A Simple Task-aware Contrastive Local Descriptor Selection Strategy for Few-shot Learning between inter class and intra class

• URL: http://arxiv.org/abs/2408.05953v1
• Date: Mon, 12 Aug 2024 07:04:52 GMT
• Title: A Simple Task-aware Contrastive Local Descriptor Selection Strategy for Few-shot Learning between inter class and intra class
• Authors: Qian Qiao, Yu Xie, Shaoyao Huang, Fanzhang Li,
• Abstract summary: Few-shot image classification aims to classify novel classes with few labeled samples. Recent research indicates that deep local descriptors have better representational capabilities. This paper proposes a novel task-aware contrastive local descriptor selection network (TCDSNet)
• Score: 6.204356280380338
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Few-shot image classification aims to classify novel classes with few labeled samples. Recent research indicates that deep local descriptors have better representational capabilities. These studies recognize the impact of background noise on classification performance. They typically filter query descriptors using all local descriptors in the support classes or engage in bidirectional selection between local descriptors in support and query sets. However, they ignore the fact that background features may be useful for the classification performance of specific tasks. This paper proposes a novel task-aware contrastive local descriptor selection network (TCDSNet). First, we calculate the contrastive discriminative score for each local descriptor in the support class, and select discriminative local descriptors to form a support descriptor subset. Finally, we leverage support descriptor subsets to adaptively select discriminative query descriptors for specific tasks. Extensive experiments demonstrate that our method outperforms state-of-the-art methods on both general and fine-grained datasets.

Related papers

• Local Descriptors Weighted Adaptive Threshold Filtering For Few-Shot Learning [0.0]
  Few-shot image classification is a challenging task in the field of machine learning. We propose an innovative weighted adaptive threshold filtering (WATF) strategy for local descriptors. Our method maintains a simple and lightweight design philosophy without additional learnable parameters.
  arXiv  Detail & Related papers  (2024-08-28T16:36:23Z)
• Feature Aligning Few shot Learning Method Using Local Descriptors Weighted Rules [0.0]
  Few-shot classification involves identifying new categories using a limited number of labeled samples. This paper proposes a Feature Aligning Few-shot Learning Method Using Local Descriptors Weighted Rules (FAFD-LDWR) It innovatively introduces a cross-normalization method into few-shot image classification to preserve the discriminative information of local descriptors as much as possible; and enhances classification performance by aligning key local descriptors of support and query sets to remove background noise.
  arXiv  Detail & Related papers  (2024-08-26T11:36:38Z)
• DeLR: Active Learning for Detection with Decoupled Localization and Recognition Query [53.54802901197267]
  In this paper, we rethink two key components, i.e., localization and recognition, for object detection. Motivated by this, we propose an efficient query strategy, called Decoupling the localization and recognition for active query.
  arXiv  Detail & Related papers  (2023-12-28T09:58:32Z)
• TALDS-Net: Task-Aware Adaptive Local Descriptors Selection for Few-shot Image Classification [6.204356280380338]
  Few-shot image classification aims to classify images from unseen novel classes with few samples. Recent works demonstrate that deep local descriptors exhibit enhanced representational capabilities compared to image-level features. We propose a novel Task-Aware Adaptive Local Descriptors Selection Network (TALDS-Net)
  arXiv  Detail & Related papers  (2023-12-09T03:33:14Z)
• Learning to Detect Instance-level Salient Objects Using Complementary Image Labels [55.049347205603304]
  We present the first weakly-supervised approach to the salient instance detection problem. We propose a novel weakly-supervised network with three branches: a Saliency Detection Branch leveraging class consistency information to locate candidate objects; a Boundary Detection Branch exploiting class discrepancy information to delineate object boundaries; and a Centroid Detection Branch using subitizing information to detect salient instance centroids.
  arXiv  Detail & Related papers  (2021-11-19T10:15:22Z)
• Revisiting Deep Local Descriptor for Improved Few-Shot Classification [56.74552164206737]
  We show how one can improve the quality of embeddings by leveraging textbfDense textbfClassification and textbfAttentive textbfPooling. We suggest to pool feature maps by applying attentive pooling instead of the widely used global average pooling (GAP) to prepare embeddings for few-shot classification.
  arXiv  Detail & Related papers  (2021-03-30T00:48:28Z)
• Weakly-supervised Salient Instance Detection [65.0408760733005]
  We present the first weakly-supervised approach to the salient instance detection problem. We propose a novel weakly-supervised network with three branches: a Saliency Detection Branch leveraging class consistency information to locate candidate objects; a Boundary Detection Branch exploiting class discrepancy information to delineate object boundaries; and a Centroid Detection Branch using subitizing information to detect salient instance centroids.
  arXiv  Detail & Related papers  (2020-09-29T09:47:23Z)
• Learning and aggregating deep local descriptors for instance-level recognition [11.692327697598175]
  Training only requires examples of positive and negative image pairs. At inference, the local descriptors are provided by the activations of internal components of the network. We achieve state-of-the-art performance, in some cases even with a backbone network as small as ResNet18.
  arXiv  Detail & Related papers  (2020-07-26T16:30:56Z)
• Online Invariance Selection for Local Feature Descriptors [93.32949876169785]
  A limitation of current feature descriptors is the trade-off between generalization and discriminative power. We propose to overcome this limitation with a disentanglement of invariance in local descriptors and with an online selection of the most appropriate invariance given the context. We demonstrate that our method can boost the performance of current descriptors and outperforms state-of-the-art descriptors in several matching tasks.
  arXiv  Detail & Related papers  (2020-07-17T14:08:22Z)
• D2D: Keypoint Extraction with Describe to Detect Approach [48.0325745125635]
  We present a novel approach that exploits the information within the descriptor space to propose keypoint locations. We propose an approach that inverts this process by first describing and then detecting the keypoint locations.
  arXiv  Detail & Related papers  (2020-05-27T19:27:46Z)

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.