TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Hierarchical Average Precision Training for Pertinent Imag...

Hierarchical Average Precision Training for Pertinent Image Retrieval

Elias Ramzi, Nicolas Audebert, Nicolas Thome, Clément Rambour, Xavier Bitot

2022-07-05Metric LearningImage Retrieval
PaperPDFCodeCode(official)

Abstract

Image Retrieval is commonly evaluated with Average Precision (AP) or Recall@k. Yet, those metrics, are limited to binary labels and do not take into account errors' severity. This paper introduces a new hierarchical AP training method for pertinent image retrieval (HAP-PIER). HAPPIER is based on a new H-AP metric, which leverages a concept hierarchy to refine AP by integrating errors' importance and better evaluate rankings. To train deep models with H-AP, we carefully study the problem's structure and design a smooth lower bound surrogate combined with a clustering loss that ensures consistent ordering. Extensive experiments on 6 datasets show that HAPPIER significantly outperforms state-of-the-art methods for hierarchical retrieval, while being on par with the latest approaches when evaluating fine-grained ranking performances. Finally, we show that HAPPIER leads to better organization of the embedding space, and prevents most severe failure cases of non-hierarchical methods. Our code is publicly available at: https://github.com/elias-ramzi/HAPPIER.

Results

TaskDatasetMetricValueModel
Image RetrievaliNaturalistR@171HAPPIER_F (ResNet-50)
Image RetrievaliNaturalistR@170.7HAPPIER (ResNet-50)
Metric LearningDyML-VehicleAverage-mAP37HAPPIER
Metric LearningStanford Online ProductsR@181.8HAPPIER_F
Metric LearningStanford Online ProductsR@181HAPPIER
Metric LearningDyML-AnimalAverage-mAP43.8HAPPIER
Metric LearningDyML-ProductAverage-mAP38HAPPIER

Related Papers

Unsupervised Ground Metric Learning2025-07-17FAR-Net: Multi-Stage Fusion Network with Enhanced Semantic Alignment and Adaptive Reconciliation for Composed Image Retrieval2025-07-17MCoT-RE: Multi-Faceted Chain-of-Thought and Re-Ranking for Training-Free Zero-Shot Composed Image Retrieval2025-07-17Are encoders able to learn landmarkers for warm-starting of Hyperparameter Optimization?2025-07-16$\texttt{Droid}$: A Resource Suite for AI-Generated Code Detection2025-07-11RadiomicsRetrieval: A Customizable Framework for Medical Image Retrieval Using Radiomics Features2025-07-11MS-DPPs: Multi-Source Determinantal Point Processes for Contextual Diversity Refinement of Composite Attributes in Text to Image Retrieval2025-07-09Orchestrator-Agent Trust: A Modular Agentic AI Visual Classification System with Trust-Aware Orchestration and RAG-Based Reasoning2025-07-09