De-biasing Weakly Supervised Learning by Regularizing Prediction Entropy
We explore the effect of regularizing prediction entropy in a weakly supervised setting with inexact class labels. When underlying data distributions are biased toward a specific subclass, we hypothesize that entropy regularization can be used to bootstrap a training set that mitigates this bias. We conduct experiments over multiple datasets under supervision of an oracle and in a semi-supervised setting finding substantial reductions in training set bias capable of decreasing test error rate. These findings suggest entropy regularization as a promising approach to de-biasing weakly supervised learning systems.
Code (0)
등록된 구현이 없습니다.
Tasks
Weakly-supervised LearningSimilar Papers 제목 키워드 기반
Debate-Enhanced Pseudo Labeling and Frequency-Aware Progressive Debiasing for Weakly-Supervised Camouflaged Object Detection with Scribble Annotations
Weakly-Supervised Camouflaged Object Detection (WSCOD) aims to locate and segment objects that are visually concealed within their surrounding scenes, relying solely on sparse supervision such as scribble annotations. De…
Object DetectionAdaptation of Weakly Supervised Localization in Histopathology by Debiasing Predictions
Weakly Supervised Object Localization (WSOL) models enable joint classification and region-of-interest localization in histology images using only image-class supervision. When deployed in a target domain, distributions …
Object LocalizationDomain AdaptationUsing Focal Loss to Fight Shallow Heuristics: An Empirical Analysis of Modulated Cross-Entropy in Natural Language Inference
There is no such thing as a perfect dataset. In some datasets, deep neural networks discover underlying heuristics that allow them to take shortcuts in the learning process, resulting in poor generalization capability. I…
Natural Language InferenceInformation Entropy Based Feature Pooling for Convolutional Neural Networks
In convolutional neural networks (CNNs), we propose to estimate the importance of a feature vector at a spatial location in the feature maps by the network's uncertainty on its class prediction, which can be quantified u…
General ClassificationObject LocalizationSegmentationSemantic Segmentation+3Min-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. The inconsistency between the weak su…
image-classificationImage ClassificationObjectobject-detection+4