7 papers
A Realistic Protocol for Evaluation of Weakly Supervised Object Localization
Shakeeb Murtaza, Soufiane Belharbi, Marco Pedersoli +1
Weakly Supervised Object Localization (WSOL) allows training deep learning models for classification and localization (LOC) using only global class-level labels. The absence of bou…
InterPartAbility: Phrase-Region Grounding for Interpretable Text-to-Image Person Re-Identification
Shakeeb Murtaza, Aryan Shukla, Rajarshi Bhattacharya +2
Text-to-image person re-identification (TI-ReID) relies on natural-language text descriptions to retrieve top matching individuals from a gallery of reference images. While recent…
Seeing What Shouldn't Be There: Counterfactual GANs for Medical Image Attribution
Shakeeb Murtaza
Ascription of an image gives insights into the objects that influence the classification of the whole image or its pixels towards a specific category. These insights help radiologi…
TeD-Loc: Text Distillation for Weakly Supervised Object Localization
Shakeeb Murtaza, Soufiane Belharbi, Alexis Guichemerre +2
Weakly supervised object localization (WSOL) models are trained using only image-level class labels. They can predict both the object class and spatial regions corresponding to the…
DART: Leveraging Distance for Test Time Adaptation in Person Re-Identification
Rajarshi Bhattacharya, Shakeeb Murtaza, Christian Desrosiers +3
Person re-identification (ReID) models are known to suffer from camera bias, where learned representations cluster according to camera viewpoints rather than identity, leading to s…
CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videos
Soufiane Belharbi, Shakeeb Murtaza, Marco Pedersoli +3
Leveraging spatiotemporal information in videos is critical for weakly supervised video object localization (WSVOL) tasks. However, state-of-the-art methods only rely on visual and…