Soft Proposal Networks for Weakly Supervised Object Localization

@article{Zhu2017SoftPN,
  title={Soft Proposal Networks for Weakly Supervised Object Localization},
  author={Yi Zhu and Yanzhao Zhou and Qixiang Ye and Qiang Qiu and Jianbin Jiao},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={1859-1868}
}
Weakly supervised object localization remains challenging, where only image labels instead of bounding boxes are available during training. Object proposal is an effective component in localization, but often computationally expensive and incapable of joint optimization with some of the remaining modules. In this paper, to the best of our knowledge, we for the first time integrate weakly supervised object proposal into convolutional neural networks (CNNs) in an end-to-end learning manner. We… 

Figures and Tables from this paper

Weakly Supervised Region Proposal Network and Object Detection
TLDR
This paper proposes a weakly supervised region proposal network which is trained using only image-level annotations and achieves the state-of-the-art performance for WSOD with performance gain of about \(3\%\) on average.
Attention-Based Dropout Layer for Weakly Supervised Object Localization
  • Junsuk Choe, Hyunjung Shim
  • Computer Science
    2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2019
TLDR
An Attention-based Dropout Layer (ADL), which utilizes the self-attention mechanism to process the feature maps of the model to improve the accuracy of WSOL, achieving a new state-of-the-art localization accuracy in CUB-200-2011 dataset.
Proposal-Based Instance Segmentation With Point Supervision
TLDR
A method called WISE-Net is proposed that only requires point-level annotations for instance segmentation with point- level supervision and obtains competitive results compared to fully-supervised methods in certain scenarios.
Instance Segmentation with Point Supervision
TLDR
The method obtains competitive results compared to fully-supervised methods in certain scenarios; outperforms fully- and weakly- supervised methods with a fixed annotation budget; and is a first strong baseline for instance segmentation with point-level supervision.
Enabling Deep Residual Networks for Weakly Supervised Object Detection
TLDR
The intrinsic root is discovered with sophisticated analysis and a sequence of design principles to take full advantages of deep residual learning for WSOD from the perspectives of adding redundancy, improving robustness and aligning features are proposed.
Dual-Gradients Localization Framework for Weakly Supervised Object Localization
TLDR
This work proposes an offline framework to achieve precise localization on any convolutional layer of a classification model by exploiting two kinds of gradients, called Dual-Gradients Localization (DGL) framework.
Deep Learning for Weakly-Supervised Object Detection and Object Localization: A Survey
TLDR
This paper considers WSOL is a sub-task of WSOD and provides a comprehensive survey of the recent achievements ofWSOD and describes the formulation and setting of WS OD, including the background, challenges, basic framework.
Fine-Grained Attention for Weakly Supervised Object Localization
TLDR
A novel residual fine-grained attention (RFGA) module that autonomously excites the less activated regions of an object by utilizing information distributed over channels and locations within feature maps in combination with a residual operation.
Group R-CNN for Weakly Semi-supervised Object Detection with Points
TLDR
An effective point-to-box regressor based on the classic RCNN architecture that significantly outperforms the prior method Point DETR by 3.9 mAP with 5% well-labeled images, which is the most challenging scenario.
Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation
TLDR
This article proposes a multiple instance learning (MIL) framework, which can be trained in an end-to-end manner using training images with image-level labels and achieves state-of-the-art performance for both weakly supervised instance segmentation and semantic segmentation.
...
...

References

SHOWING 1-10 OF 43 REFERENCES
Weakly Supervised Object Localization with Multi-Fold Multiple Instance Learning
TLDR
This work follows a multiple-instance learning approach that iteratively trains the detector and infers the object locations in the positive training images and proposes a window refinement method, which improves the localization accuracy by incorporating an objectness prior.
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TLDR
This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.
Is object localization for free? - Weakly-supervised learning with convolutional neural networks
TLDR
A weakly supervised convolutional neural network is described for object classification that relies only on image-level labels, yet can learn from cluttered scenes containing multiple objects.
Weakly Supervised Localization Using Deep Feature Maps
TLDR
This paper proposes an efficient beam search based approach to detect and localize multiple objects in images and significantly outperforms the state-of-the-art in standard object localization data-sets.
ProNet: Learning to Propose Object-Specific Boxes for Cascaded Neural Networks
TLDR
A novel classification architecture ProNet based on convolutional neural networks that outperforms previous state-of-the-art significantly on PASCAL VOC 2012 and MS COCO datasets for object classification and point-based localization.
Learning Deep Features for Discriminative Localization
In this work, we revisit the global average pooling layer proposed in [13], and shed light on how it explicitly enables the convolutional neural network (CNN) to have remarkable localization ability
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TLDR
This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%.
ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization
TLDR
This work introduces two types of context-aware guidance models, additive and contrastive models, that leverage their surrounding context regions to improve localization in objects in images using image-level supervision only.
Weakly Supervised Deep Detection Networks
  • Hakan Bilen, A. Vedaldi
  • Computer Science
    2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
TLDR
This paper proposes a weakly supervised deep detection architecture that modifies one such network to operate at the level of image regions, performing simultaneously region selection and classification.
On learning to localize objects with minimal supervision
TLDR
This paper proposes a new method that achieves this goal with only image-level labels of whether the objects are present or not, and combines a discriminative submodular cover problem for automatically discovering a set of positive object windows with a smoothed latent SVM formulation.
...
...