Collaborative Learning for Weakly Supervised Object Detection

Abstract

Weakly supervised object detection has recently received much attention, since it only requires image-level labels instead of the bounding-box labels consumed in strongly supervised learning. Nevertheless, the save in labeling expense is usually at the cost of model accuracy. In this paper, we propose a simple but effective weakly supervised collaborative learning framework to resolve this problem, which trains a weakly supervised learner and a strongly supervised learner jointly by enforcing partial feature sharing and prediction consistency. For object detection, taking WSDDN-like architecture as weakly supervised detector sub-network and Faster-RCNN-like architecture as strongly supervised detector sub-network, we propose an end-to-end Weakly Supervised Collaborative Detection Network. As there is no strong supervision available to train the Faster-RCNN-like sub-network, a new prediction consistency loss is defined to enforce consistency of predictions between the two sub-networks as well as within the Faster-RCNN-like sub-networks. At the same time, the two detectors are designed to partially share features to further guarantee the model consistency at perceptual level. Extensive experiments on PASCAL VOC 2007 and 2012 data sets have demonstrated the effectiveness of the proposed framework.

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning
• YOLO9000: Better, Faster, Stronger
• Weakly- and Semi-Supervised Object Detection with Expectation-Maximization Algorithm
• Multiple Instance Detection Network with Online Instance Classifier Refinement
• Deep Self-Taught Learning for Weakly Supervised Object Localization

Cited by in corpus (4)

• WSOD^2: Learning Bottom-up and Top-down Objectness Distillation for Weakly-supervised Object Detection
• Interpolation-based semi-supervised learning for object detection
• Reinforcement Learning for Weakly Supervised Temporal Grounding of Natural Language in Untrimmed Videos
• Cascade Attentive Dropout for Weakly Supervised Object Detection