Two-Phase Learning for Weakly Supervised Object Localization
2017-09-14 11:14
766 查看
Background
1. Weakly supervised semantic segmentation and localization have a problem of focus only on the most important parts of an image since they use only image-level annotations.
2. The complete extent of objects are good for object localization.
3. A novel method is proposed to cover the entire parts of objects.
Main points
ff
To cover the entire parts of objects, a simple way is to find the most discriminative part, the second most discriminative part and so on. When locating the second most discriminative part, we mask out the most discriminative one. This is the core
idea of this paper.
1. Find the most discriminative parts of an image as usual, which is done by the first network.
2. Mask out the most discriminative parts of an image.
3. Train the same network to find the second most discriminatvie parts.
Drawbacks
1. The network is not shared during two-phase learning.
2. The network can not be trained in an end-to-end manner.
1. Weakly supervised semantic segmentation and localization have a problem of focus only on the most important parts of an image since they use only image-level annotations.
2. The complete extent of objects are good for object localization.
3. A novel method is proposed to cover the entire parts of objects.
Main points
ff
To cover the entire parts of objects, a simple way is to find the most discriminative part, the second most discriminative part and so on. When locating the second most discriminative part, we mask out the most discriminative one. This is the core
idea of this paper.
1. Find the most discriminative parts of an image as usual, which is done by the first network.
2. Mask out the most discriminative parts of an image.
3. Train the same network to find the second most discriminatvie parts.
Drawbacks
1. The network is not shared during two-phase learning.
2. The network can not be trained in an end-to-end manner.
相关文章推荐
- 《Deep Self-Taught Learning for Weakly Supervised Object Localization》
- 目标定位--Deep Self-Taught Learning for Weakly Supervised Object Localization
- Deep Self-Taught Learning for Weakly Supervised Object Localization
- 论文笔记《IS object localization for free? Weakly-supervised learning with convolutional neural network》
- 论文研读--Weakly Supervised Object Localization with Progressive Domain Adaptation
- 论文阅读Soft Proposal Networks for weekly-supervised object localization
- 行人属性“Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Loca”
- [EMNLP2017]Deep Residual Learning for Weakly-Supervised Relation Extraction
- 【CV论文阅读】+【搬运工】LocNet: Improving Localization Accuracy for Object Detection + A Theoretical analysis of feature pooling in Visual Recognition
- Learning Deep Features for Discriminative Localization 笔记2
- 物体检测“DSOD: Learning Deeply Supervised Object Detectors from Scratch”
- Learning Deep Features for Discriminative Localization 阅读笔记-网络可视化NO.2
- Supervised Hashing for Image Retrieval via Image Represention Learning-笔记1
- A Twofold Siamese Network for Real-Time Object Tracking 阅读笔记
- Weakly Supervised Object Recognition with Convolutional Neural Networks
- deep learning for object detection
- Weakly Supervised Action Localization by Sparse Temporal Pooling Network
- DSOD: Learning Deeply Supervised Object Detectors from Scratch
- 【深度学习】深度学习中监督优化入门(A Primer on Supervised Optimization for Deep Learning)
- DSOD: Learning Deeply Supervised Object Detectors from Scratch 论文解读