1 code implementation • 24 Apr 2024 • Yi Hu, Hanchi Ren, Chen Hu, Jingjing Deng, Xianghua Xie
A central challenge in FL is the effective aggregation of local model weights from disparate and potentially unbalanced participating clients.
no code implementations • 10 Mar 2024 • Junhui Yin, Xinyu Zhang, Lin Wu, Xianghua Xie, Xiaojie Wang
To this end, we explore the concept of test-time prompt tuning (TTPT), which enables the adaptation of the CLIP model to novel downstream tasks through only one step of optimization on an unsupervised objective that involves the test sample.
1 code implementation • 27 Nov 2023 • Xianghua Xie, Chen Hu, Hanchi Ren, Jingjing Deng
In this survey paper, our research indicates that the to-learn data, the learning gradients, and the learned model at different stages all can be manipulated to initiate malicious attacks that range from undermining model performance, reconstructing private local data, and to inserting backdoors.
no code implementations • 6 Jul 2023 • Alex Milne, Xianghua Xie
By comparing a selection of data-driven approaches, including both deep learning and non-deep learning methods, to the close-form transformation, we evaluate their potential for improving surface texture control in temper strip steel manufacturing.
1 code implementation • 6 May 2023 • Hanchi Ren, Jingjing Deng, Xianghua Xie, Xiaoke Ma, Jianfeng Ma
Our proposed learning method is resistant to gradient leakage attacks, and the key-lock module is designed and trained to ensure that, without the private information of the key-lock module: a) reconstructing private training data from the shared gradient is infeasible; and b) the global model's inference performance is significantly compromised.
1 code implementation • 20 Jan 2023 • Alexander J. M. Milne, Xianghua Xie
Control of the surface texture of steel strip during the galvanizing and temper rolling processes is essential to satisfy customer requirements and is conventionally measured post-production using a stylus.
no code implementations • 9 Jul 2022 • Deyin Liu, Lin Wu, Haifeng Zhao, Farid Boussaid, Mohammed Bennamoun, Xianghua Xie
Moreover, adversarially training a defense model in general cannot produce interpretable predictions towards the inputs with perturbations, whilst a highly interpretable robust model is required by different domain experts to understand the behaviour of a DNN.
1 code implementation • 2 May 2021 • Hanchi Ren, Jingjing Deng, Xianghua Xie
In this paper, we show that, in the FL system, image-based privacy data can be easily recovered in full from the shared gradient only via our proposed Generative Regression Neural Network (GRNN).
1 code implementation • ICCV 2021 • Avishek Siris, Jianbo Jiao, Gary K.L. Tam, Xianghua Xie, Rynson W.H. Lau
To our knowledge, such high-level semantic contextual information of image scenes is under-explored for saliency detection in the literature.
no code implementations • 23 Nov 2020 • Felix Richards, Adeline Paiement, Xianghua Xie, Elisabeth Sola, Pierre-Alain Duc
Robustness to transformation is desirable in many computer vision tasks, given that input data often exhibits pose variance.
2 code implementations • 14 Jul 2020 • Hanchi Ren, Jingjing Deng, Xianghua Xie, Xiaoke Ma, Yichuan Wang
Typical machine learning approaches require centralized data for model training, which may not be possible where restrictions on data sharing are in place due to, for instance, privacy and gradient protection.
no code implementations • 28 Sep 2016 • Michael Edwards, Xianghua Xie
Signal filters take the form of spectral multipliers, applying convolution in the graph spectral domain.
no code implementations • 18 Nov 2015 • Michael Edwards, Jingjing Deng, Xianghua Xie
We present a review on the current state of publicly available datasets within the human action recognition community; highlighting the revival of pose based methods and recent progress of understanding person-person interaction modeling.