相关论文: Do Image Classifiers Generalize Across Time?

A plethora of attack methods have been proposed to generate adversarial examples, among which the iterative methods have been demonstrated the ability to find a strong attack. However, the computation of an adversarial perturbation for a…

Video classification has advanced tremendously over the recent years. A large part of the improvements in video classification had to do with the work done by the image classification community and the use of deep convolutional networks…

Recently, self-supervised representation learning gives further development in multimedia technology. Most existing self-supervised learning methods are applicable to packaged data. However, when it comes to streamed data, they are…

This paper introduces the system we developed for the Google Cloud & YouTube-8M Video Understanding Challenge, which can be considered as a multi-label classification problem defined on top of the large scale YouTube-8M Dataset. We employ a…

We introduce a framework for learning robust visual representations that generalize to new viewpoints, backgrounds, and scene contexts. Discriminative models often learn naturally occurring spurious correlations, which cause them to fail on…

We propose a self-supervised method for learning motion-focused video representations. Existing approaches minimize distances between temporally augmented videos, which maintain high spatial similarity. We instead propose to learn…

Adversarial patches are optimized contiguous pixel blocks in an input image that cause a machine-learning model to misclassify it. However, their optimization is computationally demanding, and requires careful hyperparameter tuning,…

Despite extensive research since the community learned about adversarial examples 10 years ago, we still do not know how to train high-accuracy classifiers that are guaranteed to be robust to small perturbations of their inputs. Previous…

Joint visual and language modeling on large-scale datasets has recently shown good progress in multi-modal tasks when compared to single modal learning. However, robustness of these approaches against real-world perturbations has not been…

Convolutional image classifiers can achieve high predictive accuracy, but quantifying their uncertainty remains an unresolved challenge, hindering their deployment in consequential settings. Existing uncertainty quantification techniques,…

Convolutional Neural Networks (CNNs) do not have a predictable recognition behavior with respect to the input resolution change. This prevents the feasibility of deployment on different input image resolutions for a specific model. To…

Visual error metrics play a fundamental role in the quantification of perceived image similarity. Most recently, use cases for them in real-time applications have emerged, such as content-adaptive shading and shading reuse to increase…

Many recent advancements in Computer Vision are attributed to large datasets. Open-source software packages for Machine Learning and inexpensive commodity hardware have reduced the barrier of entry for exploring novel approaches at scale.…

The vulnerability of Convolutional Neural Networks (CNNs) to adversarial samples has recently garnered significant attention in the machine learning community. Furthermore, recent studies have unveiled the existence of universal adversarial…

End-to-end (geometric) deep learning has seen first successes in approximating the solution of combinatorial optimization problems. However, generating data in the realm of NP-hard/-complete tasks brings practical and theoretical…

Real world uses of deep learning require predictable model behavior under distribution shifts. Models such as CLIP show emergent natural distributional robustness comparable to humans, but may require hundreds of millions of training…

Recent advances in deep learning have significantly improved performance of video prediction. However, state-of-the-art methods still suffer from blurriness and distortions in their future predictions, especially when there are large…

Understanding temporal information and how the visual world changes over time is a fundamental ability of intelligent systems. In video understanding, temporal information is at the core of many current challenges, including compression,…

Machine learning plays an increasingly significant role in many aspects of our lives (including medicine, transportation, security, justice and other domains), making the potential consequences of false predictions increasingly devastating.…

Decades of psychological research have been aimed at modeling how people learn features and categories. The empirical validation of these theories is often based on artificial stimuli with simple representations. Recently, deep neural…