Enhancing Feature Invariance with Learned Image Transformations for Image Retrieval

02/05/2020
by   Osman Tursun, et al.
27

Off-the-shelf convolutional neural network features achieve state-of-the-art results in many image retrieval tasks. However, their invariance is pre-defined by the network architecture and training data. In this work, we propose using features aggregated from transformed images to increase the invariance of off-the-shelf features without fine-tuning or modifying the network. We learn an ensemble of beneficial image transformations through reinforcement learning in an efficient way. Experiment results show the learned ensemble of transformations is effective and transferable.

READ FULL TEXT

page 6

page 7

page 8

page 9

page 10

research
04/08/2016

CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples

Convolutional Neural Networks (CNNs) achieve state-of-the-art performanc...
research
11/03/2017

Fine-tuning CNN Image Retrieval with No Human Annotation

Image descriptors based on activations of Convolutional Neural Networks ...
research
04/15/2021

Learning Regional Attention over Multi-resolution Deep Convolutional Features for Trademark Retrieval

Large-scale trademark retrieval is an important content-based image retr...
research
11/09/2020

What Does CNN Shift Invariance Look Like? A Visualization Study

Feature extraction with convolutional neural networks (CNNs) is a popula...
research
07/13/2019

Learning Complex Basis Functions for Invariant Representations of Audio

Learning features from data has shown to be more successful than using h...
research
02/22/2023

A study on the invariance in security whatever the dimension of images for the steganalysis by deep-learning

In this paper, we study the performance invariance of convolutional neur...
research
09/28/2022

Learning Deep Representations via Contrastive Learning for Instance Retrieval

Instance-level Image Retrieval (IIR), or simply Instance Retrieval, deal...

Please sign up or login with your details

Forgot password? Click here to reset