Zobrazeno 1 - 10
of 56
pro vyhledávání: '"Yang, Zhaoyuan"'
Although soft prompt tuning is effective in efficiently adapting Vision-Language (V&L) models for downstream tasks, it shows limitations in dealing with distribution shifts. We address this issue with Attribute-Guided Prompt Tuning (ArGue), making th
Externí odkaz:
http://arxiv.org/abs/2311.16494
Autor:
Yang, Zhaoyuan, Yu, Zhengyang, Xu, Zhiwei, Singh, Jaskirat, Zhang, Jing, Campbell, Dylan, Tu, Peter, Hartley, Richard
We present a diffusion-based image morphing approach with perceptually-uniform sampling (IMPUS) that produces smooth, direct and realistic interpolations given an image pair. The embeddings of two images may lie on distinct conditioned distributions
Externí odkaz:
http://arxiv.org/abs/2311.06792
Deep learning approaches to natural language processing have made great strides in recent years. While these models produce symbols that convey vast amounts of diverse knowledge, it is unclear how such symbols are grounded in data from the world. In
Externí odkaz:
http://arxiv.org/abs/2309.06335
We analysis performance of semantic segmentation models wrt. adversarial attacks, and observe that the adversarial examples generated from a source model fail to attack the target models. i.e The conventional attack methods, such as PGD and FGSM, do
Externí odkaz:
http://arxiv.org/abs/2307.16572
Autor:
Tu, Peter, Yang, Zhaoyuan, Hartley, Richard, Xu, Zhiwei, Zhang, Jing, Fu, Yiwei, Campbell, Dylan, Singh, Jaskirat, Wang, Tianyu
This paper begins with a description of methods for estimating image probability density functions that reflects the observation that such data is usually constrained to lie in restricted regions of the high-dimensional image space-not every pattern
Externí odkaz:
http://arxiv.org/abs/2307.02881
Autor:
Tsai, Yun-Yun, Chao, Ju-Chin, Wen, Albert, Yang, Zhaoyuan, Mao, Chengzhi, Shah, Tapan, Yang, Junfeng
Training-time defenses, known as adversarial training, incur high training costs and do not generalize to unseen attacks. Test-time defenses solve these issues but most existing test-time defenses require adapting the model weights, therefore they do
Externí odkaz:
http://arxiv.org/abs/2303.12848
In this work, we formulate a novel framework for adversarial robustness using the manifold hypothesis. This framework provides sufficient conditions for defending against adversarial examples. We develop an adversarial purification method with this f
Externí odkaz:
http://arxiv.org/abs/2210.14404
Autor:
Yang, Zhaoyuan, Tan, Yewteck, Sen, Shiraj, Reimann, Johan, Karigiannis, John, Yousefhussien, Mohammed, Virani, Nurali
Off-road autonomous unmanned ground vehicles (UGVs) are being developed for military and commercial use to deliver crucial supplies in remote locations, help with mapping and surveillance, and to assist war-fighters in contested environments. Due to
Externí odkaz:
http://arxiv.org/abs/2209.11115
Autor:
Yang, Zhaoyuan, Jain, Arpit
Dropout as regularization has been used extensively to prevent overfitting for training neural networks. During training, units and their connections are randomly dropped, which could be considered as sampling many different submodels from the origin
Externí odkaz:
http://arxiv.org/abs/2204.13047
With proliferation of deep learning (DL) applications in diverse domains, vulnerability of DL models to adversarial attacks has become an increasingly interesting research topic in the domains of Computer Vision (CV) and Natural Language Processing (
Externí odkaz:
http://arxiv.org/abs/2110.07462