Large-Scale Object Discovery and Detector Adaptation from Unlabeled Video

Abstract

We explore object discovery and detector adaptation based on unlabeled video sequences captured from a mobile platform. We propose a fully automatic approach for object mining from video which builds upon a generic object tracking approach. By applying this method to three large video datasets from autonomous driving and mobile robotics scenarios, we demonstrate its robustness and generality. Based on the object mining results, we propose a novel approach for unsupervised object discovery by appearance-based clustering. We show that this approach successfully discovers interesting objects relevant to driving scenarios. In addition, we perform self-supervised detector adaptation in order to improve detection performance on the KITTI dataset for existing categories. Our approach has direct relevance for enabling large-scale object learning for autonomous driving.

arXiv commentCVPR'18 submission

References in corpus (3)

• In Defense of the Triplet Loss for Person Re-Identification
• SfM-Net: Learning of Structure and Motion from Video
• Deep Image Category Discovery using a Transferred Similarity Function

Cited by in corpus (5)

• Key Instance Selection for Unsupervised Video Object Segmentation
• A probabilistic constrained clustering for transfer learning and image category discovery
• Parallel Total Variation Distance Estimation with Neural Networks for Merging Over-Clusterings
• Learning Dynamic Network Using a Reuse Gate Function in Semi-supervised Video Object Segmentation
• Self-supervised Transfer Learning for Instance Segmentation through Physical Interaction