Multi-level Metric Learning for Few-shot Image Recognition

• URL: http://arxiv.org/abs/2103.11383v1
• Date: Sun, 21 Mar 2021 12:49:07 GMT
• Title: Multi-level Metric Learning for Few-shot Image Recognition
• Authors: Haoxing Chen and Huaxiong Li and Yaohui Li and Chunlin Chen
• Abstract summary: We argue that if query images can simultaneously be well classified via three level similarity metrics, the query images within a class can be more tightly distributed in a smaller feature space. Motivated by this, we propose a novel Multi-level Metric Learning (MML) method for few-shot learning, which not only calculates the pixel-level similarity but also considers the similarity of part-level features and the similarity of distributions.
• Score: 5.861206243996454
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Few-shot learning is devoted to training a model on few samples. Recently, the method based on local descriptor metric-learning has achieved great performance. Most of these approaches learn a model based on a pixel-level metric. However, such works can only measure the relations between them on a single level, which is not comprehensive and effective. We argue that if query images can simultaneously be well classified via three distinct level similarity metrics, the query images within a class can be more tightly distributed in a smaller feature space, generating more discriminative feature maps. Motivated by this, we propose a novel Multi-level Metric Learning (MML) method for few-shot learning, which not only calculates the pixel-level similarity but also considers the similarity of part-level features and the similarity of distributions. First, we use a feature extractor to get the feature maps of images. Second, a multi-level metric module is proposed to calculate the part-level, pixel-level, and distribution-level similarities simultaneously. Specifically, the distribution-level similarity metric calculates the distribution distance (i.e., Wasserstein distance, Kullback-Leibler divergence) between query images and the support set, the pixel-level, and the part-level metric calculates the pixel-level and part-level similarities respectively. Finally, the fusion layer fuses three kinds of relation scores to obtain the final similarity score. Extensive experiments on popular benchmarks demonstrate that the MML method significantly outperforms the current state-of-the-art methods.

Related papers

• Layer-Wise Feature Metric of Semantic-Pixel Matching for Few-Shot Learning [14.627378118194933]
  In Few-Shot Learning, traditional metric-based approaches often rely on global metrics to compute similarity. In natural scenes, the spatial arrangement of key instances is often inconsistent across images. We propose a novel method called the Layer-Wise Features Metric of Semantic-Pixel Matching to make finer comparisons.
  arXiv  Detail & Related papers  (2024-11-10T05:12:24Z)
• Learning Spatial Similarity Distribution for Few-shot Object Counting [17.28147599627954]
  Few-shot object counting aims to count the number of objects in a query image that belong to the same class as the given exemplar images. Existing methods compute the similarity between the query image and exemplars in the 2D spatial domain and perform regression to obtain the counting number. We propose a network learning Spatial Similarity Distribution (SSD) for few-shot object counting, which preserves the spatial structure of exemplar features.
  arXiv  Detail & Related papers  (2024-05-20T04:15:59Z)
• Hierarchical Matching and Reasoning for Multi-Query Image Retrieval [113.44470784756308]
  We propose a novel Hierarchical Matching and Reasoning Network (HMRN) for Multi-Query Image Retrieval (MQIR) It disentangles MQIR into three hierarchical semantic representations, which is responsible to capture fine-grained local details, contextual global scopes, and high-level inherent correlations. Our HMRN substantially surpasses the current state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-06-26T07:03:56Z)
• Probabilistic Deep Metric Learning for Hyperspectral Image Classification [91.5747859691553]
  This paper proposes a probabilistic deep metric learning framework for hyperspectral image classification. It aims to predict the category of each pixel for an image captured by hyperspectral sensors. Our framework can be readily applied to existing hyperspectral image classification methods.
  arXiv  Detail & Related papers  (2022-11-15T17:57:12Z)
• Learning Contrastive Representation for Semantic Correspondence [150.29135856909477]
  We propose a multi-level contrastive learning approach for semantic matching. We show that image-level contrastive learning is a key component to encourage the convolutional features to find correspondence between similar objects.
  arXiv  Detail & Related papers  (2021-09-22T18:34:14Z)
• Deep Relational Metric Learning [84.95793654872399]
  This paper presents a deep relational metric learning framework for image clustering and retrieval. We learn an ensemble of features that characterizes an image from different aspects to model both interclass and intraclass distributions. Experiments on the widely-used CUB-200-2011, Cars196, and Stanford Online Products datasets demonstrate that our framework improves existing deep metric learning methods and achieves very competitive results.
  arXiv  Detail & Related papers  (2021-08-23T09:31:18Z)
• Towards Interpretable Deep Metric Learning with Structural Matching [86.16700459215383]
  We present a deep interpretable metric learning (DIML) method for more transparent embedding learning. Our method is model-agnostic, which can be applied to off-the-shelf backbone networks and metric learning methods. We evaluate our method on three major benchmarks of deep metric learning including CUB200-2011, Cars196, and Stanford Online Products.
  arXiv  Detail & Related papers  (2021-08-12T17:59:09Z)
• Multi-scale Adaptive Task Attention Network for Few-Shot Learning [5.861206243996454]
  The goal of few-shot learning is to classify unseen categories with few labeled samples. This paper proposes a novel Multi-scale Adaptive Task Attention Network (MATANet) for few-shot learning.
  arXiv  Detail & Related papers  (2020-11-30T00:36:01Z)
• BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classification [35.50808687239441]
  We propose a so-called textitBi-Similarity Network (textitBSNet) The bi-similarity module learns feature maps according to two similarity measures of diverse characteristics. In this way, the model is enabled to learn more discriminative and less similarity-biased features from few shots of fine-grained images.
  arXiv  Detail & Related papers  (2020-11-29T08:38:17Z)
• Asymmetric Distribution Measure for Few-shot Learning [82.91276814477126]
  metric-based few-shot image classification aims to measure the relations between query images and support classes. We propose a novel Asymmetric Distribution Measure (ADM) network for few-shot learning. We achieve $3.02%$ and $1.56%$ gains over the state-of-the-art method on the $5$-way $1$-shot task.
  arXiv  Detail & Related papers  (2020-02-01T06:41:52Z)

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.