Portrait de Ankit Vani n'est pas disponible

Ankit Vani

vanianki@mila.quebec
Doctorat - Université de Montréal
Superviseur⋅e principal⋅e
Aaron Courville
Site web
Github
Google Scholar

Publications

SPARO: Selective Attention for Robust and Compositional Transformer Encodings for Vision
Ankit Vani
Bac Nguyen
Samuel Lavoie
Ranjay Krishna
Aaron Courville
Selective attention helps us focus on task-relevant aspects in the constant flood of our sensory input. This constraint in our perception al… (voir plus)lows us to robustly generalize under distractions and to new compositions of perceivable concepts. Transformers employ a similar notion of attention in their architecture, but representation learning models with transformer backbones like CLIP and DINO often fail to demonstrate robustness and compositionality. We highlight a missing architectural prior: unlike human perception, transformer encodings do not separately attend over individual concepts. In response, we propose SPARO, a read-out mechanism that partitions encodings into separately-attended slots, each produced by a single attention head. Using SPARO with CLIP imparts an inductive bias that the vision and text modalities are different views of a shared compositional world with the same corresponding concepts. 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). We also showcase a powerful ability to intervene and select individual SPARO concepts to further improve downstream task performance (up from +4% to +9% for SugarCrepe) and use this ability to study the robustness of SPARO's representation structure. Finally, we provide insights through ablation experiments and visualization of learned concepts.
2024-04-24
ArXiv (prépublication)
doi.org
arxiv.org
Simplicial Embeddings in Self-Supervised Learning and Downstream Classification
Samuel Lavoie
Christos Tsirigotis
Max Schwarzer
Kenji Kawaguchi
Ankit Vani
Michael Noukhovitch
Aaron Courville
Simplicial Embeddings (SEM) are representations learned through self-supervised learning (SSL), wherein a representation is projected into …
2023-02-01
ICLR.cc/2023/Conference (notable)
doi.org
openreview.net
Fortuitous Forgetting in Connectionist Networks
Hattie Zhou
Ankit Vani
Hugo Larochelle
Aaron Courville
Forgetting is often seen as an unwanted characteristic in both human and machine learning. However, we propose that forgetting can in fact b… (voir plus)e favorable to learning. We introduce"forget-and-relearn"as a powerful paradigm for shaping the learning trajectories of artificial neural networks. In this process, the forgetting step selectively removes undesirable information from the model, and the relearning step reinforces features that are consistently useful under different conditions. The forget-and-relearn framework unifies many existing iterative training algorithms in the image classification and language emergence literature, and allows us to understand the success of these algorithms in terms of the disproportionate forgetting of undesirable information. We leverage this understanding to improve upon existing algorithms by designing more targeted forgetting operations. Insights from our analysis provide a coherent view on the dynamics of iterative training in neural networks and offer a clear path towards performance improvements.
2022-01-28
ICLR.cc/2022/Conference (poster)
openreview.net
openreview.net
GAIT: A Geometric Approach to Information Theory
Jose Gallego-Posada
Ankit Vani
Max Schwarzer
Simon Lacoste-Julien
We advocate the use of a notion of entropy that reflects the relative abundances of the symbols in an alphabet, as well as the similarities … (voir plus)between them. This concept was originally introduced in theoretical ecology to study the diversity of ecosystems. Based on this notion of entropy, we introduce geometry-aware counterparts for several concepts and theorems in information theory. Notably, our proposed divergence exhibits performance on par with state-of-the-art methods based on the Wasserstein distance, but enjoys a closed-form expression that can be computed efficiently. We demonstrate the versatility of our method via experiments on a broad range of domains: training generative models, computing image barycenters, approximating empirical measures and counting modes.
2020-01-01
AISTATS (publié)
proceedings.mlr.press
arxiv.org
GAIT: A Geometric Approach to Information Theory
Jose Gallego-Posada
Ankit Vani
Max Schwarzer
Simon Lacoste-Julien
We advocate the use of a notion of entropy that reflects the relative abundances of the symbols in an alphabet, as well as the similarities … (voir plus)between them. This concept was originally introduced in theoretical ecology to study the diversity of ecosystems. Based on this notion of entropy, we introduce geometry-aware counterparts for several concepts and theorems in information theory. Notably, our proposed divergence exhibits performance on par with state-of-the-art methods based on the Wasserstein distance, but enjoys a closed-form expression that can be computed efficiently. We demonstrate the versatility of our method via experiments on a broad range of domains: training generative models, computing image barycenters, approximating empirical measures and counting modes.
2019-06-19
ArXiv (preprint)
arxiv.org
arxiv.org