Unsupervised Domain Adaptation for One-stage Object Detector using Offsets to Bounding Box

• URL: http://arxiv.org/abs/2207.09656v1
• Date: Wed, 20 Jul 2022 05:17:12 GMT
• Title: Unsupervised Domain Adaptation for One-stage Object Detector using Offsets to Bounding Box
• Authors: Jayeon Yoo, Inseop Chung, Nojun Kwak
• Abstract summary: Most existing domain object detection methods exploit adversarial feature alignment to adapt the model to a new domain. Recent advances in adversarial feature alignment strives to reduce the negative effect of alignment, or negative transfer, that occurs because the distribution of features varies depending on the category of objects.
• Score: 31.594207790000226
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Most existing domain adaptive object detection methods exploit adversarial feature alignment to adapt the model to a new domain. Recent advances in adversarial feature alignment strives to reduce the negative effect of alignment, or negative transfer, that occurs because the distribution of features varies depending on the category of objects. However, by analyzing the features of the anchor-free one-stage detector, in this paper, we find that negative transfer may occur because the feature distribution varies depending on the regression value for the offset to the bounding box as well as the category. To obtain domain invariance by addressing this issue, we align the feature conditioned on the offset value, considering the modality of the feature distribution. With a very simple and effective conditioning method, we propose OADA (Offset-Aware Domain Adaptive object detector) that achieves state-of-the-art performances in various experimental settings. In addition, by analyzing through singular value decomposition, we find that our model enhances both discriminability and transferability.

Related papers

• AIR-DA: Adversarial Image Reconstruction for Unsupervised Domain Adaptive Object Detection [28.22783703278792]
  Adrial Image Reconstruction (AIR) as the regularizer to facilitate the adversarial training of the feature extractor. Our evaluations across several datasets of challenging domain shifts demonstrate that the proposed method outperforms all previous methods.
  arXiv  Detail & Related papers  (2023-03-27T16:51:51Z)
• Exploiting Domain Transferability for Collaborative Inter-level Domain Adaptive Object Detection [17.61278045720336]
  Domain adaptation for object detection (DAOD) has recently drawn much attention owing to its capability of detecting target objects without any annotations. Previous works focus on aligning features extracted from partial levels in a two-stage detector via adversarial training. We introduce a novel framework for ProposalD with three proposed components: Multi-scale-aware Uncertainty Attention (MUA), Transferable Region Network (TRPN), and Dynamic Instance Sampling (DIS)
  arXiv  Detail & Related papers  (2022-07-20T01:50:26Z)
• Decoupled Adaptation for Cross-Domain Object Detection [69.5852335091519]
  Cross-domain object detection is more challenging than object classification. D-adapt achieves a state-of-the-art results on four cross-domain object detection tasks.
  arXiv  Detail & Related papers  (2021-10-06T08:43:59Z)
• Vector-Decomposed Disentanglement for Domain-Invariant Object Detection [75.64299762397268]
  We try to disentangle domain-invariant representations from domain-specific representations. In the experiment, we evaluate our method on the single- and compound-target case.
  arXiv  Detail & Related papers  (2021-08-15T07:58:59Z)
• 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)
• Domain-Specific Suppression for Adaptive Object Detection [20.887838391558624]
  We propose a new perspective on how CNN models gain the transferability, viewing the weights of a model as a series of motion patterns. The goal of domain adaptation is to concentrate on the domain-invariant direction while eliminating the disturbance from domain-specific one. In this paper, we propose the domain-specific suppression, an exemplary and generalizable constraint to the original convolution gradients in backpropagation.
  arXiv  Detail & Related papers  (2021-05-08T03:11:36Z)
• Re-energizing Domain Discriminator with Sample Relabeling for Adversarial Domain Adaptation [88.86865069583149]
  Unsupervised domain adaptation (UDA) methods exploit domain adversarial training to align the features to reduce domain gap. In this work, we propose an efficient optimization strategy named Re-enforceable Adversarial Domain Adaptation (RADA) RADA aims to re-energize the domain discriminator during the training by using dynamic domain labels.
  arXiv  Detail & Related papers  (2021-03-22T08:32:55Z)
• Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation [62.29076080124199]
  This paper proposes a novel coarse-to-fine feature adaptation approach to cross-domain object detection. At the coarse-grained stage, foreground regions are extracted by adopting the attention mechanism, and aligned according to their marginal distributions. At the fine-grained stage, we conduct conditional distribution alignment of foregrounds by minimizing the distance of global prototypes with the same category but from different domains.
  arXiv  Detail & Related papers  (2020-03-23T13:40:06Z)
• Harmonizing Transferability and Discriminability for Adapting Object Detectors [48.78231850215302]
  We propose a Hierarchical Transferability Network (HTCN) that calibrates the transferability of feature representations for harmonizing discriminability. Experimental results show that HTCN significantly outperforms the state-of-the-art methods on benchmark datasets.
  arXiv  Detail & Related papers  (2020-03-13T13:47:48Z)

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.