English
Related papers

Related papers: Do Image Classifiers Generalize Across Time?

200 papers

In this paper we establish rigorous benchmarks for image classifier robustness. Our first benchmark, ImageNet-C, standardizes and expands the corruption robustness topic, while showing which classifiers are preferable in safety-critical…

Machine Learning · Computer Science 2019-04-01 Dan Hendrycks , Thomas Dietterich

Discriminative self-supervised learning allows training models on any random group of internet images, and possibly recover salient information that helps differentiate between the images. Applied to ImageNet, this leads to object centric…

Computer Vision and Pattern Recognition · Computer Science 2022-02-23 Priya Goyal , Quentin Duval , Isaac Seessel , Mathilde Caron , Ishan Misra , Levent Sagun , Armand Joulin , Piotr Bojanowski

ConvNets and Imagenet have driven the recent success of deep learning for image classification. However, the marked slowdown in performance improvement combined with the lack of robustness of neural networks to adversarial examples and…

Machine Learning · Computer Science 2018-07-23 Pierre Stock , Moustapha Cisse

Recently, it was found that many real-world examples without intentional modifications can fool machine learning models, and such examples are called "natural adversarial examples". ImageNet-A is a famous dataset of natural adversarial…

Computer Vision and Pattern Recognition · Computer Science 2021-02-24 Xiao Li , Jianmin Li , Ting Dai , Jie Shi , Jun Zhu , Xiaolin Hu

Images can vary according to changes in viewpoint, resolution, noise, and illumination. In this paper, we aim to learn representations for an image, which are robust to wide changes in such environmental conditions, using training pairs of…

Computer Vision and Pattern Recognition · Computer Science 2013-01-17 Kye-Hyeon Kim , Rui Cai , Lei Zhang , Seungjin Choi

This paper strives for video event detection using a representation learned from deep convolutional neural networks. Different from the leading approaches, who all learn from the 1,000 classes defined in the ImageNet Large Scale Visual…

Computer Vision and Pattern Recognition · Computer Science 2017-12-14 Pascal Mettes , Dennis C. Koelma , Cees G. M. Snoek

Recurrent neural networks have recently been used for learning to describe images using natural language. However, it has been observed that these models generalize poorly to scenes that were not observed during training, possibly depending…

Computer Vision and Pattern Recognition · Computer Science 2016-08-30 Yuval Atzmon , Jonathan Berant , Vahid Kezami , Amir Globerson , Gal Chechik

Image classifiers should be used with caution in the real world. Performance evaluated on a validation set may not reflect performance in the real world. In particular, classifiers may perform well for conditions that are frequently…

Computer Vision and Pattern Recognition · Computer Science 2024-09-30 Adrien LeCoz , Houssem Ouertatani , Stéphane Herbin , Faouzi Adjed

News videos require efficient content organisation and retrieval systems, but their unstructured nature poses significant challenges for automated processing. This paper presents a comprehensive comparative analysis of image, video, and…

Computer Vision and Pattern Recognition · Computer Science 2025-03-31 Jonathan Attard , Dylan Seychell

Standard adversarial attacks change the predicted class label of a selected image by adding specially tailored small perturbations to its pixels. In contrast, a universal perturbation is an update that can be added to any image in a broad…

Computer Vision and Pattern Recognition · Computer Science 2019-11-22 Ali Shafahi , Mahyar Najibi , Zheng Xu , John Dickerson , Larry S. Davis , Tom Goldstein

In cinema, visual motifs are recurrent iconographic compositions that carry artistic or aesthetic significance. Their use throughout the history of visual arts and media is interesting to researchers and filmmakers alike. Our goal in this…

Computer Vision and Pattern Recognition · Computer Science 2024-10-22 Adam Phillips , Daniel Grandes Rodriguez , Miriam Sánchez-Manzano , Alan Salvadó , Manuel Garin , Gloria Haro , Coloma Ballester

Since its release, ImageNet-1k dataset has become a gold standard for evaluating model performance. It has served as the foundation for numerous other datasets and training tasks in computer vision. As models have improved in accuracy,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Nikita Kisel , Illia Volkov , Katerina Hanzelkova , Klara Janouskova , Jiri Matas

Convolutional neural networks (CNNs) have demonstrated remarkable success in vision-related tasks. However, their susceptibility to failing when inputs deviate from the training distribution is well-documented. Recent studies suggest that…

Computer Vision and Pattern Recognition · Computer Science 2023-07-14 Pradyumna Elavarthi , James Lee , Anca Ralescu

Natural distribution shift causes a deterioration in the perception performance of convolutional neural networks (CNNs). This comprehensive analysis for real-world traffic data addresses: 1) investigating the effect of natural distribution…

Computer Vision and Pattern Recognition · Computer Science 2024-09-24 Fabian Diet , Moussa Kassem Sbeyti , Michelle Karg

The prediction accuracy has been the long-lasting and sole standard for comparing the performance of different image classification models, including the ImageNet competition. However, recent studies have highlighted the lack of robustness…

Computer Vision and Pattern Recognition · Computer Science 2019-03-05 Dong Su , Huan Zhang , Hongge Chen , Jinfeng Yi , Pin-Yu Chen , Yupeng Gao

Perceptual distances between images, as measured in the space of pre-trained deep features, have outperformed prior low-level, pixel-based metrics on assessing perceptual similarity. While the capabilities of older and less accurate models…

Computer Vision and Pattern Recognition · Computer Science 2022-11-01 Manoj Kumar , Neil Houlsby , Nal Kalchbrenner , Ekin D. Cubuk

Contrastively trained language-image models such as CLIP, ALIGN, and BASIC have demonstrated unprecedented robustness to multiple challenging natural distribution shifts. Since these language-image models differ from previous training…

Computer Vision and Pattern Recognition · Computer Science 2022-08-24 Alex Fang , Gabriel Ilharco , Mitchell Wortsman , Yuhao Wan , Vaishaal Shankar , Achal Dave , Ludwig Schmidt

While video compression algorithms effectively reduce bitrate, aggressive quantization often compromises temporal coherence, introducing artifacts such as flicker, motion inconsistency, and unstable textures. Although spatial quality…

Image and Video Processing · Electrical Eng. & Systems 2026-05-19 Peter Zsoldos

As video analysis using deep learning models becomes more widespread, the vulnerability of such models to adversarial attacks is becoming a pressing concern. In particular, Universal Adversarial Perturbation (UAP) poses a significant…

Computer Vision and Pattern Recognition · Computer Science 2023-11-20 Hee-Seon Kim , Minji Son , Minbeom Kim , Myung-Joon Kwon , Changick Kim

Humans represent scenes and objects in rich feature spaces, carrying information that allows us to generalise about category memberships and abstract functions with few examples. What determines whether a neural network model generalises…