Timezone: »

 
Poster
A Geometric Perspective towards Neural Calibration via Sensitivity Decomposition
Junjiao Tian · Dylan Yung · Yen-Chang Hsu · Zsolt Kira

Thu Dec 09 08:30 AM -- 10:00 AM (PST) @

It is well known that vision classification models suffer from poor calibration in the face of data distribution shifts. In this paper, we take a geometric approach to this problem. We propose Geometric Sensitivity Decomposition (GSD) which decomposes the norm of a sample feature embedding and the angular similarity to a target classifier into an instance-dependent and an instance-independent com-ponent. The instance-dependent component captures the sensitive information about changes in the input while the instance-independent component represents the insensitive information serving solely to minimize the loss on the training dataset. Inspired by the decomposition, we analytically derive a simple extension to current softmax-linear models, which learns to disentangle the two components during training. On several common vision models, the disentangled model out-performs other calibration methods on standard calibration metrics in the face of out-of-distribution (OOD) data and corruption with significantly less complexity. Specifically, we surpass the current state of the art by 30.8% relative improvement on corrupted CIFAR100 in Expected Calibration Error.

Author Information

Junjiao Tian (Georgia Institute of Technology)
Dylan Yung (Georgia Institute of Technology)
Yen-Chang Hsu (Georgia Institute of Technology)
Zsolt Kira (Georgia Institute of Techology)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors

  • 2021 Spotlight: Habitat 2.0: Training Home Assistants to Rearrange their Habitat »
    Andrew Szot · Alexander Clegg · Eric Undersander · Erik Wijmans · Yili Zhao · John Turner · Noah Maestre · Mustafa Mukadam · Devendra Singh Chaplot · Oleksandr Maksymets · Aaron Gokaslan · Vladimír Vondruš · Sameer Dharur · Franziska Meier · Wojciech Galuba · Angel Chang · Zsolt Kira · Vladlen Koltun · Jitendra Malik · Manolis Savva · Dhruv Batra
  • 2021 : Exploring Covariate and Concept Shift for Out-of-Distribution Detection »
    Junjiao Tian · Yen-Chang Hsu · Yilin Shen · Hongxia Jin · Zsolt Kira
  • 2022 : Fifteen-minute Competition Overview Video »
    Dhruv Batra · Manolis Savva · Zsolt Kira · Vincent-Pierre Berges · Karmesh Yadav · Angel Chang · Andrew Szot · Alexander Clegg · Aaron Gokaslan
  • 2022 : On the Surprising Effectiveness of Transformers in Low-Labeled Video Recognition »
    Farrukh Rahman · Ömer Mubarek · Zsolt Kira
  • 2022 Competition: Habitat Rearrangement Challenge »
    Andrew Szot · Karmesh Yadav · Alexander Clegg · Vincent-Pierre Berges · Aaron Gokaslan · Angel Chang · Manolis Savva · Zsolt Kira · Dhruv Batra
  • 2022 : Panel »
    Tyler Hayes · Tinne Tuytelaars · Subutai Ahmad · João Sacramento · Zsolt Kira · Hava Siegelmann · Christopher Summerfield
  • 2022 Poster: Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Tasks »
    Yen-Cheng Liu · CHIH-YAO MA · Junjiao Tian · Zijian He · Zsolt Kira
  • 2021 : Habitat 2.0: Training Home Assistants to Rearrange their Habitat »
    Andrew Szot · Alexander Clegg · Eric Undersander · Erik Wijmans · Yili Zhao · Noah Maestre · Mustafa Mukadam · Oleksandr Maksymets · Aaron Gokaslan · Sameer Dharur · Franziska Meier · Wojciech Galuba · Angel Chang · Zsolt Kira · Vladlen Koltun · Jitendra Malik · Manolis Savva · Dhruv Batra
  • 2021 : Habitat 2.0: Training Home Assistants to Rearrange their Habitat »
    Andrew Szot · Alexander Clegg · Eric Undersander · Erik Wijmans · Yili Zhao · Noah Maestre · Mustafa Mukadam · Oleksandr Maksymets · Aaron Gokaslan · Sameer Dharur · Franziska Meier · Wojciech Galuba · Angel Chang · Zsolt Kira · Vladlen Koltun · Jitendra Malik · Manolis Savva · Dhruv Batra
  • 2021 Poster: Habitat 2.0: Training Home Assistants to Rearrange their Habitat »
    Andrew Szot · Alexander Clegg · Eric Undersander · Erik Wijmans · Yili Zhao · John Turner · Noah Maestre · Mustafa Mukadam · Devendra Singh Chaplot · Oleksandr Maksymets · Aaron Gokaslan · Vladimír Vondruš · Sameer Dharur · Franziska Meier · Wojciech Galuba · Angel Chang · Zsolt Kira · Vladlen Koltun · Jitendra Malik · Manolis Savva · Dhruv Batra
  • 2020 Poster: Posterior Re-calibration for Imbalanced Datasets »
    Junjiao Tian · Yen-Cheng Liu · Nathaniel Glaser · Yen-Chang Hsu · Zsolt Kira
  • 2018 : Lunch & Posters »
    Haytham Fayek · German Parisi · Brian Xu · Pramod Kaushik Mudrakarta · Sophie Cerf · Sarah Wassermann · Davit Soselia · Rahaf Aljundi · Mohamed Elhoseiny · Frantzeska Lavda · Kevin J Liang · Arslan Chaudhry · Sanmit Narvekar · Vincenzo Lomonaco · Wesley Chung · Michael Chang · Ying Zhao · Zsolt Kira · Pouya Bashivan · Banafsheh Rafiee · Oleksiy Ostapenko · Andrew Jones · Christos Kaplanis · Sinan Kalkan · Dan Teng · Xu He · Vincent Liu · Somjit Nath · Sungsoo Ahn · Ting Chen · Shenyang Huang · Yash Chandak · Nathan Sprague · Martin Schrimpf · Tony Kendall · Jonathan Schwarz · Michael Li · Yunshu Du · Yen-Chang Hsu · Samira Abnar · Bo Wang