105 citations · 652 across the 49 of their papers we have counts for
7 papers · 1 filter
ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation
Laurynas Karazija, Iro Laina, Christian Rupprecht
There has been a recent surge in methods that aim to decompose and segment scenes into multiple objects in an unsupervised manner, i.e., unsupervised multi-object segmentation. Per…
The Curious Layperson: Fine-Grained Image Recognition without Expert Labels
Subhabrata Choudhury, Iro Laina, Christian Rupprecht +1
Most of us are not experts in specific fields, such as ornithology. Nonetheless, we do have general image and language understanding capabilities that we use to match what we see t…
Unsupervised Part Discovery from Contrastive Reconstruction
Subhabrata Choudhury, Iro Laina, Christian Rupprecht +1
The goal of self-supervised visual representation learning is to learn strong, transferable image representations, with the majority of research focusing on object or scene level.…
PASS: An ImageNet replacement for self-supervised pretraining without humans
Yuki M. Asano, Christian Rupprecht, Andrew Zisserman +1
Computer vision has long relied on ImageNet and other large datasets of images sampled from the Internet for pretraining models. However, these datasets have ethical and technical…
DOVE: Learning Deformable 3D Objects by Watching Videos
Shangzhe Wu, Tomas Jakab, Christian Rupprecht +1
Learning deformable 3D objects from 2D images is often an ill-posed problem. Existing methods rely on explicit supervision to establish multi-view correspondences, such as template…
Finding an Unsupervised Image Segmenter in Each of Your Deep Generative Models
Luke Melas-Kyriazi, Christian Rupprecht, Iro Laina +1
Recent research has shown that numerous human-interpretable directions exist in the latent space of GANs. In this paper, we develop an automatic procedure for finding directions th…