Skip to yearly menu bar Skip to main content

Spotlight Poster

CrIBo: Self-Supervised Learning via Cross-Image Object-Level Bootstrapping

Tim Lebailly · Thomas Stegmüller · Behzad Bozorgtabar · Jean-Philippe Thiran · Tinne Tuytelaars

Halle B #111
[ ]
Tue 7 May 1:45 a.m. PDT — 3:45 a.m. PDT

Abstract: Leveraging nearest neighbor retrieval for self-supervised representation learning has proven beneficial with object-centric images. However, this approach faces limitations when applied to scene-centric datasets, where multiple objects within an image are only implicitly captured in the global representation. Such global bootstrapping can lead to undesirable entanglement of object representations. Furthermore, even object-centric datasets stand to benefit from a finer-grained bootstrapping approach. In response to these challenges, we introduce a novel $\textbf{Cr}$oss-$\textbf{I}$mage Object-Level $\textbf{Bo}$otstrapping method tailored to enhance dense visual representation learning. By employing object-level nearest neighbor bootstrapping throughout the training, CrIBo emerges as a notably strong and adequate candidate for in-context learning, leveraging nearest neighbor retrieval at test time. CrIBo shows state-of-the-art performance on the latter task while being highly competitive in more standard downstream segmentation tasks. Our code and pretrained models are publicly available at

Chat is not available.