Zobrazeno 1 - 10
of 203
pro vyhledávání: '"Oberman, Adam"'
Non-contrastive self-supervised learning (NC-SSL) methods like BarlowTwins and VICReg have shown great promise for label-free representation learning in computer vision. Despite the apparent simplicity of these techniques, researchers must rely on se
Externí odkaz:
http://arxiv.org/abs/2312.10725
Autor:
Li, Xinlin, Parazeres, Mariana, Oberman, Adam, Ghaffari, Alireza, Asgharian, Masoud, Nia, Vahid Partovi
With the advent of deep learning application on edge devices, researchers actively try to optimize their deployments on low-power and restricted memory devices. There are established compression method such as quantization, pruning, and architecture
Externí odkaz:
http://arxiv.org/abs/2212.11803
Publikováno v:
NeurIPS 2022 Workshop on Score-Based Methods
Generative models based on denoising diffusion techniques have led to an unprecedented increase in the quality and diversity of imagery that is now possible to create with neural generative models. However, most contemporary state-of-the-art methods
Externí odkaz:
http://arxiv.org/abs/2210.12254
Unsupervised Domain Adaptation (UDA) aims at classifying unlabeled target images leveraging source labeled ones. In this work, we consider the Partial Domain Adaptation (PDA) variant, where we have extra source classes not present in the target domai
Externí odkaz:
http://arxiv.org/abs/2210.01210
In reinforcement learning, state representations are used to tractably deal with large problem spaces. State representations serve both to approximate the value function with few parameters, but also to generalize to newly encountered states. Their f
Externí odkaz:
http://arxiv.org/abs/2203.00543
Recent work has shown that Neural Ordinary Differential Equations (ODEs) can serve as generative models of images using the perspective of Continuous Normalizing Flows (CNFs). Such models offer exact likelihood calculation, and invertible generation/
Externí odkaz:
http://arxiv.org/abs/2106.08462
Distribution shift is an important concern in deep image classification, produced either by corruption of the source images, or a complete change, with the solution involving domain adaptation. While the primary goal is to improve accuracy under dist
Externí odkaz:
http://arxiv.org/abs/2106.03762
Despite being widely used, face recognition models suffer from bias: the probability of a false positive (incorrect face match) strongly depends on sensitive attributes such as the ethnicity of the face. As a result, these models can disproportionate
Externí odkaz:
http://arxiv.org/abs/2106.03761
Machine learning models are vulnerable to adversarial attacks. One approach to addressing this vulnerability is certification, which focuses on models that are guaranteed to be robust for a given perturbation size. A drawback of recent certified mode
Externí odkaz:
http://arxiv.org/abs/2010.02508
We present a deterministic method to compute the Gaussian average of neural networks used in regression and classification. Our method is based on an equivalence between training with a particular regularized loss, and the expected values of Gaussian
Externí odkaz:
http://arxiv.org/abs/2006.06061