Fourier self-supervision, using low- and high-pass filtered image views with frequency-specialized latent dimensions, improves fine-grained Generalized Category Discovery over SimGCD and SelEx baselines.
In: Proceedings of the IEEE/CVF International Conference on Computer Vision
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Fourier Self-Supervision for Fine-Grained Generalized Category Discovery
Fourier self-supervision, using low- and high-pass filtered image views with frequency-specialized latent dimensions, improves fine-grained Generalized Category Discovery over SimGCD and SelEx baselines.