Concept-based abductive and contrastive explanations find minimal high-level concepts that causally determine vision model outcomes on individual images or groups sharing a specified behavior.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
S3 decomposes multimodal data into selectable semantic experts, routes them adaptively, and sparsifies to achieve higher accuracy on MultiBench benchmarks with peak performance at intermediate sparsity levels.
H-SemiS decomposes multi-class KOA severity grading into binary sub-tasks in a semi-supervised setup with self-supervision and quantum-inspired mixing, outperforming baselines on two multi-class and two binary datasets.
citing papers explorer
-
Concept-Based Abductive and Contrastive Explanations for Behaviors of Vision Models
Concept-based abductive and contrastive explanations find minimal high-level concepts that causally determine vision model outcomes on individual images or groups sharing a specified behavior.
-
Toward Structural Multimodal Representations: Specialization, Selection, and Sparsification via Mixture-of-Experts
S3 decomposes multimodal data into selectable semantic experts, routes them adaptively, and sparsifies to achieve higher accuracy on MultiBench benchmarks with peak performance at intermediate sparsity levels.
-
H-SemiS: Hierarchical Fusion of Semi and Self-Supervised Learning for Knee Osteoarthritis Severity Grading
H-SemiS decomposes multi-class KOA severity grading into binary sub-tasks in a semi-supervised setup with self-supervision and quantum-inspired mixing, outperforming baselines on two multi-class and two binary datasets.