research
∙
03/16/2021
BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation
Weakly supervised segmentation methods using bounding box annotations fo...
share
research
∙
01/17/2021
Removing Undesirable Feature Contributions Using Out-of-Distribution Data
Several data augmentation methods deploy unlabeled-in-distribution (UID)...
research
∙
10/27/2020
Interpretation of NLP models through input marginalization
To demystify the "black box" property of deep neural networks for natura...
research
∙
09/23/2020
Information-Theoretic Visual Explanation for Black-Box Classifiers
In this work, we attempt to explain the prediction of any black-box clas...
research
∙
08/20/2020
iCaps: An Interpretable Classifier via Disentangled Capsule Networks
We propose an interpretable Capsule Network, iCaps, for image classifica...
research
∙
06/29/2020
Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentation
In this paper, we tackle the problem of image anomaly detection and segm...
research
∙
06/28/2017