Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

SynCB: A Synergy Concept-Based Model with Dynamic Routing Between Concepts and Complementary Neural Branches

About

Concept-based (CB) models provide interpretability and support test-time human intervention, while standard neural networks (NN) offer strong task performance but little transparency. Prior work has explored hybrid formulations that integrate concepts and additional representations to improve accuracy, often at the cost of human interventions. We introduce the \emph{Synergy Concept-Based Model (SynCB)} framework, that combines a CB branch with a complementary neural branch, and a trainable routing module that dynamically selects which branch to use for each input. Unlike prior models, which fuse residual and concept-based predictions, SynCB keeps the two branches distinct and coordinates them through the routing module. Moreover, both branches are learned jointly, allowing information sharing between the complementary neural branch and CB branches through their common backbone. To improve responsiveness to interventions, we further introduce a test-time intervention policy and a corresponding loss. Across five datasets and CB benchmarks, SynCB consistently achieves higher task accuracy while remaining more responsive to human interventions, surpassing the full neural baseline by up to 3.9 percentage points and exceeding the strongest competitor in intervention performance by up to 6.43 percentage points.

Tores Julie, Sun R\'emy, Sassatelli Lucile, Ancarani Elisa, Wu Hui-Yin, Precioso Fr\'ed\'eric• 2026

Related benchmarks

TaskDatasetResultRank
ClassificationCUB--
93
ClassificationCIFAR10
Accuracy94.2
68
Task ClassificationCUB Inc
Task Accuracy91.02
35
Task ClassificationAWA Inc
Task Accuracy97.08
35
Task ClassificationAwA
Task Accuracy98.65
35
Animal ClassificationAwA
Task Accuracy92.23
8
Animal ClassificationAWA Inc
Task Accuracy91.86
8
Fine-grained Bird ClassificationCUB
Task Accuracy72.48
8
Image ClassificationCIFAR10
Task Accuracy91.49
8
Fine-grained Bird ClassificationCUB Inc
Task Accuracy67.31
8
Showing 10 of 10 rows

Other info

Follow for update