Weakly-supervised Discovery of Visual Pattern Configurations
arXiv:1406.6507
Abstract
The increasing prominence of weakly labeled data nurtures a growing demand for object detection methods that can cope with minimal supervision. We propose an approach that automatically identifies discriminative configurations of visual patterns that are characteristic of a given object class. We formulate the problem as a constrained submodular optimization problem and demonstrate the benefits of the discovered configurations in remedying mislocalizations and finding informative positive and negative training examples. Together, these lead to state-of-the-art weakly-supervised detection results on the challenging PASCAL VOC dataset.
Cited by in corpus (8)
- C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection
- Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing
- Sample Greedy Based Task Allocation for Multiple Robot Systems
- Towards Precise End-to-end Weakly Supervised Object Detection Network
- WSSOD: A New Pipeline for Weakly- and Semi-Supervised Object Detection
- Adaptively Denoising Proposal Collection for Weakly Supervised Object Localization
- Min-Entropy Latent Model for Weakly Supervised Object Detection
- Weakly Supervised Object Localization and Detection: A Survey