AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

Mixture of Gaussian-Distributed Prototypes With Generative Modelling for Interpretable and Trustworthy Image Recognition

Chong Wang, Yuanhong Chen, Fengbei Liu, Y. Liu, Davis James McCarthy, Helen M. L. Frazer, Gustavo Carneiro

TPAMI 2025 · Label-efficient and robust learning › OOD and anomaly detection · approach: Robust fine-tuning for OOD generalization · 16 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add auxiliary loss L_aux (ablation)MGProto · CUB (R34)accuracy: 79.6 -> 81.1Improved
add prototype mining L_mn (ablation)MGProto · CUB (R34)accuracy: 79.6 -> 81.5Improved
add both L_aux and L_mn (ablation)MGProto · Cars (R50)accuracy: 87.0 -> 89.2Improved
add L_mn (ablation)MGProto · CUB interpretability V19DAUC: 3.91 -> 3.20Improved
add L_aux (ablation)MGProto · CUB interpretability V19consistency: 92.97 -> 92.90No clear effect
add prototype miningProtoPNet · CUB (ResNet34)accuracy: 72.4 -> 76.5Improved
add prototype miningTesNet · CUB (ResNet34)accuracy: 76.2 -> 78.6Improved
add prototype miningST-ProtoPNet · CUB (ResNet34)accuracy: 77.4 -> 79.3Improved
use diversity constraint instead of closed-form M-step (ablation)MGProto · CUB (R34)accuracy: 81.2 -> 82.2Improved
use diversity constraint instead of closed-form M-step (ablation)MGProto · Cars (R50)accuracy: 88.3 -> 89.2Improved
importance-based pruning of 20% prototypesMGProto · CUB (ResNet34)accuracy: 82.2 -> 82.4Improved
importance-based pruning of 90% prototypesMGProto · CUB (ResNet34)accuracy: 82.2 -> 80.5Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy