Instance Search

9 papers with code • 0 benchmarks • 1 datasets

Visual Instance Search is the task of retrieving from a database of images the ones that contain an instance of a visual query. It is typically much more challenging than finding images from the database that contain objects belonging to the same category as the object in the query. If the visual query is an image of a shoe, visual Instance Search does not try to find images of shoes, which might differ from the query in shape, color or size, but tries to find images of the exact same shoe as the one in the query image. Visual Instance Search challenges image representations as the features extracted from the images must enable such fine-grained recognition despite variations in viewpoints, scale, position, illumination, etc. Whereas holistic image representations, where each image is mapped to a single high-dimensional vector, are sufficient for coarse-grained similarity retrieval, local features are needed for instance retrieval.

Source: Dynamicity and Durability in Scalable Visual Instance Search


Most implemented papers

Faster R-CNN Features for Instance Search

imatge-upc/retrieval-2016-deepvision 29 Apr 2016

This work explores the suitability for instance retrieval of image- and region-wise representations pooled from an object detection CNN such as Faster R-CNN.

Bags of Local Convolutional Features for Scalable Instance Search

imatge-upc/retrieval-2016-icmr 15 Apr 2016

This work proposes a simple instance retrieval pipeline based on encoding the convolutional features of CNN using the bag of words aggregation scheme (BoW).

Class-Weighted Convolutional Features for Visual Instance Search

imatge-upc/retrieval-2017-cam 9 Jul 2017

In this paper, we go beyond this spatial information and propose a local-aware encoding of convolutional features based on semantic information predicted in the target image.

Saliency Weighted Convolutional Features for Instance Search

imatge-upc/salbow 29 Nov 2017

This work explores attention models to weight the contribution of local convolutional representations for the instance search task.

Instance Search via Instance Level Segmentation and Feature Representation

YxZhxn/Instance-Search-Based-on-Instance-Segmentation-for-Feature-Representation 10 Jun 2018

In addition, the proposed enhancement on the network structure also shows superior performance on the instance segmentation task.

GlobalTrack: A Simple and Strong Baseline for Long-term Tracking

huanglianghua/GlobalTrack 18 Dec 2019

Specifically, we propose GlobalTrack, a pure global instance search based tracker that makes no assumption on the temporal consistency of the target's positions and scales.

Confidence-Aware Active Feedback for Interactive Instance Search

nercms-mmap/caaf 23 Oct 2021

To address this issue, we propose a confidence-aware active feedback method (CAAF) that is specifically designed for online RF in interactive INS tasks.

Data-efficient End-to-end Information Extraction for Statistical Legal Analysis

lbox-kr/lbox-open 3 Nov 2022

Lawyers, for instance, search for appropriate precedents favorable to their clients, while the number of legal precedents is ever-growing.

The Effect of Points Dispersion on the $k$-nn Search in Random Projection Forests

mashaan14/RPTree 25 Feb 2023

$k$-nn search in an rpForest is influenced by two factors: 1) the dispersion of points along the random direction and 2) the number of rpTrees in the rpForest.