all AI news
SPARO: Selective Attention for Robust and Compositional Transformer Encodings for Vision
April 25, 2024, 7:45 p.m. | Ankit Vani, Bac Nguyen, Samuel Lavoie, Ranjay Krishna, Aaron Courville
cs.CV updates on arXiv.org arxiv.org
Abstract: Selective attention helps us focus on task-relevant aspects in the constant flood of our sensory input. This constraint in our perception allows 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 …
abstract arxiv attention concepts cs.ai cs.cv distractions flood focus notion perception robust sensory transformer transformers type vision
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote