all AI news
CA-Stream: Attention-based pooling for interpretable image recognition
April 24, 2024, 4:45 a.m. | Felipe Torres, Hanwei Zhang, Ronan Sicre, St\'ephane Ayache, Yannis Avrithis
cs.CV updates on arXiv.org arxiv.org
Abstract: Explanations obtained from transformer-based architectures in the form of raw attention, can be seen as a class-agnostic saliency map. Additionally, attention-based pooling serves as a form of masking the in feature space. Motivated by this observation, we design an attention-based pooling mechanism intended to replace Global Average Pooling (GAP) at inference. This mechanism, called Cross-Attention Stream (CA-Stream), comprises a stream of cross attention blocks interacting with features at different network depths. CA-Stream enhances interpretability in …
abstract architectures arxiv attention class cs.cv design feature form global image image recognition map masking observation pooling raw recognition space transformer type
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
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