Aayush Dhakal

cross-modal retrieval (2) contrastive learning (2) zero-shot learning (1) vision transformer (1) embedding space (1) hierarchical classification (1) multimodal learning (1) fine-grained classification (1) fine-grained visual classification (1) vision-language model (1) cross-modal embedding (1) masked autoencoder (1) species classification (1) partial order (1) masked image modeling (1) species distribution map (1) species distribution mapping (1) retrieval augmented generation (1) entailment learning (1) representation learning (1)