Search Results for author: Da Li

Found 47 papers, 16 papers with code

Recurrent Early Exits for Federated Learning with Heterogeneous Clients

no code implementations23 May 2024 Royson Lee, Javier Fernandez-Marques, Shell Xu Hu, Da Li, Stefanos Laskaridis, Łukasz Dudziak, Timothy Hospedales, Ferenc Huszár, Nicholas D. Lane

Nonetheless, these approaches fall short of mitigating the challenges of joint learning multiple exit classifiers, often relying on hand-picked heuristic solutions for knowledge distillation among classifiers and/or utilizing additional layers for weaker classifiers.

Federated Learning Knowledge Distillation +1

Ground-to-UAV 140 GHz channel measurement and modeling

no code implementations3 Apr 2024 Da Li, Peian Li, Jiabiao Zhao, Jianjian Liang, Jiacheng Liu, Guohao Liu, Yuanshuai Lei, Wenbo Liu, Jianqin Deng, Fuyong Liu, Jianjun Ma

Employing experimental measurements through an unmodulated channel setup and a geometry-based stochastic model (GBSM) that integrates three-dimensional positional coordinates and beamwidth, this work evaluates the impact of UAV dynamic movements and antenna orientation on channel performance.

Extraction of n = 0 pick-up by locked mode detectors based on neural networks in J-TEXT

no code implementations23 Nov 2023 Chengshuo Shen, Jianchao Li, Yonghua Ding, Jiaolong Dong, Nengchao Wang, Dongliang. Han, Feiyue Mao, Da Li, Zhipeng Chen, Zhoujun Yang, Zhongyong Chen, Yuan Pan, J-TEXT team

A new method to extract this pick-up has been developed by predicting the n = 0 pick-up brn=0 by the LM detectors based on Neural Networks (NNs) in J-TEXT.

Sketch-based Video Object Segmentation: Benchmark and Analysis

no code implementations13 Nov 2023 Ruolin Yang, Da Li, Conghui Hu, Timothy Hospedales, Honggang Zhang, Yi-Zhe Song

Reference-based video object segmentation is an emerging topic which aims to segment the corresponding target object in each video frame referred by a given reference, such as a language expression or a photo mask.

Object Segmentation +3

Better Practices for Domain Adaptation

no code implementations7 Sep 2023 Linus Ericsson, Da Li, Timothy M. Hospedales

However, the domain shift scenario raises a second more subtle challenge: the difficulty of performing hyperparameter optimisation (HPO) for these adaptation algorithms without access to a labelled validation set.

Benchmarking Source-Free Domain Adaptation +2

Feed-Forward Source-Free Domain Adaptation via Class Prototypes

no code implementations20 Jul 2023 Ondrej Bohdal, Da Li, Timothy Hospedales

Source-free domain adaptation has become popular because of its practical usefulness and no need to access source data.

Source-Free Domain Adaptation

Label Calibration for Semantic Segmentation Under Domain Shift

no code implementations20 Jul 2023 Ondrej Bohdal, Da Li, Timothy Hospedales

Performance of a pre-trained semantic segmentation model is likely to substantially decrease on data from a new domain.

Segmentation Semantic Segmentation

Neural Fine-Tuning Search for Few-Shot Learning

1 code implementation15 Jun 2023 Panagiotis Eustratiadis, Łukasz Dudziak, Da Li, Timothy Hospedales

In few-shot recognition, a classifier that has been trained on one set of classes is required to rapidly adapt and generalize to a disjoint, novel set of classes.

Few-Shot Learning Neural Architecture Search

Valley: Video Assistant with Large Language model Enhanced abilitY

1 code implementation12 Jun 2023 Ruipu Luo, Ziwang Zhao, Min Yang, Junwei DOng, Da Li, Pengcheng Lu, Tao Wang, Linmei Hu, Minghui Qiu, Zhongyu Wei

Large language models (LLMs), with their remarkable conversational capabilities, have demonstrated impressive performance across various applications and have emerged as formidable AI assistants.

Action Recognition Instruction Following +4

Meta Omnium: A Benchmark for General-Purpose Learning-to-Learn

1 code implementation CVPR 2023 Ondrej Bohdal, Yinbing Tian, Yongshuo Zong, Ruchika Chavhan, Da Li, Henry Gouk, Li Guo, Timothy Hospedales

Meta-learning and other approaches to few-shot learning are widely studied for image recognition, and are increasingly applied to other vision tasks such as pose estimation and dense prediction.

Few-Shot Learning Pose Estimation +1

Multi-Spectrally Constrained Low-PAPR Waveform Optimization for MIMO Radar Space-Time Adaptive Processing

no code implementations5 Apr 2023 Da Li, Bo Tang, Lei Xue

This paper focuses on the joint design of transmit waveforms and receive filters for airborne multiple-input-multiple-output (MIMO) radar systems in spectrally crowded environments.

Co-Design for Spectral Coexistence between RIS-aided MIMO Radar and MIMO Communication Systems

no code implementations4 Apr 2023 Da Li, Bo Tang, Xuyang Wang, Wenjun Wu, Lei Xue

Reconfigurable intelligent surface (RIS) refers to a signal reflection surface containing a large number of low-cost passive reflecting elements.

Zero-Shot Everything Sketch-Based Image Retrieval, and in Explainable Style

1 code implementation CVPR 2023 Fengyin Lin, Mingkang Li, Da Li, Timothy Hospedales, Yi-Zhe Song, Yonggang Qi

This paper studies the problem of zero-short sketch-based image retrieval (ZS-SBIR), however with two significant differentiators to prior art (i) we tackle all variants (inter-category, intra-category, and cross datasets) of ZS-SBIR with just one network (``everything''), and (ii) we would really like to understand how this sketch-photo matching operates (``explainable'').

Relation Network Retrieval +1

Generative Model Based Noise Robust Training for Unsupervised Domain Adaptation

no code implementations10 Mar 2023 Zhongying Deng, Da Li, Junjun He, Yi-Zhe Song, Tao Xiang

D-CFA minimizes the domain gap by augmenting the source data with distribution-sampled target features, and trains a noise-robust discriminative classifier by using target domain knowledge from the generative models.

Unsupervised Domain Adaptation

Domain Generalisation via Domain Adaptation: An Adversarial Fourier Amplitude Approach

no code implementations23 Feb 2023 Minyoung Kim, Da Li, Timothy Hospedales

We tackle the domain generalisation (DG) problem by posing it as a domain adaptation (DA) task where we adversarially synthesise the worst-case target domain and adapt a model to that worst-case domain, thereby improving the model's robustness.

Domain Adaptation

An Electromagnetic-Information-Theory Based Model for Efficient Characterization of MIMO Systems in Complex Space

no code implementations13 Jan 2023 Ruifeng Li, Da Li, Jinyan Ma, Zhaoyang Feng, Ling Zhang, Shurun Tan, Wei E. I. Sha, Hongsheng Chen, Er-Ping Li

In this manuscript, an Electromagnetic-Information-Theory (EMIT) based model is developed for efficient characterization of MIMO systems in complex space.

Quality Diversity for Visual Pre-Training

no code implementations ICCV 2023 Ruchika Chavhan, Henry Gouk, Da Li, Timothy Hospedales

Notably, the augmentations used in both supervised and self-supervised training lead to features with high invariance to spatial and appearance transformations.

Inductive Bias Transfer Learning

Federated Learning for Inference at Anytime and Anywhere

no code implementations8 Dec 2022 Zicheng Liu, Da Li, Javier Fernandez-Marques, Stefanos Laskaridis, Yan Gao, Łukasz Dudziak, Stan Z. Li, Shell Xu Hu, Timothy Hospedales

Federated learning has been predominantly concerned with collaborative training of deep networks from scratch, and especially the many challenges that arise, such as communication cost, robustness to heterogeneous data, and support for diverse device capabilities.

Federated Learning

Learning to Augment via Implicit Differentiation for Domain Generalization

no code implementations25 Oct 2022 Tingwei Wang, Da Li, Kaiyang Zhou, Tao Xiang, Yi-Zhe Song

Machine learning models are intrinsically vulnerable to domain shift between training and testing data, resulting in poor performance in novel domains.

Data Augmentation Domain Generalization +1

Robust Target Training for Multi-Source Domain Adaptation

1 code implementation4 Oct 2022 Zhongying Deng, Da Li, Yi-Zhe Song, Tao Xiang

Given any existing fully-trained one-step MSDA model, BORT$^2$ turns it to a labeling function to generate pseudo-labels for the target data and trains a target model using pseudo-labeled target data only.

Domain Adaptation

Attacking Adversarial Defences by Smoothing the Loss Landscape

1 code implementation1 Aug 2022 Panagiotis Eustratiadis, Henry Gouk, Da Li, Timothy Hospedales

This paper investigates a family of methods for defending against adversarial attacks that owe part of their success to creating a noisy, discontinuous, or otherwise rugged loss landscape that adversaries find difficult to navigate.

Navigate

Feed-Forward Latent Domain Adaptation

no code implementations15 Jul 2022 Ondrej Bohdal, Da Li, Shell Xu Hu, Timothy Hospedales

Recognizing that device's data are likely to come from multiple latent domains that include a mixture of unlabelled domain-relevant and domain-irrelevant examples, we focus on the comparatively under-studied problem of latent domain adaptation.

Source-Free Domain Adaptation

Fisher SAM: Information Geometry and Sharpness Aware Minimisation

no code implementations10 Jun 2022 Minyoung Kim, Da Li, Shell Xu Hu, Timothy M. Hospedales

Recent sharpness-aware minimisation (SAM) is known to find flat minima which is beneficial for better generalisation with improved robustness.

Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference

1 code implementation CVPR 2022 Shell Xu Hu, Da Li, Jan Stühmer, Minyoung Kim, Timothy M. Hospedales

To this end, we explore few-shot learning from the perspective of neural network architecture, as well as a three stage pipeline of network updates under different data supplies, where unsupervised external data is considered for pre-training, base categories are used to simulate few-shot tasks for meta-training, and the scarcely labelled data of an novel task is taken for fine-tuning.

Few-Shot Image Classification Few-Shot Learning +1

Dynamic Instance Domain Adaptation

1 code implementation9 Mar 2022 Zhongying Deng, Kaiyang Zhou, Da Li, Junjun He, Yi-Zhe Song, Tao Xiang

In this paper, we address both single-source and multi-source UDA from a completely different perspective, which is to view each instance as a fine domain.

Unsupervised Domain Adaptation

On the Limitations of General Purpose Domain Generalisation Methods

no code implementations1 Feb 2022 Henry Gouk, Ondrej Bohdal, Da Li, Timothy Hospedales

Our analysis also suggests how different strategies can be used to optimise the performance of ERM in each of these DG setting.

Domain Generalization

Multi-task Pre-training Language Model for Semantic Network Completion

1 code implementation13 Jan 2022 Da Li, Sen yang, Kele Xu, Ming Yi, Yukai He, Huaimin Wang

To demonstrate the effectiveness of our method, we conduct extensive experiments on three widely-used datasets, WN18RR, FB15k-237, and UMLS.

Contrastive Learning Data Augmentation +3

A Channel Coding Benchmark for Meta-Learning

1 code implementation15 Jul 2021 Rui Li, Ondrej Bohdal, Rajesh Mishra, Hyeji Kim, Da Li, Nicholas Lane, Timothy Hospedales

We use our MetaCC benchmark to study several aspects of meta-learning, including the impact of task distribution breadth and shift, which can be controlled in the coding problem.

Meta-Learning

Angstrom-wide conductive channels in black phosphorus by Cu intercalation

no code implementations21 Jan 2021 Suk Woo Lee, Lu Qiu, Jong Chan Yoon, Yohan Kim, Da Li, Inseon Oh, Gil-Ho Lee, Jung-Woo Yoo, Hyung-Joon Shin, Feng Ding, Zonghoon Lee

Intercalation is an effective method to improve and modulate properties of two-dimensional materials.

Materials Science

A Simple Feature Augmentation for Domain Generalization

no code implementations ICCV 2021 Pan Li, Da Li, Wei Li, Shaogang Gong, Yanwei Fu, Timothy M. Hospedales

The topical domain generalization (DG) problem asks trained models to perform well on an unseen target domain with different data statistics from the source training domains.

Data Augmentation Domain Generalization

Weight-Covariance Alignment for Adversarially Robust Neural Networks

1 code implementation17 Oct 2020 Panagiotis Eustratiadis, Henry Gouk, Da Li, Timothy Hospedales

Stochastic Neural Networks (SNNs) that inject noise into their hidden layers have recently been shown to achieve strong robustness against adversarial attacks.

Adversarial Robustness

Online Meta-Learning for Multi-Source and Semi-Supervised Domain Adaptation

no code implementations ECCV 2020 Da Li, Timothy Hospedales

Therefore we propose an online shortest-path meta-learning framework that is both computationally tractable and practically effective for improving DA performance.

Meta-Learning Multi-Source Unsupervised Domain Adaptation +2

Sequential Learning for Domain Generalization

no code implementations3 Apr 2020 Da Li, Yongxin Yang, Yi-Zhe Song, Timothy Hospedales

In DG this means encountering a sequence of domains and at each step training to maximise performance on the next domain.

Domain Generalization Meta-Learning

Simple and Effective Stochastic Neural Networks

no code implementations25 Sep 2019 Tianyuan Yu, Yongxin Yang, Da Li, Timothy Hospedales, Tao Xiang

Stochastic neural networks (SNNs) are currently topical, with several paradigms being actively investigated including dropout, Bayesian neural networks, variational information bottleneck (VIB) and noise regularized learning.

Adversarial Attack Adversarial Defense

Large-Scale Pedestrian Retrieval Competition

no code implementations6 Mar 2019 Da Li, Zhang Zhang

The Large-Scale Pedestrian Retrieval Competition (LSPRC) mainly focuses on person retrieval which is an important end application in intelligent vision system of surveillance.

Attribute Pedestrian Detection +2

Episodic Training for Domain Generalization

2 code implementations ICCV 2019 Da Li, Jianshu Zhang, Yongxin Yang, Cong Liu, Yi-Zhe Song, Timothy M. Hospedales

In this paper, we build on this strong baseline by designing an episodic training procedure that trains a single deep network in a way that exposes it to the domain shift that characterises a novel domain at runtime.

Domain Generalization

Deep Factorised Inverse-Sketching

no code implementations ECCV 2018 Kaiyue Pang, Da Li, Jifei Song, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales

Instead there is a fundamental process of abstraction and iconic rendering, where overall geometry is warped and salient details are selectively included.

Retrieval Sketch-Based Image Retrieval +1

Deeper, Broader and Artier Domain Generalization

6 code implementations ICCV 2017 Da Li, Yongxin Yang, Yi-Zhe Song, Timothy M. Hospedales

In this paper, we make two main contributions: Firstly, we build upon the favorable domain shift-robust properties of deep learning methods, and develop a low-rank parameterized CNN model for end-to-end DG learning.

Domain Generalization

A Large-scale Distributed Video Parsing and Evaluation Platform

no code implementations29 Nov 2016 Kai Yu, Yang Zhou, Da Li, Zhang Zhang, Kaiqi Huang

Visual surveillance systems have become one of the largest data sources of Big Visual Data in real world.

Cannot find the paper you are looking for? You can Submit a new open access paper.