1 code implementation • 11 Oct 2023 • Tim Lebailly, Thomas Stegmüller, Behzad Bozorgtabar, Jean-Philippe Thiran, Tinne Tuytelaars
Leveraging nearest neighbor retrieval for self-supervised representation learning has proven beneficial with object-centric images.
1 code implementation • ICCV 2023 • Tim Lebailly, Thomas Stegmüller, Behzad Bozorgtabar, Jean-Philippe Thiran, Tinne Tuytelaars
Most self-supervised methods for representation learning leverage a cross-view consistency objective i. e., they maximize the representation similarity of a given image's augmented views.
2 code implementations • CVPR 2023 • Thomas Stegmüller, Tim Lebailly, Behzad Bozorgtabar, Tinne Tuytelaars, Jean-Philippe Thiran
More importantly, the clustering algorithm conjointly operates on the features of both views, thereby elegantly bypassing the issue of content not represented in both views and the ambiguous matching of objects from one crop to the other.
Ranked #11 on Unsupervised Semantic Segmentation on COCO-Stuff-27
no code implementations • 10 Feb 2023 • Thomas Stegmüller, Christian Abbet, Behzad Bozorgtabar, Holly Clarke, Patrick Petignat, Pierre Vassilakos, Jean-Philippe Thiran
Screening Papanicolaou test samples has proven to be highly effective in reducing cervical cancer-related mortality.
1 code implementation • 15 Feb 2022 • Thomas Stegmüller, Behzad Bozorgtabar, Antoine Spahr, Jean-Philippe Thiran
We further introduce a novel mixing data-augmentation, namely ScoreMix, by leveraging the image's semantic distribution to guide the data mixing and produce coherent sample-label pairs.