Source linked

Energy-Aware Gradient Coordinator for Robust Generalized Category Discovery

A new optimization technique, EAGC, improves Generalized Category Discovery by addressing gradient entanglement and achieves state-of-the-art results.

gradient-entanglementgeneralized-category-discoveryenergy-aware-optimizationfrontierautomatedarxiv_ml

The preprint presents a novel optimization technique, Energy-Aware Gradient Coordinator (EAGC), which addresses gradient entanglement in Generalized Category Discovery (GCD). Gradient entanglement distorts supervised gradients and weakens discrimination among known classes, and induces representation-subspace overlap between known and novel classes, reducing the separability of novel categories. EAGC comprises two components: Anchor-based Gradient Alignment (AGA) and Energy-aware Elastic Projection (EEP). AGA introduces a reference model to anchor the gradient directions of labeled samples, preserving the discriminative structure of known classes against the interference of unlabeled gradients. EEP softly projects unlabeled gradients onto the complement of the known-class subspace and derives an energy-based coefficient to adaptively scale the projection for each unlabeled sample according to its degree of alignment with the known subspace. Experiments show that EAGC consistently boosts existing methods and establishes new state-of-the-art results.


Source: The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discovery

Read original source ->

External source stays available while the OJO article and comment thread stay local.

Comments load interactively on the live page.