← Search

Neha Kalibhat

2 accepted papers

2024

Measuring Self-Supervised Representation Quality for Downstream Classification Using Discriminative Features

AAAI 2024technical

Self-supervised learning (SSL) has shown impressive results in downstream classification tasks. However, there is limited work in understanding their failure modes and interpreting their learned representations. In this paper, we study the representation space of state-of-the-art self-supervised mod…

Cited by 7SourcePDFScholar
2023

Identifying Interpretable Subspaces in Image Representations

ICML 2023poster

We propose Automatic Feature Explanation using Contrasting Concepts (FALCON), an interpretability framework to explain features of image representations. For a target feature, FALCON captions its highly activating cropped images using a large captioning dataset (like LAION-400m) and a pre-trained vi…