Learning Deep Features for Discriminative Localization

@article{Zhou2016LearningDF,
  title={Learning Deep Features for Discriminative Localization},
  author={Bolei Zhou and Aditya Khosla and {\`A}gata Lapedriza and Aude Oliva and Antonio Torralba},
  journal={2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2016},
  pages={2921-2929}
}
  • Bolei Zhou, A. Khosla, +2 authors A. Torralba
  • Published 14 December 2015
  • Computer Science
  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
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 despite being trained on imagelevel labels. [...] Key Result We demonstrate in a variety of experiments that our network is able to localize the discriminative image regions despite just being trained for solving classification task1.Expand
Weakly Supervised Deep Learning for Objects Detection from Images
  • Jianfang Shi, Xiaohui Yuan, M. Elhoseny, Xiaojing Yuan
  • Computer Science
  • 2020
TLDR
A cascaded deep network architecture that leverages the class activation mapping with global average pooling to infer object localization maps based on the image-level annotations, which generates bounding boxes of objects in every image. Expand
Trustworthy AI: A Computational Perspective
  • Haochen Liu, Yiqi Wang, +5 authors Jiliang Tang
  • Computer Science
  • ArXiv
  • 2021
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 abilityExpand
Convolutional STN for Weakly Supervised Object Localization
TLDR
A convolutional, multi-scale spatial localization network that provides accurate localization for the object of interest and experimental results show that the proposed approach provides competitive performance for weakly supervised localization. Expand
WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation
TLDR
This paper introduces WILDCAT, a deep learning method which jointly aims at aligning image regions for gaining spatial invariance and learning strongly localized features, and significantly outperforms state-of-the-art methods. Expand
The success of deep convolutional networks for large-scale object recognition
Extracting saliency maps, which indicate parts of the image important to classification, requires many tricks to achieve satisfactory performance when using classifier-dependent methods. Instead, weExpand
Visual Concept Recognition and Localization via Iterative Introspection
TLDR
This work proposes a weakly-supervised iterative scheme, which shifts its center of attention to increasingly discriminative regions as it progresses, by alternating stages of classification and introspection, and shows its effectiveness over a range of datasets. Expand
Extending Input Channel Using Global Feature Image for Convolutional Neural Networks
TLDR
This paper proposes a new simple training strategy using global feature images as the inputs of the convolutional neural networks, in which the images are generated by image processing techniques. Expand
ELoPE: Fine-Grained Visual Classification with Efficient Localization, Pooling and Embedding
TLDR
The aim is to enhance the performance of a backbone CNN such as ResNet by including three efficient and lightweight components specifically designed for FGVC by using global k-max pooling, a discriminative embedding layer trained by optimizing class means and an efficient localization module that estimates bounding boxes using only class labels for training. Expand
Weakly Supervised Learning for Object Localization Based on an Attention Mechanism
  • Nojin Park, Hanseok Ko
  • Applied Sciences
  • 2021
Recently, deep learning has been successfully applied to object detection and localization tasks in images. When setting up deep learning frameworks for supervised training with large datasets,Expand
Weakly-supervised Discriminative Patch Learning via CNN for Fine-grained Recognition
TLDR
This work designs a novel asymmetric two-stream network architecture with supervision on convolutional filters and a nonrandom way of layer initialization that achieves state-of-the-art on two publicly available fine-grained recognition datasets. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 41 REFERENCES
Self-taught object localization with deep networks
This paper introduces self-taught object localization, a novel approach that leverages deep convolutional networks trained for whole-image recognition to localize objects in images without additionalExpand
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
TLDR
This integrated framework for using Convolutional Networks for classification, localization and detection is the winner of the localization task of the ImageNet Large Scale Visual Recognition Challenge 2013 and obtained very competitive results for the detection and classifications tasks. Expand
Very Deep Convolutional Networks for Large-Scale Image Recognition
TLDR
This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. Expand
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. Expand
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
TLDR
DeCAF, an open-source implementation of deep convolutional activation features, along with all associated network parameters, are released to enable vision researchers to be able to conduct experimentation with deep representations across a range of visual concept learning paradigms. Expand
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%. Expand
Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks
TLDR
This work designs a method to reuse layers trained on the ImageNet dataset to compute mid-level image representation for images in the PASCAL VOC dataset, and shows that despite differences in image statistics and tasks in the two datasets, the transferred representation leads to significantly improved results for object and action classification. Expand
Object Detectors Emerge in Deep Scene CNNs
TLDR
This work demonstrates that the same network can perform both scene recognition and object localization in a single forward-pass, without ever having been explicitly taught the notion of objects. Expand
Going deeper with convolutions
We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual RecognitionExpand
Inverting Visual Representations with Convolutional Networks
  • A. Dosovitskiy, T. Brox
  • Computer Science
  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
TLDR
This work proposes a new approach to study image representations by inverting them with an up-convolutional neural network, and applies this method to shallow representations (HOG, SIFT, LBP), as well as to deep networks. Expand
...
1
2
3
4
5
...