• Corpus ID: 202537780

Weakly Supervised Localization using Min-Max Entropy: an Interpretable Framework

@inproceedings{Belharbi2019WeaklySL,
  title={Weakly Supervised Localization using Min-Max Entropy: an Interpretable Framework},
  author={Soufiane Belharbi and J{\'e}r{\^o}me Rony and Jos{\'e} Dolz and Ismail Ben Ayed and Luke McCaffrey and Eric Granger},
  year={2019}
}
Weakly supervised object localization (WSOL) models aim to locate objects of interest in an image after being trained only on data with coarse image level labels. Deep learning models for WSOL rely typically on convolutional attention maps with no constraints on the regions of interest which allows these models to select any region, making them vulnerable to false positive regions and inconsistent predictions. This issue occurs in many application domains, e.g., medical image analysis, where… 

References

SHOWING 1-10 OF 60 REFERENCES
From image-level to pixel-level labeling with Convolutional Networks
TLDR
A Convolutional Neural Network-based model is proposed, which is constrained during training to put more weight on pixels which are important for classifying the image, and which beats the state of the art results in weakly supervised object segmentation task by a large margin.
Adversarial Complementary Learning for Weakly Supervised Object Localization
TLDR
This work mathematically proves that class localization maps can be obtained by directly selecting the class-specific feature maps of the last convolutional layer, which paves a simple way to identify object regions and presents a simple network architecture including two parallel-classifiers for object localization.
Two-Phase Learning for Weakly Supervised Object Localization
TLDR
This paper proposes a novel two-phase learning scheme that can be utilized in well-designed techniques for weakly supervised semantic segmentation, salient region detection, and object location prediction.
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.
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.
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.
Attention Networks for Weakly Supervised Object Localization
TLDR
This work considers the problem of weakly supervised learning for object localization given a collection of images with image-level annotations indicating the presence/absence of an object and proposes a neural network architecture called the attention network for this problem.
Multi-evidence Filtering and Fusion for Multi-label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning
TLDR
A novel weakly supervised curriculum learning pipeline for multi-label object recognition, detection and semantic segmentation, and a novel algorithm for filtering, fusing and classifying object instances collected from multiple solution mechanisms is proposed.
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.
Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach
TLDR
This work investigates a principle way to progressively mine discriminative object regions using classification networks to address the weakly-supervised semantic segmentation problems and proposes a new adversarial erasing approach for localizing and expanding object regions progressively.
...
1
2
3
4
5
...