English
Related papers

Related papers: Shortcut Learning Susceptibility in Vision Classif…

200 papers

Advances in deep learning are re-defining how visual data is processed and understand by the machines. Vision Transformers (ViTs) have recently demonstrated prominent performance in computer vision related tasks. However, their performance…

Deep neural networks are susceptible to shortcut learning, using simple features to achieve low training loss without discovering essential semantic structure. Contrary to prior belief, we show that generative models alone are not…

Machine Learning · Computer Science 2022-11-29 Wanqian Yang , Polina Kirichenko , Micah Goldblum , Andrew Gordon Wilson

In recent years, convolutional neural networks (CNNs) have achieved impressive performance for various visual recognition scenarios. CNNs trained on large labeled datasets can not only obtain significant performance on most challenging…

Computer Vision and Pattern Recognition · Computer Science 2023-03-29 Xiangyang Li , Luis Herranz , Shuqiang Jiang

When seeing a new object, humans can immediately recognize it across different retinal locations: we say that the internal object representation is invariant to translation. It is commonly believed that Convolutional Neural Networks (CNNs)…

Computer Vision and Pattern Recognition · Computer Science 2020-11-25 Valerio Biscione , Jeffrey Bowers

This paper presents a comparative study of a custom convolutional neural network (CNN) architecture against widely used pretrained and transfer learning CNN models across five real-world image datasets. The datasets span binary…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Mahmudul Hasan , Mabsur Fatin Bin Hossain

Vision-Language Models (VLMs) achieve strong cross-modal performance, yet recent evidence suggests they over-rely on textual descriptions while under-utilizing visual evidence -- a phenomenon termed ``text shortcut learning.'' We propose an…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Lijie Zhou

Unsupervised visual representation learning remains a largely unsolved problem in computer vision research. Among a big body of recently proposed approaches for unsupervised learning of visual representations, a class of self-supervised…

Computer Vision and Pattern Recognition · Computer Science 2019-01-28 Alexander Kolesnikov , Xiaohua Zhai , Lucas Beyer

Transformer models have achieved great progress on computer vision tasks recently. The rapid development of vision transformers is mainly contributed by their high representation ability for extracting informative features from input…

Computer Vision and Pattern Recognition · Computer Science 2021-07-01 Yehui Tang , Kai Han , Chang Xu , An Xiao , Yiping Deng , Chao Xu , Yunhe Wang

Vision Transformers (ViTs) that leverage self-attention mechanism have shown superior performance on many classical vision tasks compared to convolutional neural networks (CNNs) and gain increasing popularity recently. Existing ViTs works…

Cryptography and Security · Computer Science 2024-04-29 Xinghua Xue , Cheng Liu , Ying Wang , Bing Yang , Tao Luo , Lei Zhang , Huawei Li , Xiaowei Li

It is well accepted that convolutional neural networks play an important role in learning excellent features for image classification and recognition. However, in tradition they only allow adjacent layers connected, limiting integration of…

Computer Vision and Pattern Recognition · Computer Science 2017-10-04 Yujian Li , Ting Zhang , Zhaoying Liu , Haihe Hu

The hybrid architecture of convolutional neural networks (CNNs) and Transformer are very popular for medical image segmentation. However, it suffers from two challenges. First, although a CNNs branch can capture the local image features…

Image and Video Processing · Electrical Eng. & Systems 2023-12-21 Tao Lei , Rui Sun , Xuan Wang , Yingbo Wang , Xi He , Asoke Nandi

Vision Transformers (ViTs), when pre-trained on large-scale data, provide general-purpose representations for diverse downstream tasks. However, artifacts in ViTs are widely observed across different supervision paradigms and downstream…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Cheng Shi , Yizhou Yu , Sibei Yang

Deep neural networks are often considered opaque systems, prompting the need for explainability methods to improve trust and accountability. Existing approaches typically attribute test-time predictions either to input features (e.g.,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Aziz Bacha , Thomas George

Radiographs are a versatile diagnostic tool for the detection and assessment of pathologies, for treatment planning or for navigation and localization purposes in clinical interventions. However, their interpretation and assessment by…

Computer Vision and Pattern Recognition · Computer Science 2022-08-18 Finn Behrendt , Debayan Bhattacharya , Julia Krüger , Roland Opfer , Alexander Schlaefer

Convolutional Neural Networks (CNNs) are a popular type of computer model that have proven their worth in many computer vision tasks. Moreover, they form an interesting study object for the field of psychology, with shown correspondences…

Computer Vision and Pattern Recognition · Computer Science 2025-12-04 Laurent Mertens , Elahe' Yargholi , Laura Van Hove , Hans Op de Beeck , Jan Van den Stock , Joost Vennekens

Deep neural networks (DNNs) are vulnerable to shortcut learning: rather than learning the intended task, they tend to draw inconclusive relationships between their inputs and outputs. Shortcut learning is ubiquitous among many failure cases…

Machine Learning · Computer Science 2024-08-27 Hadi M. Dolatabadi , Sarah M. Erfani , Christopher Leckie

Vision Transformers (ViT) have recently demonstrated the significant potential of transformer architectures for computer vision. To what extent can image-based deep reinforcement learning also benefit from ViT architectures, as compared to…

Machine Learning · Computer Science 2022-05-17 Tianxin Tao , Daniele Reda , Michiel van de Panne

Large Vision-Language Models (LVLMs) typically align visual features from an encoder with a pre-trained Large Language Model (LLM). However, this makes the visual perception module a bottleneck, which constrains the overall capabilities of…

Artificial Intelligence · Computer Science 2025-11-18 Wenhao Zhou , Hao Zheng , Rong Zhao

Shape learning, or the ability to leverage shape information, could be a desirable property of convolutional neural networks (CNNs) when target objects have specific shapes. While some research on the topic is emerging, there is no…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Yixin Zhang , Maciej A. Mazurowski

Machine learning models tend to over-rely on statistical shortcuts. These spurious correlations between parts of the input and the output labels does not hold in real-world settings. We target this issue on the recent open-ended visual…

Computer Vision and Pattern Recognition · Computer Science 2020-07-02 Corentin Dancette , Remi Cadene , Xinlei Chen , Matthieu Cord
‹ Prev 1 4 5 6 7 8 10 Next ›