DeepAI AI Chat
Log In Sign Up

Benchmarking unsupervised near-duplicate image detection

by   Lia Morra, et al.
Politecnico di Torino

Unsupervised near-duplicate detection has many practical applications ranging from social media analysis and web-scale retrieval, to digital image forensics. It entails running a threshold-limited query on a set of descriptors extracted from the images, with the goal of identifying all possible near-duplicates, while limiting the false positives due to visually similar images. Since the rate of false alarms grows with the dataset size, a very high specificity is thus required, up to 1 - 10^-9 for realistic use cases; this important requirement, however, is often overlooked in literature. In recent years, descriptors based on deep convolutional neural networks have matched or surpassed traditional feature extraction methods in content-based image retrieval tasks. To the best of our knowledge, ours is the first attempt to establish the performance range of deep learning-based descriptors for unsupervised near-duplicate detection on a range of datasets, encompassing a broad spectrum of near-duplicate definitions. We leverage both established and new benchmarks, such as the Mir-Flick Near-Duplicate (MFND) dataset, in which a known ground truth is provided for all possible pairs over a general, large scale image collection. To compare the specificity of different descriptors, we reduce the problem of unsupervised detection to that of binary classification of near-duplicate vs. not-near-duplicate images. The latter can be conveniently characterized using Receiver Operating Curve (ROC). Our findings in general favor the choice of fine-tuning deep convolutional networks, as opposed to using off-the-shelf features, but differences at high specificity settings depend on the dataset and are often small. The best performance was observed on the MFND benchmark, achieving 96% sensitivity at a false positive rate of 1.43 × 10^-6.


page 7

page 20


Dataset and Case Studies for Visual Near-Duplicates Detection in the Context of Social Media

The massive spread of visual content through the web and social media po...

Techniques for effective and efficient fire detection from social media images

Social media could provide valuable information to support decision maki...

Tiny Descriptors for Image Retrieval with Unsupervised Triplet Hashing

A typical image retrieval pipeline starts with the comparison of global ...

Efficient image retrieval using multi neural hash codes and bloom filters

This paper aims to deliver an efficient and modified approach for image ...

GPR1200: A Benchmark for General-Purpose Content-Based Image Retrieval

Even though it has extensively been shown that retrieval specific traini...

Rotation Invariant Descriptors for Galaxy Morphological Classification

The detection of objects that are multi-oriented is a difficult pattern ...