On the Unreasonable Effectiveness of Centroids in Image Retrieval

• URL: http://arxiv.org/abs/2104.13643v1
• Date: Wed, 28 Apr 2021 08:57:57 GMT
• Title: On the Unreasonable Effectiveness of Centroids in Image Retrieval
• Authors: Mikolaj Wieczorek, Barbara Rychalska, Jacek Dabrowski
• Abstract summary: We propose to use the mean centroid representation both during training and retrieval. As each class is represented by a single embedding - the class centroid - both retrieval time and storage requirements are reduced significantly.
• Score: 0.1933681537640272
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image retrieval task consists of finding similar images to a query image from a set of gallery (database) images. Such systems are used in various applications e.g. person re-identification (ReID) or visual product search. Despite active development of retrieval models it still remains a challenging task mainly due to large intra-class variance caused by changes in view angle, lighting, background clutter or occlusion, while inter-class variance may be relatively low. A large portion of current research focuses on creating more robust features and modifying objective functions, usually based on Triplet Loss. Some works experiment with using centroid/proxy representation of a class to alleviate problems with computing speed and hard samples mining used with Triplet Loss. However, these approaches are used for training alone and discarded during the retrieval stage. In this paper we propose to use the mean centroid representation both during training and retrieval. Such an aggregated representation is more robust to outliers and assures more stable features. As each class is represented by a single embedding - the class centroid - both retrieval time and storage requirements are reduced significantly. Aggregating multiple embeddings results in a significant reduction of the search space due to lowering the number of candidate target vectors, which makes the method especially suitable for production deployments. Comprehensive experiments conducted on two ReID and Fashion Retrieval datasets demonstrate effectiveness of our method, which outperforms the current state-of-the-art. We propose centroid training and retrieval as a viable method for both Fashion Retrieval and ReID applications.

Related papers

• Advancing Image Retrieval with Few-Shot Learning and Relevance Feedback [5.770351255180495]
  Image Retrieval with Relevance Feedback (IRRF) involves iterative human interaction during the retrieval process. We propose a new scheme based on a hyper-network, that is tailored to the task and facilitates swift adjustment to user feedback. We show that our method can attain SoTA results in few-shot one-class classification and reach comparable results in binary classification task of few-shot open-set recognition.
  arXiv  Detail & Related papers  (2023-12-18T10:20:28Z)
• Two Approaches to Supervised Image Segmentation [55.616364225463066]
  The present work develops comparison experiments between deep learning and multiset neurons approaches. The deep learning approach confirmed its potential for performing image segmentation. The alternative multiset methodology allowed for enhanced accuracy while requiring little computational resources.
  arXiv  Detail & Related papers  (2023-07-19T16:42:52Z)
• A Triplet-loss Dilated Residual Network for High-Resolution Representation Learning in Image Retrieval [0.0]
  In some applications, such as localization, image retrieval is employed as the initial step. The current paper introduces a simple yet efficient image retrieval system with a fewer trainable parameters. The proposed method benefits from a dilated residual convolutional neural network with triplet loss.
  arXiv  Detail & Related papers  (2023-03-15T07:01:44Z)
• Real-World Image Super-Resolution by Exclusionary Dual-Learning [98.36096041099906]
  Real-world image super-resolution is a practical image restoration problem that aims to obtain high-quality images from in-the-wild input. Deep learning-based methods have achieved promising restoration quality on real-world image super-resolution datasets. We propose Real-World image Super-Resolution by Exclusionary Dual-Learning (RWSR-EDL) to address the feature diversity in perceptual- and L1-based cooperative learning.
  arXiv  Detail & Related papers  (2022-06-06T13:28:15Z)
• Where Does the Performance Improvement Come From? - A Reproducibility Concern about Image-Text Retrieval [85.03655458677295]
  Image-text retrieval has gradually become a major research direction in the field of information retrieval. We first examine the related concerns and why the focus is on image-text retrieval tasks. We analyze various aspects of the reproduction of pretrained and nonpretrained retrieval models.
  arXiv  Detail & Related papers  (2022-03-08T05:01:43Z)
• Cross-Modality Sub-Image Retrieval using Contrastive Multimodal Image Representations [3.3754780158324564]
  Cross-modality image retrieval is challenging, since images of similar (or even the same) content captured by different modalities might share few common structures. We propose a new application-independent content-based image retrieval system for reverse (sub-)image search across modalities.
  arXiv  Detail & Related papers  (2022-01-10T19:04:28Z)
• Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detection [114.00301664929911]
  We show that long-tailed detection differs from classification since multiple classes may be present in one image. We introduce an object-centric memory replay strategy based on dynamic, episodic memory banks. Our method outperforms state-of-the-art long-tailed detection and segmentation methods on LVIS v0.5 across various backbones.
  arXiv  Detail & Related papers  (2021-04-12T17:58:30Z)
• Tasks Integrated Networks: Joint Detection and Retrieval for Image Search [99.49021025124405]
  In many real-world searching scenarios (e.g., video surveillance), the objects are seldom accurately detected or annotated. We first introduce an end-to-end Integrated Net (I-Net), which has three merits. We further propose an improved I-Net, called DC-I-Net, which makes two new contributions.
  arXiv  Detail & Related papers  (2020-09-03T03:57:50Z)
• Discriminative Residual Analysis for Image Set Classification with Posture and Age Variations [27.751472312581228]
  Discriminant Residual Analysis (DRA) is proposed to improve the classification performance. DRA attempts to obtain a powerful projection which casts the residual representations into a discriminant subspace. Two regularization approaches are used to deal with the probable small sample size problem.
  arXiv  Detail & Related papers  (2020-08-23T08:53:06Z)
• One-Shot Image Classification by Learning to Restore Prototypes [11.448423413463916]
  One-shot image classification aims to train image classifiers over the dataset with only one image per category. For one-shot learning, the existing metric learning approaches would suffer poor performance because the single training image may not be representative of the class. We propose a simple yet effective regression model, denoted by RestoreNet, which learns a class transformation on the image feature to move the image closer to the class center in the feature space.
  arXiv  Detail & Related papers  (2020-05-04T02:11:30Z)
• Unsupervised Person Re-identification via Softened Similarity Learning [122.70472387837542]
  Person re-identification (re-ID) is an important topic in computer vision. This paper studies the unsupervised setting of re-ID, which does not require any labeled information. Experiments on two image-based and video-based datasets demonstrate state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-04-07T17:16:41Z)

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.