Object Detection With Self-Supervised Scene Adaptation
This paper proposes a novel method to improve the performance of a trained object detector on scenes with fixed camera perspectives based on self-supervised adaptation. Given a specific scene, the trained detector is adapted using pseudo-ground truth labels generated by the detector itself and an object tracker in a cross-teaching manner. When the camera perspective is fixed, our method can utilize the background equivariance by proposing artifact-free object mixup as a means of data augmentation, and utilize accurate background extraction as an additional input modality. We also introduce a large-scale and diverse dataset for the development and evaluation of scene-adaptive object detection. Experiments on this dataset show that our method can improve the average precision of the original detector, outperforming the previous state-of-the-art self-supervised domain adaptive object detection methods by a large margin. Our dataset and code are published at https://github.com/cvlab-stonybrook/scenes100.
Code (1)
Tasks
Data AugmentationObjectobject-detectionObject DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
3D Object Detection with a Self-supervised Lidar Scene Flow Backbone
State-of-the-art lidar-based 3D object detection methods rely on supervised learning and large labeled datasets. However, annotating lidar data is resource-consuming, and depending only on supervised learning limits the …
3D Object DetectionObjectobject-detectionObject Detection+3Domain Generalization of 3D Object Detection by Density-Resampling
Point-cloud-based 3D object detection suffers from performance degradation when encountering data with novel domain gaps. To tackle it, the single-domain generalization (SDG) aims to generalize the detection model traine…
3D Object DetectionData AugmentationDomain AdaptationDomain Generalization+6STAL3D: Unsupervised Domain Adaptation for 3D Object Detection via Collaborating Self-Training and Adversarial Learning
Existing 3D object detection suffers from expensive annotation costs and poor transferability to unknown data due to the domain gap, Unsupervised Domain Adaptation (UDA) aims to generalize detection models trained in lab…
3D Object DetectionDomain Adaptationobject-detectionObject Detection+1Self-supervised Domain Adaptation for Computer Vision Tasks
Recent progress of self-supervised visual representation learning has achieved remarkable success on many challenging computer vision benchmarks. However, whether these techniques can be used for domain adaptation has no…
Domain AdaptationObject RecognitionRepresentation LearningSegmentation+1Test-time Adaptation with Slot-Centric Models
Current visual detectors, though impressive within their training distribution, often fail to parse out-of-distribution scenes into their constituent entities. Recent test-time adaptation methods use auxiliary self-super…
image-classificationImage ClassificationImage SegmentationInductive Bias+7