What type of study is this?

September 10, 2025Open Access

Contextual Feature Expansion with Superordinate Concept for Compositional Zero-Shot Learning

Puntos clave

CoFAD achieved state-of-the-art performance, reducing training time by up to 50×.
The method uses 2×–4× less GPU memory compared to existing approaches.
Spectral clustering and fuzzy logic are key components of the feature adjustment technique.
CZSL enables machines to generalize and infer like humans in recognizing objects and attributes.

Resumen

Compositional Zero-Shot Learning (CZSL) seeks to enable machines to recognize objects and attributes (i.e.,primitives), learn their associations, and generalize to novel compositions, enabling systems to exhibit a human-like ability to infer and generalize. Existing approaches, multi-label and multi-class classification, face inherent trade-offs: the former suffers from biases against unrelated compositions, while the latter struggles with exponentially growing search spaces as the number of objects and attributes increases. To overcome these limitations and address the exponential complexity in CZSL, we introduce Concept-oriented Feature ADjustment (CoFAD), a novel method that extracts superordinate conceptual features based on primitive relationships and expands label feature boundaries. By incorporating spectral clustering and membership function in fuzzy logic, CoFAD achieves state-of-the-art performance while using 2×–4× less GPU memory and reducing training time by up to 50× on large-scale dataset.

Leer artículo completoexternamente

Me gusta

Guardar

Ver artículo completo