AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

ProtoMappingNet: Interpretable Hierarchical Prototypes through Relational Prototype Mappings

Jaehun Park, Jongmin Lim, Soobin Cha, Kwangsu Kim

ECCV 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Prototype and concept dictionary models · 0 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 bidirectional cross-level prototype mappings (ablation)ProtoHierarchy · CUB-200-2011 (relational integrity)overall HRC: 0.17 -> 18.27Improved
add bidirectional cross-level prototype mappings (ablation)ProtoHierarchy · CUB-200-2011 (relational integrity)overall HSS: 34.72 -> 65.36Improved
add bidirectional cross-level prototype mappings (ablation)ProtoHierarchy · CUB-200-2011 (ResNet50)accuracy (%): 86.8 -> 86.5No clear effect
add top-down mappings to bottom-up-only model (ablation)Bottom-up only · CUB-200-2011 (relational integrity)overall HRC: 12.92 -> 18.27Improved
add top-down mappings to bottom-up-only model (ablation)Bottom-up only · CUB-200-2011 (relational integrity)overall HSS: 54.41 -> 65.36Improved
add bottom-up mappings to top-down-only model (ablation)Top-down only · CUB-200-2011 (relational integrity)overall HRC: 5.28 -> 18.27Improved
add bottom-up mappings to top-down-only model (ablation)Top-down only · CUB-200-2011 (relational integrity)overall HSS: 46.24 -> 65.36Improved
add bottom-up mappings only (ablation)ProtoHierarchy · CUB-200-2011 (relational integrity)overall HRC: 0.17 -> 12.92Improved
add top-down mappings only (ablation)ProtoHierarchy · CUB-200-2011 (relational integrity)overall HRC: 0.17 -> 5.28Improved
add bidirectional mappings (ablation)ProtoHierarchy · CUB-200-2011 (relational integrity) Mid->HighHSS@1 (%): 48.04 -> 94.29Improved
add bidirectional mappings (ablation)ProtoHierarchy · CUB-200-2011 (relational integrity) Mid->LowHRC@1 (%): 0.23 -> 3.20Improved
add hierarchical relational constraints (ablation)ProtoHierarchy · CUB-200-2011 (relational integrity)overall stability (%): 54.81 -> 54.00No clear effect

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