A Self-Supervised Descriptor for Image Copy Detection

• URL: http://arxiv.org/abs/2202.10261v1
• Date: Mon, 21 Feb 2022 14:25:32 GMT
• Title: A Self-Supervised Descriptor for Image Copy Detection
• Authors: Ed Pizzi, Sreya Dutta Roy, Sugosh Nagavara Ravindra, Priya Goyal, Matthijs Douze
• Abstract summary: 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.
• Score: 13.624995441674642
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image copy detection is an important task for content moderation. We introduce SSCD, a model that builds on a recent self-supervised contrastive training objective. We adapt this method to the copy detection task by changing the architecture and training objective, including a pooling operator from the instance matching literature, and adapting contrastive learning to augmentations that combine images. Our approach relies on an entropy regularization term, promoting consistent separation between descriptor vectors, and we demonstrate that this significantly improves copy detection accuracy. Our method produces a compact descriptor vector, suitable for real-world web scale applications. Statistical information from a background image distribution can be incorporated into the descriptor. On the recent DISC2021 benchmark, SSCD is shown to outperform both baseline copy detection models and self-supervised architectures designed for image classification by huge margins, in all settings. For example, SSCD out-performs SimCLR descriptors by 48% absolute.

Related papers

• CLIP Adaptation by Intra-modal Overlap Reduction [1.2277343096128712]
  We analyse the intra-modal overlap in image space in terms of embedding representation. We train a lightweight adapter on a generic set of samples from the Google Open Images dataset.
  arXiv  Detail & Related papers  (2024-09-17T16:40:58Z)
• Boosting Few-Shot Segmentation via Instance-Aware Data Augmentation and Local Consensus Guided Cross Attention [7.939095881813804]
  Few-shot segmentation aims to train a segmentation model that can fast adapt to a novel task for which only a few annotated images are provided. We introduce an instance-aware data augmentation (IDA) strategy that augments the support images based on the relative sizes of the target objects. The proposed IDA effectively increases the support set's diversity and promotes the distribution consistency between support and query images.
  arXiv  Detail & Related papers  (2024-01-18T10:29:10Z)
• With a Little Help from your own Past: Prototypical Memory Networks for Image Captioning [47.96387857237473]
  We devise a network which can perform attention over activations obtained while processing other training samples. Our memory models the distribution of past keys and values through the definition of prototype vectors. We demonstrate that our proposal can increase the performance of an encoder-decoder Transformer by 3.7 CIDEr points both when training in cross-entropy only and when fine-tuning with self-critical sequence training.
  arXiv  Detail & Related papers  (2023-08-23T18:53:00Z)
• Improving Human-Object Interaction Detection via Virtual Image Learning [68.56682347374422]
  Human-Object Interaction (HOI) detection aims to understand the interactions between humans and objects. In this paper, we propose to alleviate the impact of such an unbalanced distribution via Virtual Image Leaning (VIL) A novel label-to-image approach, Multiple Steps Image Creation (MUSIC), is proposed to create a high-quality dataset that has a consistent distribution with real images.
  arXiv  Detail & Related papers  (2023-08-04T10:28:48Z)
• 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)
• LEAD: Self-Supervised Landmark Estimation by Aligning Distributions of Feature Similarity [49.84167231111667]
  Existing works in self-supervised landmark detection are based on learning dense (pixel-level) feature representations from an image. We introduce an approach to enhance the learning of dense equivariant representations in a self-supervised fashion. We show that having such a prior in the feature extractor helps in landmark detection, even under drastically limited number of annotations.
  arXiv  Detail & Related papers  (2022-04-06T17:48:18Z)
• Matching Feature Sets for Few-Shot Image Classification [22.84472344406448]
  We argue that a set-based representation intrinsically builds a richer representation of images from the base classes. Our approach, dubbed SetFeat, embeds shallow self-attention mechanisms inside existing encoder architectures.
  arXiv  Detail & Related papers  (2022-04-02T22:42:54Z)
• A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detection [93.38607559281601]
  We devise a hierarchical generative model that captures the multi-scale patch distribution of each training image. The anomaly score is obtained by aggregating the patch-based votes of the correct transformation across scales and image regions.
  arXiv  Detail & Related papers  (2021-04-29T17:49:48Z)
• Instance Localization for Self-supervised Detection Pretraining [68.24102560821623]
  We propose a new self-supervised pretext task, called instance localization. We show that integration of bounding boxes into pretraining promotes better task alignment and architecture alignment for transfer learning. Experimental results demonstrate that our approach yields state-of-the-art transfer learning results for object detection.
  arXiv  Detail & Related papers  (2021-02-16T17:58:57Z)
• CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances [77.28192419848901]
  We propose a simple, yet effective method named contrasting shifted instances (CSI) In addition to contrasting a given sample with other instances as in conventional contrastive learning methods, our training scheme contrasts the sample with distributionally-shifted augmentations of itself. Our experiments demonstrate the superiority of our method under various novelty detection scenarios.
  arXiv  Detail & Related papers  (2020-07-16T08:32:56Z)

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.