DiffGRE generates synthetic images through cross-image interpolation in diffusion and CLIP latent spaces, filters them for diversity, and uses pseudo-labels to improve on-the-fly fine-grained category discovery.
Text-to-image diffusion mod- els are zero shot classifiers.NeurIPS, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery
DiffGRE generates synthetic images through cross-image interpolation in diffusion and CLIP latent spaces, filters them for diversity, and uses pseudo-labels to improve on-the-fly fine-grained category discovery.