Related papers: Robustness Certification of Visual Perception Mode…

Machine learning models have demonstrated remarkable success across diverse domains but remain vulnerable to adversarial attacks. Empirical defense mechanisms often fail, as new attacks constantly emerge, rendering existing defenses…

Previous research contributions on blind lossy compression identification report near perfect performance metrics on their test set, across a variety of codecs and bit rates. However, we show that such results can be deceptive and may not…

Trustworthy machine learning necessitates meticulous regulation of model reliance on non-robust features. We propose a framework to delineate and regulate such features by attributing model predictions to the input. Within our approach,…

We introduce an improved solution to the neural image-based rendering problem in computer vision. Given a set of images taken from a freely moving camera at train time, the proposed approach could synthesize a realistic image of the scene…

Feature matching is an important computer vision task that involves estimating correspondences between two images of a 3D scene, and dense methods estimate all such correspondences. The aim is to learn a robust model, i.e., a model able to…

Medical Vision-Language Models (MVLMs) have achieved par excellence generalization in medical image analysis, yet their performance under noisy, corrupted conditions remains largely untested. Clinical imaging is inherently susceptible to…

Multi-object tracking (MOT) is a fundamental task in computer vision that requires continuously tracking multiple targets while maintaining consistent identities across frames. However, most existing approaches primarily rely on…

We introduce a framework that enables both multi-view character consistency and 3D camera control in video diffusion models through a novel customization data pipeline. We train the character consistency component with recorded volumetric…

Real-time dense scene reconstruction during unstable camera motions is crucial for robotics, yet current RGB-D SLAM systems fail when cameras experience large viewpoint changes, fast motions, or sudden shaking. Classical optimization-based…

Multimodal Large Language Models struggle to maintain reliable performance under extreme real-world visual degradations, which impede their practical robustness. Existing robust MLLMs predominantly rely on implicit training/adaptation that…

Point cloud models with neural network architectures have achieved great success and have been widely used in safety-critical applications, such as Lidar-based recognition systems in autonomous vehicles. However, such models are shown…

The robustness of algorithms against covariate shifts is a fundamental problem with critical implications for the deployment of machine learning algorithms in the real world. Current evaluation methods predominantly measure robustness…

A machine learning model is traditionally considered robust if its prediction remains (almost) constant under input perturbations with small norm. However, real-world tasks like molecular property prediction or point cloud segmentation have…

We propose a smooth regularization technique that instills a strong temporal inductive bias in video recognition models, particularly benefiting lightweight architectures. Our method encourages smoothness in the intermediate-layer…

Model compression techniques allow to significantly reduce the computational cost associated with data processing by deep neural networks with only a minor decrease in average accuracy. Simultaneously, reducing the model size may have a…

Labelling of data for supervised learning can be costly and time-consuming and the risk of incorporating label noise in large data sets is imminent. When training a flexible discriminative model using a strictly proper loss, such noise will…

High-quality 4D reconstruction of human performance with complex interactions to various objects is essential in real-world scenarios, which enables numerous immersive VR/AR applications. However, recent advances still fail to provide…

Watermarking is a commonly used strategy to protect creators' rights to digital images, videos and audio. Recently, watermarking methods have been extended to deep learning models -- in principle, the watermark should be preserved when an…

The recent advances in camera-based bird's eye view (BEV) representation exhibit great potential for in-vehicle 3D perception. Despite the substantial progress achieved on standard benchmarks, the robustness of BEV algorithms has not been…

Methods to certify the robustness of neural networks in the presence of input uncertainty are vital in safety-critical settings. Most certification methods in the literature are designed for adversarial input uncertainty, but researchers…