A Benchmark and Asymmetrical-Similarity Learning for Practical Image
Copy Detection
- URL: http://arxiv.org/abs/2205.12358v1
- Date: Tue, 24 May 2022 20:39:11 GMT
- Title: A Benchmark and Asymmetrical-Similarity Learning for Practical Image
Copy Detection
- Authors: Wenhao Wang, Yifan Sun, Yi Yang
- Abstract summary: Image copy detection (ICD) aims to determine whether a query image is an edited copy of any image from a reference set.
Some queries are not edited copies but are inherently similar to some reference images.
This paper builds the first ICD benchmark featuring this characteristic.
- Score: 30.358206867280426
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Image copy detection (ICD) aims to determine whether a query image is an
edited copy of any image from a reference set. Currently, there are very
limited public benchmarks for ICD, while all overlook a critical challenge in
real-world applications, i.e., the distraction from hard negative queries.
Specifically, some queries are not edited copies but are inherently similar to
some reference images. These hard negative queries are easily false recognized
as edited copies, significantly compromising the ICD accuracy. This observation
motivates us to build the first ICD benchmark featuring this characteristic.
Based on existing ICD datasets, this paper constructs a new dataset by
additionally adding 100, 000 and 24, 252 hard negative pairs into the training
and test set, respectively. Moreover, this paper further reveals a unique
difficulty for solving the hard negative problem in ICD, i.e., there is a
fundamental conflict between current metric learning and ICD. This conflict is:
the metric learning adopts symmetric distance while the edited copy is an
asymmetric (unidirectional) process, e.g., a partial crop is close to its
holistic reference image and is an edited copy, while the latter cannot be the
edited copy of the former (in spite the distance is equally small). This
insight results in an Asymmetrical-Similarity Learning (ASL) method, which
allows the similarity in two directions (the query <-> the reference image) to
be different from each other. Experimental results show that ASL outperforms
state-of-the-art methods by a clear margin, confirming that solving the
symmetric-asymmetric conflict is critical for ICD.
Related papers
- Noisy-Correspondence Learning for Text-to-Image Person Re-identification [50.07634676709067]
We propose a novel Robust Dual Embedding method (RDE) to learn robust visual-semantic associations even with noisy correspondences.
Our method achieves state-of-the-art results both with and without synthetic noisy correspondences on three datasets.
arXiv Detail & Related papers (2023-08-19T05:34:13Z) - Generating Aligned Pseudo-Supervision from Non-Aligned Data for Image
Restoration in Under-Display Camera [84.41316720913785]
We revisit the classic stereo setup for training data collection -- capturing two images of the same scene with one UDC and one standard camera.
The key idea is to "copy" details from a high-quality reference image and "paste" them on the UDC image.
A novel Transformer-based framework generates well-aligned yet high-quality target data for the corresponding UDC input.
arXiv Detail & Related papers (2023-04-12T17:56:42Z) - Revisiting Consistency Regularization for Semi-supervised Change
Detection in Remote Sensing Images [60.89777029184023]
We propose a semi-supervised CD model in which we formulate an unsupervised CD loss in addition to the supervised Cross-Entropy (CE) loss.
Experiments conducted on two publicly available CD datasets show that the proposed semi-supervised CD method can reach closer to the performance of supervised CD.
arXiv Detail & Related papers (2022-04-18T17:59:01Z) - A Self-Supervised Descriptor for Image Copy Detection [13.624995441674642]
We introduce SSCD, a model that builds on a self-supervised contrastive training objective.
We adapt this method to the copy detection task by changing the architecture and training objective.
Our approach relies on an entropy regularization term, promoting consistent separation between descriptor vectors.
arXiv Detail & Related papers (2022-02-21T14:25:32Z) - The 2021 Image Similarity Dataset and Challenge [32.202821997745716]
This paper introduces a new benchmark for large-scale image similarity detection.
The goal is to determine whether a query image is a modified copy of any image in a reference corpus of size 1million.
arXiv Detail & Related papers (2021-06-17T17:23:59Z) - Feature Space Targeted Attacks by Statistic Alignment [74.40447383387574]
Feature space targeted attacks perturb images by modulating their intermediate feature maps.
The current choice of pixel-wise Euclidean Distance to measure the discrepancy is questionable because it unreasonably imposes a spatial-consistency constraint on the source and target features.
We propose two novel approaches called Pair-wise Alignment Attack and Global-wise Alignment Attack, which attempt to measure similarities between feature maps by high-order statistics.
arXiv Detail & Related papers (2021-05-25T03:46:39Z) - SSCR: Iterative Language-Based Image Editing via Self-Supervised
Counterfactual Reasoning [79.30956389694184]
Iterative Language-Based Image Editing (IL-BIE) tasks follow iterative instructions to edit images step by step.
Data scarcity is a significant issue for ILBIE as it is challenging to collect large-scale examples of images before and after instruction-based changes.
We introduce a Self-Supervised Counterfactual Reasoning framework that incorporates counterfactual thinking to overcome data scarcity.
arXiv Detail & Related papers (2020-09-21T01:45:58Z) - RANSAC-Flow: generic two-stage image alignment [53.11926395028508]
We show that a simple unsupervised approach performs surprisingly well across a range of tasks.
Despite its simplicity, our method shows competitive results on a range of tasks and datasets.
arXiv Detail & Related papers (2020-04-03T12:37:58Z) - A Novel Inspection System For Variable Data Printing Using Deep Learning [0.9176056742068814]
We present a novel approach for inspecting variable data prints (VDP) with an ultra-low false alarm rate (0.005%)
The system is based on a comparison between two images: a reference image and an image captured by low-cost scanners.
arXiv Detail & Related papers (2020-01-13T15:07:13Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.