PACO provides a hierarchical online decision system with proxy-simulated initial thresholds and adaptive updates from mature prototypes to enable consistent category discovery in streaming sequences.
Hilo: A learning framework for generalized category discovery robust to domain shifts
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
LAGCD inserts residual linear adapters into each ViT block plus a distribution alignment loss to improve generalized category discovery by increasing model flexibility while reducing bias between seen and novel classes.
citing papers explorer
-
PACO: Proxy-Task Alignment and Online Calibration for On-the-Fly Category Discovery
PACO provides a hierarchical online decision system with proxy-simulated initial thresholds and adaptive updates from mature prototypes to enable consistent category discovery in streaming sequences.
-
Sparsity Hurts: Simple Linear Adapter Can Boost Generalized Category Discovery
LAGCD inserts residual linear adapters into each ViT block plus a distribution alignment loss to improve generalized category discovery by increasing model flexibility while reducing bias between seen and novel classes.