no code implementations • 29 May 2024 • Raman Dutt, Pedro Sanchez, Ondrej Bohdal, Sotirios A. Tsaftaris, Timothy Hospedales
We perform our experiments for the specific task of medical image generation and outperform existing state-of-the-art training-time mitigation strategies by fine-tuning as few as 0. 019% of model parameters.
1 code implementation • 19 Mar 2024 • Yongshuo Zong, Ondrej Bohdal, Timothy Hospedales
Built on top of LLMs, vision large language models (VLLMs) have advanced significantly in areas such as recognition, reasoning, and grounding.
1 code implementation • 3 Feb 2024 • Yongshuo Zong, Ondrej Bohdal, Tingyang Yu, Yongxin Yang, Timothy Hospedales
Our experiments demonstrate that integrating this dataset into standard vision-language fine-tuning or utilizing it for post-hoc fine-tuning effectively safety aligns VLLMs.
1 code implementation • 8 Oct 2023 • Raman Dutt, Ondrej Bohdal, Sotirios A. Tsaftaris, Timothy Hospedales
We demonstrate empirically that FairTune leads to improved fairness on a range of medical imaging datasets.
no code implementations • 20 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.
no code implementations • 20 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.
1 code implementation • 30 Jun 2023 • Martin Ferianc, Ondrej Bohdal, Timothy Hospedales, Miguel Rodrigues
Enhancing the generalisation abilities of neural networks (NNs) through integrating noise such as MixUp or Dropout during training has emerged as a powerful and adaptable technique.
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.
no code implementations • 16 Apr 2023 • Ondrej Bohdal, Timothy Hospedales, Philip H. S. Torr, Fazl Barez
Successful deployment of artificial intelligence (AI) in various settings has led to numerous positive outcomes for individuals and society.
no code implementations • 15 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.
2 code implementations • 14 Jul 2022 • Ondrej Bohdal, Lukas Balles, Martin Wistuba, Beyza Ermis, Cédric Archambeau, Giovanni Zappella
Hyperparameter optimization (HPO) and neural architecture search (NAS) are methods of choice to obtain the best-in-class machine learning models, but in practice they can be costly to run.
no code implementations • 1 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.
1 code implementation • 15 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.
1 code implementation • NeurIPS 2021 • Ondrej Bohdal, Yongxin Yang, Timothy Hospedales
Gradient-based meta-learning and hyperparameter optimization have seen significant progress recently, enabling practical end-to-end training of neural networks together with many hyperparameters.
1 code implementation • 17 Jun 2021 • Ondrej Bohdal, Yongxin Yang, Timothy Hospedales
The problem is especially noticeable when using modern neural networks, for which there is a significant difference between the confidence of the model and the probability of correct prediction.
2 code implementations • 15 Jun 2020 • Ondrej Bohdal, Yongxin Yang, Timothy Hospedales
In particular, we study the problem of label distillation - creating synthetic labels for a small set of real images, and show it to be more effective than the prior image-based approach to dataset distillation.