← all areas
teach machines to see
learn computer vision
from image classification to detection, segmentation, and vision transformers.
the curated path
curatedbeginner~4 weeks, part-time
computer vision fundamentals
a practical route from your first image classifier to modern detection, segmentation, and transformers — with code you can run today.
4 modules · 12 resources · checkpoint per modulestay current
what's new in computer vision
- Design of a low-power RISC-V based intelligent endoscopy detection processor: EndoRISC-Vproposes a specialized hardware processor for real-time capsule endoscopy analysis that reduces manual review time from hours to minutes while staying power-efficient. medical device teams can use this to build next-generation wearable endoscopy systems with on-device intelligence.
- EVF-SAM: Early Vision-Language Fusion for text-prompted Segment Anything Modelextends the segment anything model to accept text prompts by fusing vision and language early in the pipeline, making segmentation more controllable and intuitive. teams doing annotation or interactive segmentation can leverage this to reduce manual effort.
- An accurate, efficient, and accessible AI-powered solution for wildlife re-identification in conservationpresents giraffe, a system for automated individual animal identification from photos, enabling scalable capture-recapture and behavioral studies. conservation teams can deploy this to track populations and demographics without manual image review.
want something more specific in computer vision? generate a fresh path.
generate a path