Advances in adversarial attacks and defenses in computer vision: A survey
Deep Learning is the most widely used tool in the contemporary field of computer vision. Its
ability to accurately solve complex problems is employed in vision research to learn deep …
ability to accurately solve complex problems is employed in vision research to learn deep …
Opportunities and challenges in deep learning adversarial robustness: A survey
SH Silva, P Najafirad - arXiv preprint arXiv:2007.00753, 2020 - arxiv.org
As we seek to deploy machine learning models beyond virtual and controlled domains, it is
critical to analyze not only the accuracy or the fact that it works most of the time, but if such a …
critical to analyze not only the accuracy or the fact that it works most of the time, but if such a …
On the opportunities and risks of foundation models
AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …
Do adversarially robust imagenet models transfer better?
Transfer learning is a widely-used paradigm in deep learning, where models pre-trained on
standard datasets can be efficiently adapted to downstream tasks. Typically, better pre …
standard datasets can be efficiently adapted to downstream tasks. Typically, better pre …
Threat of adversarial attacks on deep learning in computer vision: A survey
Deep learning is at the heart of the current rise of artificial intelligence. In the field of
computer vision, it has become the workhorse for applications ranging from self-driving cars …
computer vision, it has become the workhorse for applications ranging from self-driving cars …
Adversarial self-supervised contrastive learning
Existing adversarial learning approaches mostly use class labels to generate adversarial
samples that lead to incorrect predictions, which are then used to augment the training of the …
samples that lead to incorrect predictions, which are then used to augment the training of the …
Divergence-agnostic unsupervised domain adaptation by adversarial attacks
Conventional machine learning algorithms suffer the problem that the model trained on
existing data fails to generalize well to the data sampled from other distributions. To tackle …
existing data fails to generalize well to the data sampled from other distributions. To tackle …
xViTCOS: explainable vision transformer based COVID-19 screening using radiography
Objective: Since its outbreak, the rapid spread of COrona VIrus Disease 2019 (COVID-19)
across the globe has pushed the health care system in many countries to the verge of …
across the globe has pushed the health care system in many countries to the verge of …
Non-generative generalized zero-shot learning via task-correlated disentanglement and controllable samples synthesis
Y Feng, X Huang, P Yang, J Yu… - Proceedings of the …, 2022 - openaccess.thecvf.com
Synthesizing pseudo samples is currently the most effective way to solve the Generalized
Zero Shot Learning (GZSL) problem. Most models achieve competitive performance but still …
Zero Shot Learning (GZSL) problem. Most models achieve competitive performance but still …
Automated synthetic-to-real generalization
Abstract Models trained on synthetic images often face degraded generalization to real data.
As a convention, these models are often initialized with ImageNet pretrained representation …
As a convention, these models are often initialized with ImageNet pretrained representation …