About

I'm a third year PhD student in the Visual Geometry Group at Oxford University, co-supervised by Prof. Andrew Zisserman and Prof. Andrea Vedaldi. I previously studied Engineering Science, also at Oxford, graduating in 2018. In between graduating and beginning my PhD, I was fortunate to work at CuriousAI in Helsinki (now acquired by Apple) and Founders Factory in London. I have since continued to work with start-ups when time allows. My research is funded by a Facebook AI Research Scholarship.

Google Scholar / CV

Project Pages

Research

My research focuses on Open World Learning - I am interested in learning representations from limited (labelled) training sets which can generalize to 'open world' data, where the data distribution (e.g categories or domain) may be different.

Conference

Generalized Category Discovery
Sagar Vaze, Kai Han, Andrea Vedaldi, Andrew Zisserman
CVPR, 2022.
Paper / Code

Open-Set Recognition: A Good Closed-Set Classifier is All You Need
Sagar Vaze, Kai Han, Andrea Vedaldi, Andrew Zisserman
ICLR, 2022 (Oral, 1.6% of submissions).
Paper / Code

Semantically Grounded Object Matching for Robust Robotic Scene Rearrangement
Walter Goodwin, Sagar Vaze, Ioannis Havoutis, Ingmar Posner
ICRA, 2022.
Paper / Code

Journal

Low-Memory CNNs Enabling Real-Time Ultrasound Segmentation Towards Mobile Deployment
Sagar Vaze, Weidi Xie, Ana Namburete
In: IEEE Journal of Biomedical and Health Informatics (Impact Factor: ~4.2) , 2020.
Paper / Project Page / Code

Workshop

Optimal Use of Multi-spectral Satellite Data with Convolutional Neural Networks
Sagar Vaze, Conrad James Foley, Mohamed El Amine Seddiq, Alexey Unagaev, Natalia Efremova
In: AI For Social Good (With Harvard CRCS), 2020.
Paper

SMArtCast: Predicting soil moisture interpolations into the future using Earth observation data in a deep learning framework
Conrad James Foley, Sagar Vaze, Mohamed El Amine Seddiq, Alexey Unagaev, Natalia Efremova
In: Climate Change AI (In conjunction with ICLR) , 2020.
Paper

Segmentation of Fetal Adipose Tissue Using Efficient CNNs for Portable Ultrasound
Sagar Vaze, Ana Namburete
In: Perinatal, Preterm and Paediatric Image analysis (PIPPI, in conjunction with MICCAI) , 2018.
Paper