Unsupervised Deep Learning-based Keypoint Localization Estimating Descriptor Matching Performance

• URL: http://arxiv.org/abs/2505.02779v1
• Date: Mon, 05 May 2025 16:46:32 GMT
• Title: Unsupervised Deep Learning-based Keypoint Localization Estimating Descriptor Matching Performance
• Authors: David Rivas-Villar, Álvaro S. Hervella, José Rouco, Jorge Novo,
• Abstract summary: We present a novel unsupervised registration pipeline for color fundus images.<n>Our approach is based on the principle that locations with distinctive descriptors constitute reliable keypoints.<n>We validate our method through a comprehensive evaluation on four hold-out datasets.
• Score: 6.618504904743609
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Retinal image registration, particularly for color fundus images, is a challenging yet essential task with diverse clinical applications. Existing registration methods for color fundus images typically rely on keypoints and descriptors for alignment; however, a significant limitation is their reliance on labeled data, which is particularly scarce in the medical domain. In this work, we present a novel unsupervised registration pipeline that entirely eliminates the need for labeled data. Our approach is based on the principle that locations with distinctive descriptors constitute reliable keypoints. This fully inverts the conventional state-of-the-art approach, conditioning the detector on the descriptor rather than the opposite. First, we propose an innovative descriptor learning method that operates without keypoint detection or any labels, generating descriptors for arbitrary locations in retinal images. Next, we introduce a novel, label-free keypoint detector network which works by estimating descriptor performance directly from the input image. We validate our method through a comprehensive evaluation on four hold-out datasets, demonstrating that our unsupervised descriptor outperforms state-of-the-art supervised descriptors and that our unsupervised detector significantly outperforms existing unsupervised detection methods. Finally, our full registration pipeline achieves performance comparable to the leading supervised methods, while not employing any labeled data. Additionally, the label-free nature and design of our method enable direct adaptation to other domains and modalities.

Related papers

• Unsupervised training of keypoint-agnostic descriptors for flexible retinal image registration [6.618504904743609]
  We develop a novel unsupervised descriptor learning method that does not rely on keypoint detection.<n>This enables the resulting descriptor network to be agnostic to the keypoint detector used during the registration inference.<n>Our results demonstrate that the proposed approach offers accurate registration, not incurring in any performance loss versus supervised methods.
  arXiv  Detail & Related papers  (2025-05-05T17:02:13Z)
• Prototype-Based Continual Learning with Label-free Replay Buffer and Cluster Preservation Loss [3.824522034247845]
  Continual learning techniques employ simple replay sample selection processes and use them during subsequent tasks.<n>In this paper, we depart from this by automatically selecting prototypes stored without labels.<n>"Push-away" and "pull-toward" mechanisms are also introduced for class-incremental and domain-incremental scenarios.
  arXiv  Detail & Related papers  (2025-04-09T19:26:26Z)
• MVC-VPR: Mutual Learning of Viewpoint Classification and Visual Place Recognition [13.681827205077727]
  We introduce the mutual learning of viewpoint self-classification and Visual Place Recognition.<n>The dataset is partitioned in an unsupervised manner while simultaneously training a descriptor extractor for place recognition.<n>Our method even excels state-of-the-art (SOTA) methods that partition datasets using ground truth labels.
  arXiv  Detail & Related papers  (2024-12-12T11:49:18Z)
• Cycle-Correspondence Loss: Learning Dense View-Invariant Visual Features from Unlabeled and Unordered RGB Images [8.789674502390378]
  We introduce Cycle-Correspondence Loss (CCL) for view-invariant dense descriptor learning. The key idea is to autonomously detect valid pixel correspondences by attempting to use a prediction over a new image. Our evaluation shows that we outperform other self-supervised RGB-only methods, and approach performance of supervised methods.
  arXiv  Detail & Related papers  (2024-06-18T09:44:56Z)
• Neighbour Consistency Guided Pseudo-Label Refinement for Unsupervised Person Re-Identification [80.98291772215154]
  Unsupervised person re-identification (ReID) aims at learning discriminative identity features for person retrieval without any annotations. Recent advances accomplish this task by leveraging clustering-based pseudo labels. We propose a Neighbour Consistency guided Pseudo Label Refinement framework.
  arXiv  Detail & Related papers  (2022-11-30T09:39:57Z)
• UIA-ViT: Unsupervised Inconsistency-Aware Method based on Vision Transformer for Face Forgery Detection [52.91782218300844]
  We propose a novel Unsupervised Inconsistency-Aware method based on Vision Transformer, called UIA-ViT. Due to the self-attention mechanism, the attention map among patch embeddings naturally represents the consistency relation, making the vision Transformer suitable for the consistency representation learning.
  arXiv  Detail & Related papers  (2022-10-23T15:24:47Z)
• Unsupervised Domain Adaptive Salient Object Detection Through Uncertainty-Aware Pseudo-Label Learning [104.00026716576546]
  We propose to learn saliency from synthetic but clean labels, which naturally has higher pixel-labeling quality without the effort of manual annotations. We show that our proposed method outperforms the existing state-of-the-art deep unsupervised SOD methods on several benchmark datasets.
  arXiv  Detail & Related papers  (2022-02-26T16:03:55Z)
• SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Mining [76.95808270536318]
  We propose an end-to-end system that learns to separate proposals into labeled and unlabeled regions using Pseudo-positive mining. While the labeled regions are processed as usual, self-supervised learning is used to process the unlabeled regions. We conduct exhaustive experiments on five splits on the PASCAL-VOC and COCO datasets achieving state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-01-12T18:57:04Z)
• Decoupling Makes Weakly Supervised Local Feature Better [39.17900986173409]
  We propose a decoupled describe-then-detect pipeline tailored for weakly supervised local feature learning. Within our pipeline, the detection step is decoupled from the description step and postponed until discriminative and robust descriptors are learned. In addition, we introduce a line-to-window search strategy to explicitly use the camera pose information for better descriptor learning.
  arXiv  Detail & Related papers  (2022-01-08T16:51:02Z)
• Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection [85.11649974840758]
  3D object detection networks tend to be biased towards the data they are trained on. We propose a single-frame approach for source-free, unsupervised domain adaptation of lidar-based 3D object detectors.
  arXiv  Detail & Related papers  (2021-11-30T18:42:42Z)
• Dual-Refinement: Joint Label and Feature Refinement for Unsupervised Domain Adaptive Person Re-Identification [51.98150752331922]
  Unsupervised domain adaptive (UDA) person re-identification (re-ID) is a challenging task due to the missing of labels for the target domain data. We propose a novel approach, called Dual-Refinement, that jointly refines pseudo labels at the off-line clustering phase and features at the on-line training phase. Our method outperforms the state-of-the-art methods by a large margin.
  arXiv  Detail & Related papers  (2020-12-26T07:35:35Z)
• Solving Missing-Annotation Object Detection with Background Recalibration Loss [49.42997894751021]
  This paper focuses on a novel and challenging detection scenario: A majority of true objects/instances is unlabeled in the datasets. Previous art has proposed to use soft sampling to re-weight the gradients of RoIs based on the overlaps with positive instances, while their method is mainly based on the two-stage detector. In this paper, we introduce a superior solution called Background Recalibration Loss (BRL) that can automatically re-calibrate the loss signals according to the pre-defined IoU threshold and input image.
  arXiv  Detail & Related papers  (2020-02-12T23:11:46Z)

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.