Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector

• URL: http://arxiv.org/abs/2008.08574v1
• Date: Wed, 19 Aug 2020 17:57:03 GMT
• Title: Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector
• Authors: Cheng-Chun Hsu, Yi-Hsuan Tsai, Yen-Yu Lin, Ming-Hsuan Yang
• Abstract summary: A domain adaptive object detector aims to adapt itself to unseen domains that may contain variations of object appearance, viewpoints or backgrounds. We propose a domain adaptation framework that accounts for each pixel via predicting pixel-wise objectness and centerness.
• Score: 95.51517606475376
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A domain adaptive object detector aims to adapt itself to unseen domains that may contain variations of object appearance, viewpoints or backgrounds. Most existing methods adopt feature alignment either on the image level or instance level. However, image-level alignment on global features may tangle foreground/background pixels at the same time, while instance-level alignment using proposals may suffer from the background noise. Different from existing solutions, we propose a domain adaptation framework that accounts for each pixel via predicting pixel-wise objectness and centerness. Specifically, the proposed method carries out center-aware alignment by paying more attention to foreground pixels, hence achieving better adaptation across domains. We demonstrate our method on numerous adaptation settings with extensive experimental results and show favorable performance against existing state-of-the-art algorithms.

Related papers

• Rethinking Cross-Domain Pedestrian Detection: A Background-Focused Distribution Alignment Framework for Instance-Free One-Stage Detectors [25.967313282860626]
  Cross-domain pedestrian detection aims to generalize pedestrian detectors from one label-rich domain to another label-scarce domain. This paper proposes a novel framework, namely, background-focused distribution alignment (BFDA), to train domain adaptive onestage pedestrian detectors.
  arXiv  Detail & Related papers  (2023-09-15T21:29:27Z)
• I2F: A Unified Image-to-Feature Approach for Domain Adaptive Semantic Segmentation [55.633859439375044]
  Unsupervised domain adaptation (UDA) for semantic segmentation is a promising task freeing people from heavy annotation work. Key idea to tackle this problem is to perform both image-level and feature-level adaptation jointly. This paper proposes a novel UDA pipeline for semantic segmentation that unifies image-level and feature-level adaptation.
  arXiv  Detail & Related papers  (2023-01-03T15:19:48Z)
• PIT: Position-Invariant Transform for Cross-FoV Domain Adaptation [53.428312630479816]
  We observe that the Field of View (FoV) gap induces noticeable instance appearance differences between the source and target domains. Motivated by the observations, we propose the textbfPosition-Invariant Transform (PIT) to better align images in different domains.
  arXiv  Detail & Related papers  (2021-08-16T15:16:47Z)
• 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)
• Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation [169.82760468633236]
  We propose to build the pixel-level cycle association between source and target pixel pairs. Our method can be trained end-to-end in one stage and introduces no additional parameters.
  arXiv  Detail & Related papers  (2020-10-31T00:11:36Z)
• Channel-wise Alignment for Adaptive Object Detection [66.76486843397267]
  Generic object detection has been immensely promoted by the development of deep convolutional neural networks. Existing methods on this task usually draw attention on the high-level alignment based on the whole image or object of interest. In this paper, we realize adaptation from a thoroughly different perspective, i.e., channel-wise alignment.
  arXiv  Detail & Related papers  (2020-09-07T02:42:18Z)
• Exploring Categorical Regularization for Domain Adaptive Object Detection [27.348272177261233]
  We propose a categorical regularization framework for domain adaptive object detection. It can be applied as a plug-and-play component on a series of Adaptive Domain Faster R-CNN methods. Our method obtains a significant performance gain over original Domain Adaptive Faster R-CNN detectors.
  arXiv  Detail & Related papers  (2020-03-20T08:53:10Z)
• 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.