Weakly-Supervised Object Localization
77 papers with code • 8 benchmarks • 3 datasets
Weakly supervised object localization (WSOL) learns to localize objects with only image-level labels, no object level labels (bonding boxes, etc.,) is needed. It is more attractive since image-level labels are much easier and cheaper to obtain.
Libraries
Use these libraries to find Weakly-Supervised Object Localization models and implementationsMost implemented papers
Min-Entropy Latent Model for Weakly Supervised Object Detection
Weakly supervised object detection is a challenging task when provided with image category supervision but required to learn, at the same time, object locations and object detectors.
Modularized Textual Grounding for Counterfactual Resilience
Computer Vision applications often require a textual grounding module with precision, interpretability, and resilience to counterfactual inputs/queries.
C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection
Weakly supervised object detection (WSOD) is a challenging task when provided with image category supervision but required to simultaneously learn object locations and object detectors.
Min-max Entropy for Weakly Supervised Pointwise Localization
Pointwise localization allows more precise localization and accurate interpretability, compared to bounding box, in applications where objects are highly unstructured such as in medical domain.
Attention-based Dropout Layer for Weakly Supervised Object Localization
Weakly Supervised Object Localization (WSOL) techniques learn the object location only using image-level labels, without location annotations.
Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A Survey
Four key challenges are identified for the application of deep WSOL methods in histology -- under/over activation of CAMs, sensitivity to thresholding, and model selection.
DANet: Divergent Activation for Weakly Supervised Object Localization
In this paper, we propose a divergent activation (DA) approach, and target at learning complementary and discriminative visual patterns for image classification and weakly supervised object localization from the perspective of discrepancy.
Combinational Class Activation Maps for Weakly Supervised Object Localization
Most previous methods utilize the activation map corresponding to the highest activation source.
Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator
We show that optimising the parameters of classification neural networks with softmax cross-entropy is equivalent to maximising the mutual information between inputs and labels under the balanced data assumption.
Attributional Robustness Training using Input-Gradient Spatial Alignment
Safe deployment of machine learning system mandates that the prediction and its explanation be reliable and robust.