ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization
arXiv:1609.04331
Abstract
We aim to localize objects in images using image-level supervision only. Previous approaches to this problem mainly focus on discriminative object regions and often fail to locate precise object boundaries. We address this problem by introducing two types of context-aware guidance models, additive and contrastive models, that leverage their surrounding context regions to improve localization. The additive model encourages the predicted object region to be supported by its surrounding context region. The contrastive model encourages the predicted object region to be outstanding from its surrounding context region. Our approach benefits from the recent success of convolutional neural networks for object recognition and extends Fast R-CNN to weakly supervised object localization. Extensive experimental evaluation on the PASCAL VOC 2007 and 2012 benchmarks shows hat our context-aware approach significantly improves weakly supervised localization and detection.
Accepted paper at ECCV2016. The website and code is at http://www.di.ens.fr/willow/research/contextlocnet
References in corpus (3)
Cited by in corpus (24)
- Two-Phase Learning for Weakly Supervised Object Localization
- Weakly- and Semi-Supervised Object Detection with Expectation-Maximization Algorithm
- Exploiting saliency for object segmentation from image level labels
- Multiple Instance Detection Network with Online Instance Classifier Refinement
- Learning Image Representations by Completing Damaged Jigsaw Puzzles
- Soft Proposal Networks for Weakly Supervised Object Localization
- Weakly-supervised Visual Grounding of Phrases with Linguistic Structures
- PPR-FCN: Weakly Supervised Visual Relation Detection via Parallel Pairwise R-FCN
- Training object class detectors with click supervision
- Weakly Supervised Representation Learning for Unsynchronized Audio-Visual Events
- Temporal Dynamic Graph LSTM for Action-driven Video Object Detection
- Setting an attention region for convolutional neural networks using region selective features, for recognition of materials within glass vessels
- Multiple Instance Curriculum Learning for Weakly Supervised Object Detection
- C-WSL: Count-guided Weakly Supervised Localization
- Optimizing Region Selection for Weakly Supervised Object Detection
- Learning Intelligent Dialogs for Bounding Box Annotation
- NOTE-RCNN: NOise Tolerant Ensemble RCNN for Semi-Supervised Object Detection
- Spatial Likelihood Voting with Self-Knowledge Distillation for Weakly Supervised Object Detection
- Exploiting Web Images for Weakly Supervised Object Detection
- Hierarchical semantic segmentation using modular convolutional neural networks
- Text-guided Attention Model for Image Captioning
- Zero-Annotation Object Detection with Web Knowledge Transfer
- AutoLoc: Weakly-supervised Temporal Action Localization
- Weakly Supervised Object Detection with Pointwise Mutual Information