What Is the Best Practice for CNNs Applied to Visual Instance Retrieval?

11/05/2016
by   Jiedong Hao, et al.
0

Previous work has shown that feature maps of deep convolutional neural networks (CNNs) can be interpreted as feature representation of a particular image region. Features aggregated from these feature maps have been exploited for image retrieval tasks and achieved state-of-the-art performances in recent years. The key to the success of such methods is the feature representation. However, the different factors that impact the effectiveness of features are still not explored thoroughly. There are much less discussion about the best combination of them. The main contribution of our paper is the thorough evaluations of the various factors that affect the discriminative ability of the features extracted from CNNs. Based on the evaluation results, we also identify the best choices for different factors and propose a new multi-scale image feature representation method to encode the image effectively. Finally, we show that the proposed method generalises well and outperforms the state-of-the-art methods on four typical datasets used for visual instance retrieval.

READ FULL TEXT
research
04/06/2020

Efficient Scale Estimation Methods using Lightweight Deep Convolutional Neural Networks for Visual Tracking

In recent years, visual tracking methods that are based on discriminativ...
research
05/12/2017

Adaptive Feature Representation for Visual Tracking

Robust feature representation plays significant role in visual tracking....
research
02/01/2015

Freehand Sketch Recognition Using Deep Features

Freehand sketches often contain sparse visual detail. In spite of the sp...
research
10/31/2017

Clothing Retrieval with Visual Attention Model

Clothing retrieval is a challenging problem in computer vision. With the...
research
06/10/2018

Instance Search via Instance Level Segmentation and Feature Representation

Instance search is an interesting task as well as a challenging issue du...
research
06/22/2016

Where to Focus: Query Adaptive Matching for Instance Retrieval Using Convolutional Feature Maps

Instance retrieval requires one to search for images that contain a part...
research
09/26/2022

Baking in the Feature: Accelerating Volumetric Segmentation by Rendering Feature Maps

Methods have recently been proposed that densely segment 3D volumes into...

Please sign up or login with your details

Forgot password? Click here to reset