Search papers, labs, and topics across Lattice.
3
0
6
9
Object detectors in new visual domains suffer from "astigmatism," but mimicking the human eye's foveal vision can bring them into focus.
CLIP struggles with fine-grained details in cross-domain few-shot learning, but a cycle-consistency method can fix its vision-language alignment and boost performance.
CLIP's "lost" text encoder layers actually contain valuable information for cross-domain few-shot learning, and a method to re-utilize them significantly boosts performance.
