paper-with-me

Papers

Improving robustness against common corruptions by covariate shift adaptation

2020-06-30 · NeurIPS 2020 12 · Steffen Schneider, Evgenia Rusak, Luisa Eck, Oliver Bringmann, Wieland Brendel, Matthias Bethge

Today's state-of-the-art machine vision models are vulnerable to image corruptions like blurring or compression artefacts, limiting their performance in many real-world applications. We here argue that popular benchmarks to measure model robustness against common corruptions (like ImageNet-C) underestimate model robustness in many (but not all) application scenarios. The key insight is that in many scenarios, multiple unlabeled examples of the corruptions are available and can be used for unsupervised online adaptation. Replacing the activation statistics estimated by batch normalization on the training set with the statistics of the corrupted images consistently improves the robustness across 25 different popular computer vision models. Using the corrected statistics, ResNet-50 reaches 62.2% mCE on ImageNet-C compared to 76.7% without adaptation. With the more robust DeepAugment+AugMix model, we improve the state of the art achieved by a ResNet50 model up to date from 53.6% mCE to 45.4% mCE. Even adapting to a single sample improves robustness for the ResNet-50 and AugMix models, and 32 samples are sufficient to improve the current state of the art for a ResNet-50 architecture. We argue that results with adapted statistics should be included whenever reporting scores in corruption benchmarks and other out-of-distribution generalization settings.

📄 PDF Abstract BibTeX arXiv:2006.16971

Code (2)

bethgelab/robustness 공식 구현 pytorch
Claydon-Wang/OFTTA pytorch

Tasks

Domain GeneralizationImage ClassificationOut-of-Distribution GeneralizationUnsupervised Domain Adaptation

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Average Pooling 설명 없음
Residual Connection 설명 없음
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…

Similar Papers 제목 키워드 기반

Tackling covariate shift with node-based Bayesian neural networks

2022-06-06 · Trung Trinh, Markus Heinonen, Luigi Acerbi, Samuel Kaski

Bayesian neural networks (BNNs) promise improved generalization under covariate shift by providing principled probabilistic representations of epistemic uncertainty. However, weight-based BNNs often struggle with high co…

Diversityimage-classificationImage Classification

Diverse Gaussian Noise Consistency Regularization for Robustness and Uncertainty Calibration

2021-04-02 · Theodoros Tsiligkaridis, Athanasios Tsiligkaridis

Deep neural networks achieve high prediction accuracy when the train and test distributions coincide. In practice though, various types of corruptions occur which deviate from this setup and cause severe performance degr…

Data AugmentationImage Classification

Benchmarking the Robustness of UAV Tracking Against Common Corruptions

2024-03-18 · Xiaoqiong Liu, Yunhe Feng, Shu Hu, Xiaohui Yuan 외

The robustness of unmanned aerial vehicle (UAV) tracking is crucial in many tasks like surveillance and robotics. Despite its importance, little attention is paid to the performance of UAV trackers under common corruptio…

Benchmarking

Trimmed Maximum Likelihood Estimation for Robust Learning in Generalized Linear Models

2022-06-09 · Pranjal Awasthi, Abhimanyu Das, Weihao Kong, Rajat Sen

We study the problem of learning generalized linear models under adversarial corruptions. We analyze a classical heuristic called the iterative trimmed maximum likelihood estimator which is known to be effective against …

regression

Fourier-Based Augmentations for Improved Robustness and Uncertainty Calibration

2022-02-24 · Ryan Soklaski, Michael Yee, Theodoros Tsiligkaridis

Diverse data augmentation strategies are a natural approach to improving robustness in computer vision models against unforeseen shifts in data distribution. However, the ability to tailor such strategies to inoculate a …

Data AugmentationImage Augmentation