SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.08945 · ICLR · 2022

Missingness Bias in Model Debugging

Salman Hadi, Aleksander Ądry, Pengchuan Zhang, Saachi Jain, Eric Wong, Vibhav Vineet, Sai Vemprala

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Missingness, or the absence of features from an input, is a concept fundamental to many model debugging tools. However, in computer vision, pixels cannot simply be removed from an image. One thus tends to resort to heuristics such as blacking out pixels, which may in turn introduce bias into the debugging process. We study such biases and, in particular, show how transformer-based architectures can enable a more natural implementation of missingness, which side-steps these issues and improves the reliability of model debugging in practice. 1

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2204.08945")
get_code_for_paper("2204.08945")
have("2204.08945")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2204.08945.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2204.08945.svg)](https://syntology.ai/paper/2204.08945)

Connect an agent — have() is free.