paper-with-me

Papers

FAemb: A Function Approximation-Based Embedding Method for Image Retrieval

2015-06-01 · CVPR 2015 6 · Thanh-Toan Do, Quang D. Tran, Ngai-Man Cheung

The objective of this paper is to design an embedding method mapping local features describing image (e.g. SIFT) to a higher dimensional representation used for image retrieval problem. By investigating the relationship between the linear approximation of a nonlinear function in high dimensional space and state-of-the-art feature representation used in image retrieval, i.e., VLAD, we first introduce a new approach for the approximation. The embedded vectors resulted by the function approximation process are then aggregated to form a single representation used in the image retrieval framework. The evaluation shows that our embedding method gives a performance boost over the state of the art in image retrieval, as demonstrated by our experiments on the standard public image retrieval benchmarks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Image RetrievalRetrieval

Similar Papers 제목 키워드 기반

Embedding based on function approximation for large scale image search

2016-05-23 · Thanh-Toan Do, Ngai-Man Cheung

The objective of this paper is to design an embedding method that maps local features describing an image (e.g. SIFT) to a higher dimensional representation useful for the image retrieval problem. First, motivated by the…

Image RetrievalRetrieval

Deep Metric Learning using Similarities from Nonlinear Rank Approximations

2019-09-20 · Konstantin Schall, Kai Uwe Barthel, Nico Hezel, Klaus Jung

In recent years, deep metric learning has achieved promising results in learning high dimensional semantic feature embeddings where the spatial relationships of the feature vectors match the visual similarities of the im…

Metric LearningRetrieval

A Differentiable Semantic Metric Approximation in Probabilistic Embedding for Cross-Modal Retrieval

2022-12-06 · NeurIPS 2022 2022 12 · Hao Li, Jingkuan Song, Lianli Gao, Pengpeng Zeng 외

Cross-modal retrieval aims to build correspondence between multiple modalities by learning a common representation space. Typically, an image can match multiple texts semantically and vice versa, which significantly incr…

Cross-Modal RetrievalImage-text matchingImage-to-Text RetrievalRetrieval

Deep Randomized Ensembles for Metric Learning

2018-08-13 · ECCV 2018 9 · Hong Xuan, Richard Souvenir, Robert Pless

Learning embedding functions, which map semantically related inputs to nearby locations in a feature space supports a variety of classification and information retrieval tasks. In this work, we propose a novel, generaliz…

General ClassificationImage RetrievalInformation RetrievalMetric Learning+1

Robust and Decomposable Average Precision for Image Retrieval

2021-10-01 · NeurIPS 2021 12 · Elias Ramzi, Nicolas Thome, Clément Rambour, Nicolas Audebert 외

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) addressing two major challe…

Image RetrievalMetric LearningRetrieval