On learning to localize objects with minimal supervision
arXiv:1403.1024
Abstract
Learning to localize objects with minimal supervision is an important problem in computer vision, since large fully annotated datasets are extremely costly to obtain. In this paper, we propose a new method that achieves this goal with only image-level labels of whether the objects are present or not. Our approach combines a discriminative submodular cover problem for automatically discovering a set of positive object windows with a smoothed latent SVM formulation. The latter allows us to leverage efficient quasi-Newton optimization techniques. Our experiments demonstrate that the proposed approach provides a 50% relative improvement in mean average precision over the current state-of-the-art on PASCAL VOC 2007 detection.
References in corpus (1)
Cited by in corpus (15)
- LSDA: Large Scale Detection Through Adaptation
- Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks
- C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection
- Attention-based Dropout Layer for Weakly Supervised Object Localization
- Evaluating Weakly Supervised Object Localization Methods Right
- Weakly Supervised Object Detection with Segmentation Collaboration
- Object-Aware Instance Labeling for Weakly Supervised Object Detection
- Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer
- Mixed Supervised Object Detection with Robust Objectness Transfer
- A Smoother Way to Train Structured Prediction Models
- Mining Deep And-Or Object Structures via Cost-Sensitive Question-Answer-Based Active Annotations
- Multi-patch Feature Pyramid Network for Weakly Supervised Object Detection in Optical Remote Sensing Images
- Adaptively Denoising Proposal Collection for Weakly Supervised Object Localization
- Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object Localization
- Object-sensitive Deep Reinforcement Learning