GOOD: Towards Domain Generalized Orientated Object Detection

• URL: http://arxiv.org/abs/2402.12765v1
• Date: Tue, 20 Feb 2024 07:12:22 GMT
• Title: GOOD: Towards Domain Generalized Orientated Object Detection
• Authors: Qi Bi, Beichen Zhou, Jingjun Yi, Wei Ji, Haolan Zhan, Gui-Song Xia
• Abstract summary: Oriented object detection has been rapidly developed in the past few years, but most of these methods assume the training and testing images are under the same statistical distribution. We propose the task of domain generalized oriented object detection, which intends to explore the generalization of oriented object detectors on arbitrary unseen target domains.
• Score: 39.76969237020444
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Oriented object detection has been rapidly developed in the past few years, but most of these methods assume the training and testing images are under the same statistical distribution, which is far from reality. In this paper, we propose the task of domain generalized oriented object detection, which intends to explore the generalization of oriented object detectors on arbitrary unseen target domains. Learning domain generalized oriented object detectors is particularly challenging, as the cross-domain style variation not only negatively impacts the content representation, but also leads to unreliable orientation predictions. To address these challenges, we propose a generalized oriented object detector (GOOD). After style hallucination by the emerging contrastive language-image pre-training (CLIP), it consists of two key components, namely, rotation-aware content consistency learning (RAC) and style consistency learning (SEC). The proposed RAC allows the oriented object detector to learn stable orientation representation from style-diversified samples. The proposed SEC further stabilizes the generalization ability of content representation from different image styles. Extensive experiments on multiple cross-domain settings show the state-of-the-art performance of GOOD. Source code will be publicly available.

Related papers

• Improving Generalization Ability for 3D Object Detection by Learning Sparsity-invariant Features [21.761631081209263]
  We propose a method to improve the generalization ability for 3D object detection on a single domain. To learn sparsity-invariant features from a single source domain, we selectively subsample the source data to a specific beam. We also employ the teacher-student framework to align the Bird's Eye View features for different point clouds densities.
  arXiv  Detail & Related papers  (2025-02-04T13:47:02Z)
• Object Style Diffusion for Generalized Object Detection in Urban Scene [69.04189353993907]
  We introduce a novel single-domain object detection generalization method, named GoDiff. By integrating pseudo-target domain data with source domain data, we diversify the training dataset. Experimental results demonstrate that our method not only enhances the generalization ability of existing detectors but also functions as a plug-and-play enhancement for other single-domain generalization methods.
  arXiv  Detail & Related papers  (2024-12-18T13:03:00Z)
• Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector [72.05791402494727]
  This paper studies the challenging cross-domain few-shot object detection (CD-FSOD) It aims to develop an accurate object detector for novel domains with minimal labeled examples.
  arXiv  Detail & Related papers  (2024-02-05T15:25:32Z)
• Weakly-supervised Contrastive Learning for Unsupervised Object Discovery [52.696041556640516]
  Unsupervised object discovery is promising due to its ability to discover objects in a generic manner. We design a semantic-guided self-supervised learning model to extract high-level semantic features from images. We introduce Principal Component Analysis (PCA) to localize object regions.
  arXiv  Detail & Related papers  (2023-07-07T04:03:48Z)
• CLIP the Gap: A Single Domain Generalization Approach for Object Detection [60.20931827772482]
  Single Domain Generalization tackles the problem of training a model on a single source domain so that it generalizes to any unseen target domain. We propose to leverage a pre-trained vision-language model to introduce semantic domain concepts via textual prompts. We achieve this via a semantic augmentation strategy acting on the features extracted by the detector backbone, as well as a text-based classification loss.
  arXiv  Detail & Related papers  (2023-01-13T12:01:18Z)
• Contrastive View Design Strategies to Enhance Robustness to Domain Shifts in Downstream Object Detection [37.06088084592779]
  We conduct an empirical study of contrastive learning and out-of-domain object detection. We propose strategies to augment views and enhance robustness in appearance-shifted and context-shifted scenarios. Our results and insights show how to ensure robustness through the choice of views in contrastive learning.
  arXiv  Detail & Related papers  (2022-12-09T00:34:50Z)
• Robust Object Detection via Instance-Level Temporal Cycle Confusion [89.1027433760578]
  We study the effectiveness of auxiliary self-supervised tasks to improve the out-of-distribution generalization of object detectors. Inspired by the principle of maximum entropy, we introduce a novel self-supervised task, instance-level temporal cycle confusion (CycConf) For each object, the task is to find the most different object proposals in the adjacent frame in a video and then cycle back to itself for self-supervision.
  arXiv  Detail & Related papers  (2021-04-16T21:35:08Z)

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.