Adaptively Denoising Proposal Collection for Weakly Supervised Object Localization

Abstract

In this paper, we address the problem of weakly supervised object localization (WSL), which trains a detection network on the dataset with only image-level annotations. The proposed approach is built on the observation that the proposal set from the training dataset is a collection of background, object parts, and objects. Several strategies are taken to adaptively eliminate the noisy proposals and generate pseudo object-level annotations for the weakly labeled dataset. A multiple instance learning (MIL) algorithm enhanced by mask-out strategy is adopted to collect the class-specific object proposals, which are then utilized to adapt a pre-trained classification network to a detection network. In addition, the detection results from the detection network are re-weighted by jointly considering the detection scores and the overlap ratio of proposals in a proposal subset optimization framework. The optimal proposals work as object-level labels that enable a pseudo-strongly supervised dataset for training the detection network. Consequently, we establish a fully adaptive detection network. Extensive evaluations on the PASCAL VOC 2007 and 2012 datasets demonstrate a significant improvement compared with the state-of-the-art methods.

References in corpus (15)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• DeepPose: Human Pose Estimation via Deep Neural Networks
• Beyond Bilinear: Generalized Multimodal Factorized High-order Pooling for Visual Question Answering
• Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning
• Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction
• Learning Depth from Single Images with Deep Neural Network Embedding Focal Length
• LSDA: Large Scale Detection Through Adaptation
• Learning Using Privileged Information: SVM+ and Weighted SVM
• Weakly-supervised Discovery of Visual Pattern Configurations
• On learning to localize objects with minimal supervision
• Self-taught Object Localization with Deep Networks
• Saliency Guided End-to-End Learning for Weakly Supervised Object Detection
• Weakly Supervised Object Localization Using Things and Stuff Transfer
• Towards Learning Affine-Invariant Representations via Data-Efficient CNNs
• Unsupervised Deep Feature Transfer for Low Resolution Image Classification

Cited by in corpus (1)

• Colonoscopy Polyp Detection and Classification: Dataset Creation and Comparative Evaluations