I'm a final year PhD student in the VGG in Oxford University, working on representation learning in computer vision. I'm fortunate to be supervised by Andrew Zisserman and Andrea Vedaldi.

During my PhD, I have also spent time at Meta AI (FAIR) working on scalable multi-modal modeling: first with Ishan Misra in New York, and then in the Segment Anything team with Ross Girshick.

I previously studied Engineering Science, also at Oxford, graduating in 2018. My research is funded by a Facebook AI Research Scholarship.

Google Scholar / CV


My research focuses on learning visual representations for the 'open world', which can understand a broad set of concepts, categories and domains. I am currently particularly interested in scalable vision-language modeling as a mechanism to achieve this.

No Representation Rules Them All in Category Discovery
Sagar Vaze, Andrea Vedaldi, Andrew Zisserman
NeurIPS 2023.
  Paper   Project Page   Code

GeneCIS: A Benchmark for General Conditional Image Similarity
Sagar Vaze, Nicolas Carion, Ishan Misra
CVPR 2023 (Highlighted Paper, 2.5% of submissions).
  Paper   Project Page   Code

Zero-Shot Category-Level Object Pose Estimation
Walter Goodwin*, Sagar Vaze*, Ioannis Havoutis, Ingmar Posner
ECCV 2022.
  Paper   Code

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

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

Low-Memory CNNs Enabling Real-Time Ultrasound Segmentation Towards Mobile Deployment
Sagar Vaze, Weidi Xie, Ana Namburete
IEEE JBHI, 2020 (Impact Factor: ~4.2).
  Paper   Project Page   Code

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

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
Climate Change AI Workshop (ICLR 2020)

Segmentation of Fetal Adipose Tissue Using Efficient CNNs for Portable Ultrasound
Sagar Vaze, Ana Namburete
PIPPI Workshop (MICCAI 2018)