paper-with-me

홈 › Papers

Correlated Input-Dependent Label Noise in Large-Scale Image Classification

2021-05-19 · CVPR 2021 1 · Mark Collier, Basil Mustafa, Efi Kokiopoulou, Rodolphe Jenatton, Jesse Berent

Large scale image classification datasets often contain noisy labels. We take a principled probabilistic approach to modelling input-dependent, also known as heteroscedastic, label noise in these datasets. We place a multivariate Normal distributed latent variable on the final hidden layer of a neural network classifier. The covariance matrix of this latent variable, models the aleatoric uncertainty due to label noise. We demonstrate that the learned covariance structure captures known sources of label noise between semantically similar and co-occurring classes. Compared to standard neural network training and other baselines, we show significantly improved accuracy on Imagenet ILSVRC 2012 79.3% (+2.6%), Imagenet-21k 47.0% (+1.1%) and JFT 64.7% (+1.6%). We set a new state-of-the-art result on WebVision 1.0 with 76.6% top-1 accuracy. These datasets range from over 1M to over 300M training examples and from 1k classes to more than 21k classes. Our method is simple to use, and we provide an implementation that is a drop-in replacement for the final fully-connected layer in a deep classifier.

📄 PDF Abstract BibTeX arXiv:2105.10305

Code (0)

등록된 구현이 없습니다.

Tasks

Classificationimage-classificationImage Classification

Similar Papers 제목 키워드 기반

Handling Realistic Label Noise in BERT Text Classification

2023-05-23 · Maha Tufail Agro, Hanan Aldarmaki

Labels noise refers to errors in training labels caused by cheap data annotation methods, such as web scraping or crowd-sourcing, which can be detrimental to the performance of supervised classifiers. Several methods hav…

Classificationtext-classificationText Classification

Unsupervised Denoising for Signal-Dependent and Row-Correlated Imaging Noise

2023-10-11 · Benjamin Salmon, Alexander Krull

Accurate analysis of microscopy images is hindered by the presence of noise. This noise is usually signal-dependent and often additionally correlated along rows or columns of pixels. Current self- and unsupervised denois…

DecoderDenoisingImage Denoising

Median2Median: Zero-shot Suppression of Structured Noise in Images

2025-10-02 · Jianxu Wang, Ge Wang arxiv

Image denoising is a fundamental problem in computer vision and medical imaging. However, real-world images are often degraded by structured noise with strong anisotropic correlations that existing methods struggle to re…

Image Denoising

Disentangling Correlated Speaker and Noise for Speech Synthesis via Data Augmentation and Adversarial Factorization

2018-10-30 · NIPS Workshop IRASL 2018 · Anonymous

To leverage crowd-sourced data to train multi-speaker text-to-speech (TTS) models that can synthesize clean speech for all speakers, it is essential to learn disentangled representations which can independently control t…

Data AugmentationDisentanglementSpeech Synthesistext-to-speech+1

PCA in Data-Dependent Noise (Correlated-PCA): Nearly Optimal Finite Sample Guarantees

2017-02-10 · Namrata Vaswani, Praneeth Narayanamurthy

We study Principal Component Analysis (PCA) in a setting where a part of the corrupting noise is data-dependent and, as a result, the noise and the true data are correlated. Under a bounded-ness assumption on the true da…