English
Related papers

Related papers: Consistent Semantic Attacks on Optical Flow

200 papers

In this paper we introduce the target flow -- a specific curve shortening flow with an ambient forcing term -- that, given an embedded (not necessarily convex) target curve, will attempt to evolve a given source curve to that target. The…

Differential Geometry · Mathematics 2024-12-02 Samuel Cuthbertson , Glen Wheeler , Valentina Wheeler

The importance and demands of visual scene understanding have been steadily increasing along with the active development of autonomous systems. Consequently, there has been a large amount of research dedicated to semantic segmentation and…

Computer Vision and Pattern Recognition · Computer Science 2016-07-27 Junhwa Hur , Stefan Roth

Adversarial attacks on machine learning models often rely on small, imperceptible perturbations to mislead classifiers. Such strategy focuses on minimizing the visual perturbation for humans so they are not confused, and also maximizing the…

Computer Vision and Pattern Recognition · Computer Science 2025-02-28 Anthony Etim , Jakub Szefer

Imposing consistency through proxy tasks has been shown to enhance data-driven learning and enable self-supervision in various tasks. This paper introduces novel and effective consistency strategies for optical flow estimation, a problem…

Computer Vision and Pattern Recognition · Computer Science 2022-05-25 Jisoo Jeong , Jamie Menjay Lin , Fatih Porikli , Nojun Kwak

Adversarial attacks that generate small L_p-norm perturbations to mislead classifiers have limited success in black-box settings and with unseen classifiers. These attacks are also not robust to defenses that use denoising filters and to…

Computer Vision and Pattern Recognition · Computer Science 2020-04-14 Ali Shahin Shamsabadi , Ricardo Sanchez-Matilla , Andrea Cavallaro

Adversarial attacks play an essential role in understanding deep neural network predictions and improving their robustness. Existing attack methods aim to deceive convolutional neural network (CNN)-based classifiers by manipulating RGB…

Computer Vision and Pattern Recognition · Computer Science 2021-02-22 Buu Phan , Fahim Mannan , Felix Heide

Finding image correspondences remains a challenging problem in the presence of intra-class variations and large changes in scene layout.~Semantic flow methods are designed to handle images depicting different instances of the same object or…

Computer Vision and Pattern Recognition · Computer Science 2016-07-11 Bumsub Ham , Minsu Cho , Cordelia Schmid , Jean Ponce

Adversarial attacks aim to perturb images such that a predictor outputs incorrect results. Due to the limited research in structured attacks, imposing consistency checks on natural multi-object scenes is a promising yet practical defense…

Computer Vision and Pattern Recognition · Computer Science 2023-03-09 Buyu Liu , BaoJun , Jianping Fan , Xi Peng , Kui Ren , Jun Yu

Despite significant advances in the area, adversarial robustness remains a critical challenge in systems employing machine learning models. The removal of adversarial perturbations at inference time, known as adversarial purification, has…

Machine Learning · Computer Science 2026-03-31 Elias Collaert , Abel Rodríguez , Sander Joos , Lieven Desmet , Vera Rimmer

The landscape of adversarial attacks against text classifiers continues to grow, with new attacks developed every year and many of them available in standard toolkits, such as TextAttack and OpenAttack. In response, there is a growing body…

Computation and Language · Computer Science 2022-01-24 Zhouhang Xie , Jonathan Brophy , Adam Noack , Wencong You , Kalyani Asthana , Carter Perkins , Sabrina Reis , Sameer Singh , Daniel Lowd

Adversarial attack is aimed at fooling the target classifier with imperceptible perturbation. Adversarial examples, which are carefully crafted with a malicious purpose, can lead to erroneous predictions, resulting in catastrophic…

Machine Learning · Computer Science 2021-11-19 Mingu Kang , Trung Quang Tran , Seungju Cho , Daeyoung Kim

In Virtual Reality (VR), adversarial attack remains a significant security threat. Most deep learning-based methods for physical and digital adversarial attacks focus on enhancing attack performance by crafting adversarial examples that…

Computer Vision and Pattern Recognition · Computer Science 2024-03-25 Qianyu Guo , Jiaming Fu , Yawen Lu , Dongming Gan

We present a new method for black-box adversarial attack. Unlike previous methods that combined transfer-based and scored-based methods by using the gradient or initialization of a surrogate white-box model, this new method tries to learn a…

Machine Learning · Computer Science 2020-01-07 Zhichao Huang , Tong Zhang

Optical flow estimation is one of the fundamental tasks in low-level computer vision, which describes the pixel-wise displacement and can be used in many other tasks. From the apparent aspect, the optical flow can be viewed as the…

Computer Vision and Pattern Recognition · Computer Science 2024-05-22 Yuhao Cheng , Siru Zhang , Yiqiang Yan

Adversarial black-box attacks aim to craft adversarial perturbations by querying input-output pairs of machine learning models. They are widely used to evaluate the robustness of pre-trained models. However, black-box attacks often suffer…

Machine Learning · Computer Science 2020-11-11 Lu Wang , Huan Zhang , Jinfeng Yi , Cho-Jui Hsieh , Yuan Jiang

Traditional network interdiction refers to the problem of an interdictor trying to reduce the throughput of network users by removing network edges. In this paper, we propose a new paradigm for network interdiction that models scenarios,…

Networking and Internet Architecture · Computer Science 2019-01-10 Xinzhe Fu , Eytan Modiano

Deep learning models achieve remarkable accuracy in computer vision tasks, yet remain vulnerable to adversarial examples--carefully crafted perturbations to input images that can deceive these models into making confident but incorrect…

Computer Vision and Pattern Recognition · Computer Science 2025-04-18 Khoi Nguyen Tiet Nguyen , Wenyu Zhang , Kangkang Lu , Yuhuan Wu , Xingjian Zheng , Hui Li Tan , Liangli Zhen

Adversarial attacks involve adding, small, often imperceptible, perturbations to inputs with the goal of getting a machine learning model to misclassifying them. While many different adversarial attack strategies have been proposed on image…

Computer Vision and Pattern Recognition · Computer Science 2018-06-01 Avishek Joey Bose , Parham Aarabi

Normalizing flows are prominent deep generative models that provide tractable probability distributions and efficient density estimation. However, they are well known to fail while detecting Out-of-Distribution (OOD) inputs as they directly…

Machine Learning · Computer Science 2021-11-17 Nishant Kumar , Pia Hanfeld , Michael Hecht , Michael Bussmann , Stefan Gumhold , Nico Hoffmann

Optical flow techniques are becoming increasingly performant and robust when estimating motion in a scene, but their performance has yet to be proven in the area of facial expression recognition. In this work, a variety of optical flow…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Benjamin Allaert , Isaac Ronald Ward , Ioan Marius Bilasco , Chaabane Djeraba , Mohammed Bennamoun