no code implementations • 30 Apr 2024 • Samuel Lavoie, Polina Kirichenko, Mark Ibrahim, Mahmoud Assran, Andrew Gordon Wildon, Aaron Courville, Nicolas Ballas
Contrastive Language Pretraining (CLIP) on the other hand, works by mapping an image and its caption to a single vector -- limiting how well CLIP-like models can represent the diverse ways to describe an image.
1 code implementation • 24 Apr 2024 • Ankit Vani, Bac Nguyen, Samuel Lavoie, Ranjay Krishna, Aaron Courville
Using SPARO, we demonstrate improvements on downstream recognition, robustness, retrieval, and compositionality benchmarks with CLIP (up to +14% for ImageNet, +4% for SugarCrepe), and on nearest neighbors and linear probe for ImageNet with DINO (+3% each).
1 code implementation • NeurIPS 2023 • Michael Noukhovitch, Samuel Lavoie, Florian Strub, Aaron Courville
We periodically reset the online model to an exponentially moving average (EMA) of itself, then reset the EMA model to the initial model.
no code implementations • 11 Apr 2023 • Florian Bordes, Samuel Lavoie, Randall Balestriero, Nicolas Ballas, Pascal Vincent
Self-Supervised Learning (SSL) models rely on a pretext task to learn representations.
1 code implementation • 1 Apr 2022 • Samuel Lavoie, Christos Tsirigotis, Max Schwarzer, Ankit Vani, Michael Noukhovitch, Kenji Kawaguchi, Aaron Courville
Simplicial Embeddings (SEM) are representations learned through self-supervised learning (SSL), wherein a representation is projected into $L$ simplices of $V$ dimensions each using a softmax operation.
1 code implementation • ICLR 2021 • Samuel Lavoie, Faruk Ahmed, Aaron Courville
While unsupervised domain translation (UDT) has seen a lot of success recently, we argue that mediating its translation via categorical semantic features could broaden its applicability.