Join or Log in
AI image recognition has made some stunning advances, but as new research shows, the systems can still be tripped up by examples that would never fool a person. Labsix, a group of MIT students who recently tricked an image classifier developed by Google to think a 3D-printed turtle was a rifle, released a paper on Wednesday that details a different technique that could fool systems even faster.
Computer Vision Algorithms Are Still Way Too Easy to Trick 
Added 10 months ago by Francis Tseng
Show info
Computer Vision Algorithms Are Still Way Too Easy to Trick 
Info
AI image recognition has made some stunning advances, but as new research shows, the systems can still be tripped up by examples that would never fool a person. Labsix, a group of MIT students who recently tricked an image classifier developed by Google to think a 3D-printed turtle was a rifle, released a paper on Wednesday that details a different technique that could fool systems even faster.
1 Connection