FFT-Based Selection and Optimization of Statistics for Robust Recognition of Severely Corrupted Images

Improving model robustness in case of corrupted images is among the key challenges to enable robust vision systems on smart devices, such as robotic agents. Particularly, robust test-time performance is imperative for most of the applications. This paper presents a novel approach to improve robustne...

Full description

Saved in:
Bibliographic Details
Main Authors: Camuffo, Elena, Michieli, Umberto, Moon, Jijoong, Kim, Daehyun, Ozay, Mete
Format: Conference Proceeding
Language:English
Subjects:
Corruptions
Feature extraction
Fourier Transform
Object Recognition
Performance evaluation
Robustness
Signal processing
Speech processing
Speech recognition
Transforms
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Improving model robustness in case of corrupted images is among the key challenges to enable robust vision systems on smart devices, such as robotic agents. Particularly, robust test-time performance is imperative for most of the applications. This paper presents a novel approach to improve robustness of any classification model, especially on severely corrupted images. Our method (FROST) employs high-frequency features to detect input image corruption type, and select layer-wise feature normalization statistics. FROST provides the state-of-the-art results for different models and datasets, outperforming competitors on ImageNet-C by up to 37.1% relative gain, improving baseline of 40.9% mCE on severe corruptions.
ISSN:2379-190X
DOI:10.1109/ICASSP48485.2024.10447639