each class from the landmarks.
Specifically, we severely perturb the labeled images, making PA non-trivial to achieve and thus promoting model generalizability.
arXiv Detail & Related papers (2021-04-19T08:46:08Z) - Instance Level Affinity-Based Transfer for Unsupervised Domain
Adaptation [74.71931918541748]
We propose an instance affinity based criterion for source to target transfer during adaptation, called ILA-DA.
We first propose a reliable and efficient method to extract similar and dissimilar samples across source and target, and utilize a multi-sample contrastive loss to drive the domain alignment process.
We verify the effectiveness of ILA-DA by observing consistent improvements in accuracy over popular domain adaptation approaches on a variety of benchmark datasets.
arXiv Detail & Related papers (2021-04-03T01:33:14Z) - Surprisingly Simple Semi-Supervised Domain Adaptation with Pretraining
and Consistency [93.89773386634717]
Visual domain adaptation involves learning to classify images from a target visual domain using labels available in a different source domain.
We show that in the presence of a few target labels, simple techniques like self-supervision (via rotation prediction) and consistency regularization can be effective without any adversarial alignment to learn a good target classifier.
Our Pretraining and Consistency (PAC) approach, can achieve state of the art accuracy on this semi-supervised domain adaptation task, surpassing multiple adversarial domain alignment methods, across multiple datasets.
arXiv Detail & Related papers (2021-01-29T18:40:17Z) - Cross-domain Detection via Graph-induced Prototype Alignment [114.8952035552862]
We propose a Graph-induced Prototype Alignment (GPA) framework to seek for category-level domain alignment.
In addition, in order to alleviate the negative effect of class-imbalance on domain adaptation, we design a Class-reweighted Contrastive Loss.
Our approach outperforms existing methods with a remarkable margin.
arXiv Detail & Related papers (2020-03-28T17:46:55Z)
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.