这篇文章主要探求的是对于zero-shot的对抗鲁棒性,其中训练损失和adaption方法是本文探求的对象。text-guided contrastive adversarial training loss提出然后应用于model finetuning以及visual prompt tuning。VPT在缺失文本指导的情况下效果更好,而finetuning在有指导的情况下效果更好。总的来说大大的提升了zero-shot的对抗...
In constrast, Zero-shot Learning (ZSL) and Generalized Zero-shot Learning (GZSL) tasks inherently lack supervision across all classes. In this paper, we present a study aimed on evaluating the adversarial robustness of ZSL and GZSL models. We leverage the well-established label embedding model ...
Large-scale pre-trained vision-language models like CLIP have demonstrated impressive performance across various tasks, and exhibit remarkable zero-shot generalization capability, while they are also vulnerable to imperceptible adversarial examples. Existing works typically employ adversarial training (fine-tuni...
Zero-Shot Adversarial Robustness Challenge Defence MethodSubmitted ByAccuracy (Robust)Accuracy (Clean)Accuracy (Average) CLIPPMLR 20214.90%64.42%34.66% FT-Clean(initial entry)7.05%54.37%30.71% FT-Adv.(initial entry)28.83%43.36%36.09% TeCoAICLR 202328.06%45.81%36.93% ...
表明CLIP是迈向灵活和实用的zero-shot计算机视觉分类器的重要一步。CLIP另外两个报告的数据集上也优于...
However, an important caveat is that these robustness improvements are largest in the zero-shot setting, i.e., when the model per- forms inference without fine-tuning on a target distribution. In a concrete application, a zero-shot model can be fine-tuned on extra application-specific data,...
Here, we present a zero-shot deconvolution deep neural network (ZS-DeconvNet) framework that is able to train a DLSR network in an unsupervised manner using as few as only one single planar image or volumetric image stack of low-resolution and low-SNR, which results in a zero-shot implemen...
论文关键词:Zero-shot learning,Robust generalization,Adversarial robustness论文评审过程:Received 26 September 2021, Revised 4 December 2021, Accepted 18 January 2022, Available online 23 January 2022, Version of Record 1 February 2022.论文官网地址:https://doi.org/10.1016/j.imavis.2022.104392 ...
Z∗: Zero-shot Style Transfer via Attention Reweighting Yingying Deng◦,1, Xiangyu He◦,1,Fan Tang ,2, Weiming Dong1 1 MAIS, Institute of Automation, Chinese Academy of Sciences 2 Institute of Computing Technology, Chinese Academy of Sciences dyy15@outlook.com, xiangyu...
Zero-shot 3D shape understanding aims to recognize “unseen” 3D categories that are not present in training data. Recently, Contrastive Language–Image Pre-training (CLIP) has shown promising open-world performance in zero-shot 3D shape understanding tasks by information fusion among language and 3D...