WildMAE extends masked autoencoders for wildlife camera-trap images
On 4,744 Snapshot Serengeti images at 75% masking, historical PSNR was 27.90 dB for WildMAE versus 24.33 for vanilla MAE.
Stories per day · 30 days
2 RSS
Relatedcomputer-vision1edge-ai1flox-intelligence1image-reconstruction1masked-autoencoder1self-supervised-learning1startup1transportation1
2 stories, newest first · one card per story
Stories tagged #wildlife
WildMatch: Weakly Supervised Image Matcher Adaptation for Wildlife Re-Identification
WildMatch adapts pretrained image matchers for wildlife re-identification using only identity labels.