paper-with-me

Papers

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

2024-03-21 · Elena Camuffo, Umberto Michieli, Jijoong Moon, Daehyun Kim, Mete Ozay

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.

📄 PDF Abstract BibTeX arXiv:2403.14335

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Structured Low-Rank Matrix Factorization with Missing and Grossly Corrupted Observations

2014-09-03 · Fanhua Shang, Yuanyuan Liu, Hanghang Tong, James Cheng 외

Recovering low-rank and sparse matrices from incomplete or corrupted observations is an important problem in machine learning, statistics, bioinformatics, computer vision, as well as signal and image processing. In theor…

Matrix Completion

Scalable Cluster-Consistency Statistics for Robust Multi-Object Matching

2022-01-13 · Yunpeng Shi, Shaohan Li, Tyler Maunu, Gilad Lerman

We develop new statistics for robustly filtering corrupted keypoint matches in the structure from motion pipeline. The statistics are based on consistency constraints that arise within the clustered structure of the grap…

Robust Surface Reconstruction via Triple Sparsity

2014-06-01 · CVPR 2014 6 · Hicham Badri, Hussein Yahia, Driss Aboutajdine

Reconstructing a surface/image from corrupted gradient fields is a crucial step in many imaging applications where a gradient field is subject to both noise and unlocalized outliers, resulting typically in a non-integra…

Surface Reconstruction

Tent: Fully Test-time Adaptation by Entropy Minimization

2020-06-18 · ICLR 2021 1 · Dequan Wang, Evan Shelhamer, Shaoteng Liu, Bruno Olshausen 외

A model must adapt itself to generalize to new and different data during testing. In this setting of fully test-time adaptation the model has only the test data and its own parameters. We propose to adapt by test entropy…

Domain AdaptationGeneral Classificationimage-classificationImage Classification+3

Per-Sample Kernel Adaptation for Visual Recognition and Grouping

2015-12-01 · ICCV 2015 12 · Borislav Antic, Bjorn Ommer

Object, action, or scene representations that are corrupted by noise significantly impair the performance of visual recognition. Typically, partial occlusion, clutter, or excessive articulation affects only a subset of a…

Action RecognitionAction Recognition In Videosfeature selectionGeneral Classification+3