Learning Super-Features for Image Retrieval

• URL: http://arxiv.org/abs/2201.13182v1
• Date: Mon, 31 Jan 2022 12:48:42 GMT
• Title: Learning Super-Features for Image Retrieval
• Authors: Philippe Weinzaepfel, Thomas Lucas, Diane Larlus, Yannis Kalantidis
• Abstract summary: We propose a novel architecture for deep image retrieval based solely on mid-level features that we call Super-features. Experiments on common landmark retrieval benchmarks validate that Super-features substantially outperform state-of-the-art methods when using the same number of features.
• Score: 34.22539650643026
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Methods that combine local and global features have recently shown excellent performance on multiple challenging deep image retrieval benchmarks, but their use of local features raises at least two issues. First, these local features simply boil down to the localized map activations of a neural network, and hence can be extremely redundant. Second, they are typically trained with a global loss that only acts on top of an aggregation of local features; by contrast, testing is based on local feature matching, which creates a discrepancy between training and testing. In this paper, we propose a novel architecture for deep image retrieval, based solely on mid-level features that we call Super-features. These Super-features are constructed by an iterative attention module and constitute an ordered set in which each element focuses on a localized and discriminant image pattern. For training, they require only image labels. A contrastive loss operates directly at the level of Super-features and focuses on those that match across images. A second complementary loss encourages diversity. Experiments on common landmark retrieval benchmarks validate that Super-features substantially outperform state-of-the-art methods when using the same number of features, and only require a significantly smaller memory footprint to match their performance. Code and models are available at: https://github.com/naver/FIRe.

Related papers

• Deep Homography Estimation for Visual Place Recognition [49.235432979736395]
  We propose a transformer-based deep homography estimation (DHE) network. It takes the dense feature map extracted by a backbone network as input and fits homography for fast and learnable geometric verification. Experiments on benchmark datasets show that our method can outperform several state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-02-25T13:22:17Z)
• Attribute Prototype Network for Any-Shot Learning [113.50220968583353]
  We argue that an image representation with integrated attribute localization ability would be beneficial for any-shot, i.e. zero-shot and few-shot, image classification tasks. We propose a novel representation learning framework that jointly learns global and local features using only class-level attributes.
  arXiv  Detail & Related papers  (2022-04-04T02:25:40Z)
• Local and Global GANs with Semantic-Aware Upsampling for Image Generation [201.39323496042527]
  We consider generating images using local context. We propose a class-specific generative network using semantic maps as guidance. Lastly, we propose a novel semantic-aware upsampling method.
  arXiv  Detail & Related papers  (2022-02-28T19:24:25Z)
• Sparse Spatial Transformers for Few-Shot Learning [6.271261279657655]
  Learning from limited data is challenging because data scarcity leads to a poor generalization of the trained model. We propose a novel transformer-based neural network architecture called sparse spatial transformers. Our method finds task-relevant features and suppresses task-irrelevant features.
  arXiv  Detail & Related papers  (2021-09-27T10:36:32Z)
• Multi-attentional Deepfake Detection [79.80308897734491]
  Face forgery by deepfake is widely spread over the internet and has raised severe societal concerns. We propose a new multi-attentional deepfake detection network. Specifically, it consists of three key components: 1) multiple spatial attention heads to make the network attend to different local parts; 2) textural feature enhancement block to zoom in the subtle artifacts in shallow features; 3) aggregate the low-level textural feature and high-level semantic features guided by the attention maps.
  arXiv  Detail & Related papers  (2021-03-03T13:56:14Z)
• Re-rank Coarse Classification with Local Region Enhanced Features for Fine-Grained Image Recognition [22.83821575990778]
  We re-rank the TopN classification results by using the local region enhanced embedding features to improve the Top1 accuracy. To learn more effective semantic global features, we design a multi-level loss over an automatically constructed hierarchical category structure. Our method achieves state-of-the-art performance on three benchmarks: CUB-200-2011, Stanford Cars, and FGVC Aircraft.
  arXiv  Detail & Related papers  (2021-02-19T11:30:25Z)
• DenserNet: Weakly Supervised Visual Localization Using Multi-scale Feature Aggregation [7.2531609092488445]
  We develop a convolutional neural network architecture which aggregates feature maps at different semantic levels for image representations. Second, our model is trained end-to-end without pixel-level annotation other than positive and negative GPS-tagged image pairs. Third, our method is computationally efficient as our architecture has shared features and parameters during computation.
  arXiv  Detail & Related papers  (2020-12-04T02:16:47Z)
• Inter-Image Communication for Weakly Supervised Localization [77.2171924626778]
  Weakly supervised localization aims at finding target object regions using only image-level supervision. We propose to leverage pixel-level similarities across different objects for learning more accurate object locations. Our method achieves the Top-1 localization error rate of 45.17% on the ILSVRC validation set.
  arXiv  Detail & Related papers  (2020-08-12T04:14:11Z)
• Memory-Efficient Incremental Learning Through Feature Adaptation [71.1449769528535]
  We introduce an approach for incremental learning that preserves feature descriptors of training images from previously learned classes. Keeping the much lower-dimensional feature embeddings of images reduces the memory footprint significantly. Experimental results show that our method achieves state-of-the-art classification accuracy in incremental learning benchmarks.
  arXiv  Detail & Related papers  (2020-04-01T21:16:05Z)
• Unifying Deep Local and Global Features for Image Search [9.614694312155798]
  We unify global and local image features into a single deep model, enabling accurate retrieval with efficient feature extraction. Our model achieves state-of-the-art image retrieval on the Revisited Oxford and Paris datasets, and state-of-the-art single-model instance-level recognition on the Google Landmarks dataset v2.
  arXiv  Detail & Related papers  (2020-01-14T19:59:51Z)

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.