Weakly-supervised Discovery of Visual Pattern Configurations

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.

References in corpus (1)

• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition

Cited by in corpus (15)

• Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning
• Few-Example Object Detection with Model Communication
• Self Paced Deep Learning for Weakly Supervised Object Detection
• C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection
• Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detection
• Attention-based Dropout Layer for Weakly Supervised Object Localization
• A Review of Co-saliency Detection Technique: Fundamentals, Applications, and Challenges
• Few-shot Object Detection via Feature Reweighting
• Sample Greedy Based Task Allocation for Multiple Robot Systems
• Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing
• Towards Precise End-to-end Weakly Supervised Object Detection Network
• WSSOD: A New Pipeline for Weakly- and Semi-Supervised Object Detection
• Min-Entropy Latent Model for Weakly Supervised Object Detection
• Adaptively Denoising Proposal Collection for Weakly Supervised Object Localization
• Weakly Supervised Object Localization and Detection: A Survey