642 citations · 3.9k across the 143 of their papers we have counts for
73 papers · 1 filter
SketchINR: A First Look into Sketches as Implicit Neural Representations
Hmrishav Bandyopadhyay, Ayan Kumar Bhunia, Pinaki Nath Chowdhury +4
We propose SketchINR, to advance the representation of vector sketches with implicit neural models. A variable length vector sketch is compressed into a latent space of fixed dimen…
DemoFusion: Democratising High-Resolution Image Generation With No $$$
Ruoyi Du, Dongliang Chang, Timothy Hospedales +2
High-resolution image generation with Generative Artificial Intelligence (GenAI) has immense potential but, due to the enormous capital investment required for training, it is incr…
Sketch-based Video Object Segmentation: Benchmark and Analysis
Ruolin Yang, Da Li, Conghui Hu +3
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 la…
FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysis
Raman Dutt, Ondrej Bohdal, Sotirios A. Tsaftaris +1
Training models with robust group fairness properties is crucial in ethically sensitive application areas such as medical diagnosis. Despite the growing body of work aiming to mini…
Label Calibration for Semantic Segmentation Under Domain Shift
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. We show a pre-trained model can be adapted to unlabelled tar…
Feed-Forward Source-Free Domain Adaptation via Class Prototypes
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. However, the adaptation process still takes a considerable a…
Neural Fine-Tuning Search for Few-Shot Learning
Panagiotis Eustratiadis, Łukasz Dudziak, Da Li +1
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. To that end, rece…
Meta Omnium: A Benchmark for General-Purpose Learning-to-Learn
Ondrej Bohdal, Yinbing Tian, Yongshuo Zong +5
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 den…
Parameter-Efficient Fine-Tuning for Medical Image Analysis: The Missed Opportunity
Raman Dutt, Linus Ericsson, Pedro Sanchez +2
Foundation models have significantly advanced medical image analysis through the pre-train fine-tune paradigm. Among various fine-tuning algorithms, Parameter-Efficient Fine-Tuning…
Amortised Invariance Learning for Contrastive Self-Supervision
Ruchika Chavhan, Henry Gouk, Jan Stuehmer +3
Contrastive self-supervised learning methods famously produce high quality transferable representations by learning invariances to different data augmentations. Invariances establi…
Fairness meets Cross-Domain Learning: a new perspective on Models and Metrics
Leonardo Iurada, Silvia Bucci, Timothy M. Hospedales +1
Deep learning-based recognition systems are deployed at scale for several real-world applications that inevitably involve our social life. Although being of great support when maki…
Zero-Shot Everything Sketch-Based Image Retrieval, and in Explainable Style
Fengyin Lin, Mingkang Li, Da Li +3
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-cat…
Accelerating Self-Supervised Learning via Efficient Training Strategies
Mustafa Taha Koçyiğit, Timothy M. Hospedales, Hakan Bilen
Recently the focus of the computer vision community has shifted from expensive supervised learning towards self-supervised learning of visual representations. While the performance…
Meta-Learned Kernel For Blind Super-Resolution Kernel Estimation
Royson Lee, Rui Li, Stylianos I. Venieris +3
Recent image degradation estimation methods have enabled single-image super-resolution (SR) approaches to better upsample real-world images. Among these methods, explicit kernel es…
Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference
Shell Xu Hu, Da Li, Jan Stühmer +2
Few-shot learning (FSL) is an important and topical problem in computer vision that has motivated extensive research into numerous methods spanning from sophisticated meta-learning…
Why Do Self-Supervised Models Transfer? Investigating the Impact of Invariance on Downstream Tasks
Linus Ericsson, Henry Gouk, Timothy M. Hospedales
Self-supervised learning is a powerful paradigm for representation learning on unlabelled images. A wealth of effective new methods based on instance matching rely on data-augmenta…
Vision-based system identification and 3D keypoint discovery using dynamics constraints
Miguel Jaques, Martin Asenov, Michael Burke +1
This paper introduces V-SysId, a novel method that enables simultaneous keypoint discovery, 3D system identification, and extrinsic camera calibration from an unlabeled video taken…
Towards Unsupervised Sketch-based Image Retrieval
Conghui Hu, Yongxin Yang, Yunpeng Li +2
The practical value of existing supervised sketch-based image retrieval (SBIR) algorithms is largely limited by the requirement for intensive data collection and labeling. In this…
Cloud2Curve: Generation and Vectorization of Parametric Sketches
Ayan Das, Yongxin Yang, Timothy Hospedales +2
Analysis of human sketches in deep learning has advanced immensely through the use of waypoint-sequences rather than raster-graphic representations. We further aim to model sketche…
Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwriting
Ayan Kumar Bhunia, Pinaki Nath Chowdhury, Yongxin Yang +3
Self-supervised learning has gained prominence due to its efficacy at learning powerful representations from unlabelled data that achieve excellent performance on many challenging…
Tensor Composition Net for Visual Relationship Prediction
Yuting Qiang, Yongxin Yang, Xueting Zhang +2
We present a novel Tensor Composition Net (TCN) to predict visual relationships in images. Visual Relationship Prediction (VRP) provides a more challenging test of image understand…
How Well Do Self-Supervised Models Transfer?
Linus Ericsson, Henry Gouk, Timothy M. Hospedales
Self-supervised visual representation learning has seen huge progress recently, but no large scale evaluation has compared the many models now available. We evaluate the transfer p…
BézierSketch: A generative model for scalable vector sketches
Ayan Das, Yongxin Yang, Timothy Hospedales +2
The study of neural generative models of human sketches is a fascinating contemporary modeling problem due to the links between sketch image generation and the human drawing proces…
On Learning Semantic Representations for Million-Scale Free-Hand Sketches
Peng Xu, Yongye Huang, Tongtong Yuan +4
In this paper, we study learning semantic representations for million-scale free-hand sketches. This is highly challenging due to the domain-unique traits of sketches, e.g., divers…