S
Sebastien Ehrhardt
Researcher at University of Oxford
Publications - 24
Citations - 509
Sebastien Ehrhardt is an academic researcher from University of Oxford. The author has contributed to research in topics: Cluster analysis & Recurrent neural network. The author has an hindex of 10, co-authored 24 publications receiving 281 citations.
Papers
More filters
Posted Content
Automatically Discovering and Learning New Visual Categories with Ranking Statistics
TL;DR: This work suggests that the common approach of bootstrapping an image representation using the labeled data only introduces an unwanted bias, and that this can be avoided by using self-supervised learning to train the representation from scratch on the union of labelled and unlabelled data.
Posted Content
Learning A Physical Long-term Predictor.
TL;DR: This approach demonstrates for the first time the possibility of making actionable long-term predictions from sensor data without requiring to explicitly model the underlying physical laws.
Journal ArticleDOI
AutoNovel: Automatically Discovering and Learning Novel Visual Categories.
TL;DR: In this paper, a self-supervised learning approach called AutoNovel is proposed to address the problem of discovering novel classes in an image collection given labelled examples of other classes.
Proceedings Article
RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces
Sebastien Ehrhardt,Oliver Groth,Aron Monszpart,Martin Engelcke,Ingmar Posner,Niloy J. Mitra,Andrea Vedaldi +6 more
TL;DR: It is found that RELATE is also amenable to physically realistic scene editing and that it significantly outperforms prior art in object-centric scene generation in both synthetic data and real-world data (street traffic scenes).
Proceedings ArticleDOI
Co-Attention for Conditioned Image Matching
TL;DR: In this paper, a spatial attention mechanism (a co-attention module, CoAM) is proposed to determine correspondences between image pairs in the wild under large changes in illumination, viewpoint, context, and material.