Hierarchical Average Precision Training for Pertinent Image Retrieval

• URL: http://arxiv.org/abs/2207.04873v1
• Date: Tue, 5 Jul 2022 07:55:18 GMT
• Title: Hierarchical Average Precision Training for Pertinent Image Retrieval
• Authors: Elias Ramzi (CNAM), Nicolas Audebert (CNAM), Nicolas Thome (CNAM), Cl\'ement Rambour (CNAM), Xavier Bitot
• Abstract summary: This paper introduces a new hierarchical AP training method for pertinent image retrieval (HAP-PIER) HAP-PIER is based on a new H-AP metric, which integrates errors' importance and better evaluate rankings. Experiments on 6 datasets show that HAPPIER significantly outperforms state-of-the-art methods for hierarchical retrieval.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Not All Pairs are Equal: Hierarchical Learning for Average-Precision-Oriented Video Retrieval [80.09819072780193]
  Average Precision (AP) assesses the overall rankings of relevant videos at the top list. Recent video retrieval methods utilize pair-wise losses that treat all sample pairs equally.
  arXiv  Detail & Related papers  (2024-07-22T11:52:04Z)
• Test-Time Amendment with a Coarse Classifier for Fine-Grained Classification [10.719054378755981]
  We present a novel approach for Post-Hoc Correction called Hierarchical Ensembles (HiE) HiE utilizes label hierarchy to improve the performance of fine-grained classification at test-time using the coarse-grained predictions. Our approach brings notable gains in top-1 accuracy while significantly decreasing the severity of mistakes as training data decreases for the fine-grained classes.
  arXiv  Detail & Related papers  (2023-02-01T10:55:27Z)
• Revisiting AP Loss for Dense Object Detection: Adaptive Ranking Pair Selection [19.940491797959407]
  In this work, we revisit the average precision (AP)loss and reveal that the crucial element is that of selecting the ranking pairs between positive and negative samples. We propose two strategies to improve the AP loss. The first is a novel Adaptive Pairwise Error (APE) loss that focusing on ranking pairs in both positive and negative samples. Experiments conducted on the MSCOCO dataset support our analysis and demonstrate the superiority of our proposed method compared with current classification and ranking loss.
  arXiv  Detail & Related papers  (2022-07-25T10:33:06Z)
• ReAct: Temporal Action Detection with Relational Queries [84.76646044604055]
  This work aims at advancing temporal action detection (TAD) using an encoder-decoder framework with action queries. We first propose a relational attention mechanism in the decoder, which guides the attention among queries based on their relations. Lastly, we propose to predict the localization quality of each action query at inference in order to distinguish high-quality queries.
  arXiv  Detail & Related papers  (2022-07-14T17:46:37Z)
• Open-Set Recognition: A Good Closed-Set Classifier is All You Need [146.6814176602689]
  We show that the ability of a classifier to make the 'none-of-above' decision is highly correlated with its accuracy on the closed-set classes. We use this correlation to boost the performance of the cross-entropy OSR 'baseline' by improving its closed-set accuracy. We also construct new benchmarks which better respect the task of detecting semantic novelty.
  arXiv  Detail & Related papers  (2021-10-12T17:58:59Z)
• Robust and Decomposable Average Precision for Image Retrieval [0.0]
  In image retrieval, standard evaluation metrics rely on score ranking, e.g. average precision (AP) In this paper, we introduce a method for robust and decomposable average precision (ROADMAP) We address two major challenges for end-to-end training of deep neural networks with AP: non-differentiability and non-decomposability.
  arXiv  Detail & Related papers  (2021-10-01T12:00:43Z)
• Evaluating Large-Vocabulary Object Detectors: The Devil is in the Details [107.2722027807328]
  We find that the default implementation of AP is neither category independent, nor does it directly reward properly calibrated detectors. We show that the default implementation produces a gameable metric, where a simple, nonsensical re-ranking policy can improve AP by a large margin. We benchmark recent advances in large-vocabulary detection and find that many reported gains do not translate to improvements under our new per-class independent evaluation.
  arXiv  Detail & Related papers  (2021-02-01T18:56:02Z)
• Monocular Depth Estimation via Listwise Ranking using the Plackett-Luce Model [15.472533971305367]
  In many real-world applications, the relative depth of objects in an image is crucial for scene understanding. Recent approaches mainly tackle the problem of depth prediction in monocular images by treating the problem as a regression task. Yet, ranking methods suggest themselves as a natural alternative to regression, and indeed, ranking approaches leveraging pairwise comparisons have shown promising performance on this problem.
  arXiv  Detail & Related papers  (2020-10-25T13:40:10Z)
• AP-Loss for Accurate One-Stage Object Detection [49.13608882885456]
  One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously. The former suffers much from extreme foreground-background imbalance due to the large number of anchors. This paper proposes a novel framework to replace the classification task in one-stage detectors with a ranking task.
  arXiv  Detail & Related papers  (2020-08-17T13:22:01Z)
• Simple and Effective Prevention of Mode Collapse in Deep One-Class Classification [93.2334223970488]
  We propose two regularizers to prevent hypersphere collapse in deep SVDD. The first regularizer is based on injecting random noise via the standard cross-entropy loss. The second regularizer penalizes the minibatch variance when it becomes too small.
  arXiv  Detail & Related papers  (2020-01-24T03:44:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.