Two-Phase Learning for Weakly Supervised Object Localization

Abstract

Weakly supervised semantic segmentation and localiza- tion have a problem of focusing only on the most important parts of an image since they use only image-level annota- tions. In this paper, we solve this problem fundamentally via two-phase learning. Our networks are trained in two steps. In the first step, a conventional fully convolutional network (FCN) is trained to find the most discriminative parts of an image. In the second step, the activations on the most salient parts are suppressed by inference conditional feedback, and then the second learning is performed to find the area of the next most important parts. By combining the activations of both phases, the entire portion of the tar- get object can be captured. Our proposed training scheme is novel and can be utilized in well-designed techniques for weakly supervised semantic segmentation, salient region detection, and object location prediction. Detailed experi- ments demonstrate the effectiveness of our two-phase learn- ing in each task.

Accepted at ICCV 2017

References in corpus (11)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• Fully Convolutional Networks for Semantic Segmentation
• STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation
• Learning Deconvolution Network for Semantic Segmentation
• Rich feature hierarchies for accurate object detection and semantic segmentation
• Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning
• Learning Deep Features for Discriminative Localization
• ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization
• Built-in Foreground/Background Prior for Weakly-Supervised Semantic Segmentation
• Weakly Supervised Object Localization Using Size Estimates

Cited by in corpus (15)

• Adversarial Complementary Learning for Weakly Supervised Object Localization
• Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation
• Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A Survey
• Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles
• Learning Image Representations by Completing Damaged Jigsaw Puzzles
• Self-Erasing Network for Integral Object Attention
• Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation
• Convolutional Simplex Projection Network (CSPN) for Weakly Supervised Semantic Segmentation
• C-WSL: Count-guided Weakly Supervised Localization
• Improved Techniques For Weakly-Supervised Object Localization
• Weakly-Supervised Learning for Tool Localization in Laparoscopic Videos
• CNNs, LSTMs, and Attention Networks for Pathology Detection in Medical Data
• AutoLoc: Weakly-supervised Temporal Action Localization
• Min-Entropy Latent Model for Weakly Supervised Object Detection
• Improving Weakly-supervised Object Localization via Causal Intervention