2 citations · 2 across the 6 of their papers we have counts for
3 papers · 1 filter
Why Prototypes Collapse: Diagnosing and Preventing Partial Collapse in Prototypical Self-Supervised Learning
Gabriel Y. Arteaga, Marius Aasan, Rwiddhi Chakraborty +4
Prototypical self-supervised learning methods consistently suffer from partial prototype collapse, where multiple prototypes converge to nearly identical representations. This unde…
RC2020 Report: Learning De-biased Representations with Biased Representations
Rwiddhi Chakraborty, Shubhayu Das
As part of the ML Reproducibility Challenge 2020, we investigated the ICML 2020 paper "Learning De-biased Representations with Biased Representations" by Bahng et al., where the au…
A Review and Refinement of Surprise Adequacy
Michael Weiss, Rwiddhi Chakraborty, Paolo Tonella
Surprise Adequacy (SA) is one of the emerging and most promising adequacy criteria for Deep Learning (DL) testing. As an adequacy criterion, it has been used to assess the strength…