57 citations · 104 across the 12 of their papers we have counts for
14 papers · 1 filter
Understanding Self-Supervised Features for Learning Unsupervised Instance Segmentation
Paul Engstler, Luke Melas-Kyriazi, Christian Rupprecht +1
Self-supervised learning (SSL) can be used to solve complex visual tasks without human labels. Self-supervised representations encode useful semantic information about images, and…
Unsupervised Multi-object Segmentation by Predicting Probable Motion Patterns
Laurynas Karazija, Subhabrata Choudhury, Iro Laina +2
We propose a new approach to learn to segment multiple image objects without manual supervision. The method can extract objects form still images, but uses videos for supervision.…
Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations
Vadim Tschernezki, Iro Laina, Diane Larlus +1
We present Neural Feature Fusion Fields (N3F), a method that improves dense 2D image feature extractors when the latter are applied to the analysis of multiple images reconstructib…
Measuring the Interpretability of Unsupervised Representations via Quantized Reverse Probing
Iro Laina, Yuki M. Asano, Andrea Vedaldi
Self-supervised visual representation learning has recently attracted significant research interest. While a common way to evaluate self-supervised representations is through trans…
Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization
Luke Melas-Kyriazi, Christian Rupprecht, Iro Laina +1
Unsupervised localization and segmentation are long-standing computer vision challenges that involve decomposing an image into semantically-meaningful segments without any labeled…
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…