3 papers
cs.CV2024
An Efficient Post-hoc Framework for Reducing Task Discrepancy of Text Encoders for Composed Image Retrieval
Jaeseok Byun, Seokhyeon Jeong, Wonjae Kim +2
Composed Image Retrieval (CIR) aims to retrieve a target image based on a reference image and conditioning text, enabling controllable image searches. The mainstream Zero-Shot (ZS)…
cs.CV2023
TLDR: Text Based Last-layer Retraining for Debiasing Image Classifiers
Juhyeon Park, Seokhyeon Jeong, Taesup Moon
An image classifier may depend on incidental features stemming from a strong correlation between the feature and the classification target in the training dataset. Recently, Last L…
cs.CV2022
Towards More Robust Interpretation via Local Gradient Alignment
Sunghwan Joo, Seokhyeon Jeong, Juyeon Heo +2
Neural network interpretation methods, particularly feature attribution methods, are known to be fragile with respect to adversarial input perturbations. To address this, several m…