Zobrazeno 1 - 10
of 531
pro vyhledávání: '"Duan, Ling"'
Autor:
Yu, Yi, Wang, Yufei, Yang, Wenhan, Guo, Lanqing, Lu, Shijian, Duan, Ling-Yu, Tan, Yap-Peng, Kot, Alex C.
Recent advancements in deep learning-based compression techniques have surpassed traditional methods. However, deep neural networks remain vulnerable to backdoor attacks, where pre-defined triggers induce malicious behaviors. This paper introduces a
Externí odkaz:
http://arxiv.org/abs/2412.01646
Existing Multimodal Large Language Models (MLLMs) increasingly emphasize complex understanding of various visual elements, including multiple objects, text information, and spatial relations. Their development for comprehensive visual perception hing
Externí odkaz:
http://arxiv.org/abs/2407.08303
Coding, which targets compressing and reconstructing data, and intelligence, often regarded at an abstract computational level as being centered around model learning and prediction, interweave recently to give birth to a series of significant progre
Externí odkaz:
http://arxiv.org/abs/2407.01017
Transfer learning has become crucial in computer vision tasks due to the vast availability of pre-trained deep learning models. However, selecting the optimal pre-trained model from a diverse pool for a specific downstream task remains a challenge. E
Externí odkaz:
http://arxiv.org/abs/2308.15074
Though deep neural networks have achieved impressive success on various vision tasks, obvious performance degradation still exists when models are tested in out-of-distribution scenarios. In addressing this limitation, we ponder that the feature stat
Externí odkaz:
http://arxiv.org/abs/2301.06442
Real-world visual search systems involve deployments on multiple platforms with different computing and storage resources. Deploying a unified model that suits the minimal-constrain platforms leads to limited accuracy. It is expected to deploy models
Externí odkaz:
http://arxiv.org/abs/2206.08289
Image BERT pre-training with masked image modeling (MIM) becomes a popular practice to cope with self-supervised representation learning. A seminal work, BEiT, casts MIM as a classification task with a visual vocabulary, tokenizing the continuous vis
Externí odkaz:
http://arxiv.org/abs/2203.15371
Federated Learning (FL) is an emerging distributed learning paradigm under privacy constraint. Data heterogeneity is one of the main challenges in FL, which results in slow convergence and degraded performance. Most existing approaches only tackle th
Externí odkaz:
http://arxiv.org/abs/2203.09249
Cross-domain person re-identification (re-ID), such as unsupervised domain adaptive (UDA) re-ID, aims to transfer the identity-discriminative knowledge from the source to the target domain. Existing methods commonly consider the source and target dom
Externí odkaz:
http://arxiv.org/abs/2203.01682
Though remarkable progress has been achieved in various vision tasks, deep neural networks still suffer obvious performance degradation when tested in out-of-distribution scenarios. We argue that the feature statistics (mean and standard deviation),
Externí odkaz:
http://arxiv.org/abs/2202.03958