A Pairwise DomMix Attentive Adversarial Network for Unsupervised Domain Adaptive Object Detection
- URL: http://arxiv.org/abs/2407.02835v1
- Date: Wed, 3 Jul 2024 06:25:20 GMT
- Title: A Pairwise DomMix Attentive Adversarial Network for Unsupervised Domain Adaptive Object Detection
- Authors: Jie Shao, Jiacheng Wu, Wenzhong Shen, Cheng Yang,
- Abstract summary: Unsupervised Domain Adaptive Object Detection (DAOD) could adapt a model trained on a source domain to an unlabeled target domain for object detection.
We propose a pairwise attentive adversarial network with a Domain Mixup (DomMix) module to mitigate the aforementioned challenges.
- Score: 18.67853854539245
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Unsupervised Domain Adaptive Object Detection (DAOD) could adapt a model trained on a source domain to an unlabeled target domain for object detection. Existing unsupervised DAOD methods usually perform feature alignments from the target to the source. Unidirectional domain transfer would omit information about the target samples and result in suboptimal adaptation when there are large domain shifts. Therefore, we propose a pairwise attentive adversarial network with a Domain Mixup (DomMix) module to mitigate the aforementioned challenges. Specifically, a deep-level mixup is employed to construct an intermediate domain that allows features from both domains to share their differences. Then a pairwise attentive adversarial network is applied with attentive encoding on both image-level and instance-level features at different scales and optimizes domain alignment by adversarial learning. This allows the network to focus on regions with disparate contextual information and learn their similarities between different domains. Extensive experiments are conducted on several benchmark datasets, demonstrating the superiority of our proposed method.
Related papers
- DDAM-PS: Diligent Domain Adaptive Mixer for Person Search [18.54985960776783]
Person search (PS) is a challenging computer vision problem where the objective is to achieve joint optimization for pedestrian detection and re-identification (ReID)
Previous advancements have shown promising performance in the field under fully and weakly supervised learning fashion.
We propose a diligent domain adaptive mixer (DDAM) for person search (DDAP-PS) framework that aims to bridge a gap to improve knowledge transfer from the labeled source domain to the unlabeled target domain.
arXiv Detail & Related papers (2023-10-31T17:59:14Z) - Compositional Semantic Mix for Domain Adaptation in Point Cloud
Segmentation [65.78246406460305]
compositional semantic mixing represents the first unsupervised domain adaptation technique for point cloud segmentation.
We present a two-branch symmetric network architecture capable of concurrently processing point clouds from a source domain (e.g. synthetic) and point clouds from a target domain (e.g. real-world)
arXiv Detail & Related papers (2023-08-28T14:43:36Z) - Joint Distribution Alignment via Adversarial Learning for Domain
Adaptive Object Detection [11.262560426527818]
Unsupervised domain adaptive object detection aims to adapt a well-trained detector from its original source domain with rich labeled data to a new target domain with unlabeled data.
Recently, mainstream approaches perform this task through adversarial learning, yet still suffer from two limitations.
We propose a joint adaptive detection framework (JADF) to address the above challenges.
arXiv Detail & Related papers (2021-09-19T00:27:08Z) - 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) - Adversarial Dual Distinct Classifiers for Unsupervised Domain Adaptation [67.83872616307008]
Unversarial Domain adaptation (UDA) attempts to recognize the unlabeled target samples by building a learning model from a differently-distributed labeled source domain.
In this paper, we propose a novel Adrial Dual Distincts Network (AD$2$CN) to align the source and target domain data distribution simultaneously with matching task-specific category boundaries.
To be specific, a domain-invariant feature generator is exploited to embed the source and target data into a latent common space with the guidance of discriminative cross-domain alignment.
arXiv Detail & Related papers (2020-08-27T01:29:10Z) - Unsupervised Cross-domain Image Classification by Distance Metric Guided
Feature Alignment [11.74643883335152]
Unsupervised domain adaptation is a promising avenue which transfers knowledge from a source domain to a target domain.
We propose distance metric guided feature alignment (MetFA) to extract discriminative as well as domain-invariant features on both source and target domains.
Our model integrates class distribution alignment to transfer semantic knowledge from a source domain to a target domain.
arXiv Detail & Related papers (2020-08-19T13:36:57Z) - Domain Conditioned Adaptation Network [90.63261870610211]
We propose a Domain Conditioned Adaptation Network (DCAN) to excite distinct convolutional channels with a domain conditioned channel attention mechanism.
This is the first work to explore the domain-wise convolutional channel activation for deep DA networks.
arXiv Detail & Related papers (2020-05-14T04:23:24Z) - Spatial Attention Pyramid Network for Unsupervised Domain Adaptation [66.75008386980869]
Unsupervised domain adaptation is critical in various computer vision tasks.
We design a new spatial attention pyramid network for unsupervised domain adaptation.
Our method performs favorably against the state-of-the-art methods by a large margin.
arXiv Detail & Related papers (2020-03-29T09:03:23Z) - MADAN: Multi-source Adversarial Domain Aggregation Network for Domain
Adaptation [58.38749495295393]
Domain adaptation aims to learn a transferable model to bridge the domain shift between one labeled source domain and another sparsely labeled or unlabeled target domain.
Recent multi-source domain adaptation (MDA) methods do not consider the pixel-level alignment between sources and target.
We propose a novel MDA framework to address these challenges.
arXiv Detail & Related papers (2020-02-19T21:22:00Z)
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.