paper-with-me

Papers

Transferable Normalization: Towards Improving Transferability of Deep Neural Networks

2019-12-01 · NeurIPS 2019 12 · Ximei Wang, Ying Jin, Mingsheng Long, Jian-Min Wang, Michael. I. Jordan

Deep neural networks (DNNs) excel at learning representations when trained on large-scale datasets. Pre-trained DNNs also show strong transferability when fine-tuned to other labeled datasets. However, such transferability becomes weak when the target dataset is fully unlabeled as in Unsupervised Domain Adaptation (UDA). We envision that the loss of transferability may stem from the intrinsic limitation of the architecture design of DNNs. In this paper, we delve into the components of DNN architectures and propose Transferable Normalization (TransNorm) in place of existing normalization techniques. TransNorm is an end-to-end trainable layer to make DNNs more transferable across domains. As a general method, TransNorm can be easily applied to various deep neural networks and domain adaption methods, without introducing any extra hyper-parameters or learnable parameters. Empirical results justify that TransNorm not only improves classification accuracies but also accelerates convergence for mainstream DNN-based domain adaptation methods.

📄 PDF Abstract BibTeX

Code (1)

thuml/TransNorm 공식 구현 pytorch

Tasks

Domain AdaptationUnsupervised Domain Adaptation

Similar Papers 제목 키워드 기반

StyLess: Boosting the Transferability of Adversarial Examples

2023-04-23 · CVPR 2023 1 · Kaisheng Liang, Bin Xiao

Adversarial attacks can mislead deep neural networks (DNNs) by adding imperceptible perturbations to benign examples. The attack transferability enables adversarial examples to attack black-box DNNs with unknown architec…

Logit Margin Matters: Improving Transferable Targeted Adversarial Attack by Logit Calibration

2023-03-07 · Juanjuan Weng, Zhiming Luo, Zhun Zhong, Shaozi Li 외

Previous works have extensively studied the transferability of adversarial samples in untargeted black-box scenarios. However, it still remains challenging to craft targeted adversarial examples with higher transferabili…

Adversarial Attack

Learning to Learn Transferable Generative Attack for Person Re-Identification

2024-09-06 · Yuan Bian, Min Liu, Xueping Wang, Yunfeng Ma 외

Deep learning-based person re-identification (re-id) models are widely employed in surveillance systems and inevitably inherit the vulnerability of deep networks to adversarial attacks. Existing attacks merely consider c…

Meta-LearningPerson Re-Identification

Quantifying and Improving Transferability in Domain Generalization

2021-06-07 · NeurIPS 2021 12 · Guojun Zhang, Han Zhao, YaoLiang Yu, Pascal Poupart

Out-of-distribution generalization is one of the key challenges when transferring a model from the lab to the real world. Existing efforts mostly focus on building invariant features among source and target domains. Base…

Domain GeneralizationOut-of-Distribution Generalization

Towards Transferable Targeted Adversarial Examples

2023-01-01 · CVPR 2023 1 · Zhibo Wang, Hongshan Yang, Yunhe Feng, Peng Sun 외

Transferability of adversarial examples is critical for black-box deep learning model attacks. While most existing studies focus on enhancing the transferability of untargeted adversarial attacks, few of them studied…

Adversarial Attack