Mirage · On-device structured vision
🌵
20
22 MB vision model - description, boxes, masks, OCR, forms
Colin Conwell PRO
colinconwell
·
AI & ML interests
Program induction; program synthesis; visuo-semantics for action; self-supervised learning
Recent Activity
authored a paper about 3 hours ago
On the use of Cortical Magnification and Saccades as Biological Proxies for Data Augmentation authored a paper about 3 hours ago
Using Multimodal Deep Neural Networks to Disentangle Language from Visual Aesthetics authored a paper about 3 hours ago
Relations, Negations, and Numbers: Looking for Logic in Generative Text-to-Image ModelsOrganizations
None yet
liked a
Space about 6 hours ago
liked a
model about 6 hours ago
liked a
dataset about 1 month ago