A Detector-oblivious Multi-arm Network for Keypoint Matching

• URL: http://arxiv.org/abs/2104.00947v3
• Date: Sat, 1 Jun 2024 07:55:27 GMT
• Title: A Detector-oblivious Multi-arm Network for Keypoint Matching
• Authors: Xuelun Shen, Qian Hu, Xin Li, Cheng Wang,
• Abstract summary: We propose a Multi-Arm Network (MAN) to learn region overlap and depth. Comprehensive experiments conducted on outdoor and indoor datasets demonstrated that our proposed MAN outperforms state-of-the-art methods.
• Score: 14.051194519908455
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper presents a matching network to establish point correspondence between images. We propose a Multi-Arm Network (MAN) to learn region overlap and depth, which can greatly improve the keypoint matching robustness while bringing little computational cost during the inference stage. Another design that makes this framework different from many existing learning based pipelines that require re-training when a different keypoint detector is adopted, our network can directly work with different keypoint detectors without such a time-consuming re-training process. Comprehensive experiments conducted on outdoor and indoor datasets demonstrated that our proposed MAN outperforms state-of-the-art methods.

Related papers

• Deep Internal Learning: Deep Learning from a Single Input [88.59966585422914]
  In many cases there is value in training a network just from the input at hand. This is particularly relevant in many signal and image processing problems where training data is scarce and diversity is large. This survey paper aims at covering deep internal-learning techniques that have been proposed in the past few years for these two important directions.
  arXiv  Detail & Related papers  (2023-12-12T16:48:53Z)
• CMFDFormer: Transformer-based Copy-Move Forgery Detection with Continual Learning [52.72888626663642]
  Copy-move forgery detection aims at detecting duplicated regions in a suspected forged image. Deep learning based copy-move forgery detection methods are in the ascendant. We propose a Transformer-style copy-move forgery network named as CMFDFormer. We also provide a novel PCSD continual learning framework to help CMFDFormer handle new tasks.
  arXiv  Detail & Related papers  (2023-11-22T09:27:46Z)
• The Wyner Variational Autoencoder for Unsupervised Multi-Layer Wireless Fingerprinting [6.632671046812309]
  We propose a multi-layer fingerprinting framework that jointly considers the multi-layer signatures for improved identification performance. In contrast to previous works, by leveraging the recent multi-view machine learning paradigm, our method can cluster the device information shared among the multi-layer features without supervision. Our empirical results show that the proposed method outperforms the state-of-the-art baselines in both supervised and unsupervised settings.
  arXiv  Detail & Related papers  (2023-03-28T10:05:06Z)
• Keypoints Tracking via Transformer Networks [0.0]
  We propose a pioneering work on sparse keypoints tracking across images using transformer networks. We study the particular case of real-time and robust keypoints tracking. Our method consists of two successive stages, a coarse matching followed by a fine localization of the keypoints' correspondences.
  arXiv  Detail & Related papers  (2022-03-24T05:06:46Z)
• BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning [93.38239238988719]
  We propose to enable deep neural networks with the ability to learn the sample relationships from each mini-batch. BatchFormer is applied into the batch dimension of each mini-batch to implicitly explore sample relationships during training. We perform extensive experiments on over ten datasets and the proposed method achieves significant improvements on different data scarcity applications.
  arXiv  Detail & Related papers  (2022-03-03T05:31:33Z)
• Parallel Multi-Scale Networks with Deep Supervision for Hand Keypoint Detection [3.1781111932870716]
  We propose a novel CNN model named Multi-Scale Deep Supervision Network (P-MSDSNet) P-MSDSNet learns feature maps at different scales with deep supervisions to produce attention maps for adaptive feature propagation from layers to layers. We show that P-MSDSNet outperforms the state-of-the-art approaches on benchmark datasets while requiring fewer number of parameters.
  arXiv  Detail & Related papers  (2021-12-19T22:38:16Z)
• Experience feedback using Representation Learning for Few-Shot Object Detection on Aerial Images [2.8560476609689185]
  The performance of our method is assessed on DOTA, a large-scale remote sensing images dataset. It highlights in particular some intrinsic weaknesses for the few-shot object detection task.
  arXiv  Detail & Related papers  (2021-09-27T13:04:53Z)
• Decoupled and Memory-Reinforced Networks: Towards Effective Feature Learning for One-Step Person Search [65.51181219410763]
  One-step methods have been developed to handle pedestrian detection and identification sub-tasks using a single network. There are two major challenges in the current one-step approaches. We propose a decoupled and memory-reinforced network (DMRNet) to overcome these problems.
  arXiv  Detail & Related papers  (2021-02-22T06:19:45Z)
• Suppress and Balance: A Simple Gated Network for Salient Object Detection [89.88222217065858]
  We propose a simple gated network (GateNet) to solve both issues at once. With the help of multilevel gate units, the valuable context information from the encoder can be optimally transmitted to the decoder. In addition, we adopt the atrous spatial pyramid pooling based on the proposed "Fold" operation (Fold-ASPP) to accurately localize salient objects of various scales.
  arXiv  Detail & Related papers  (2020-07-16T02:00:53Z)
• Fitting the Search Space of Weight-sharing NAS with Graph Convolutional Networks [100.14670789581811]
  We train a graph convolutional network to fit the performance of sampled sub-networks. With this strategy, we achieve a higher rank correlation coefficient in the selected set of candidates.
  arXiv  Detail & Related papers  (2020-04-17T19:12:39Z)
• Finding the Optimal Network Depth in Classification Tasks [10.248235276871258]
  We develop a fast end-to-end method for training lightweight neural networks using multiple classifier heads. By allowing the model to determine the importance of each head, we are able to detect and remove unneeded components of the network.
  arXiv  Detail & Related papers  (2020-04-17T11:08:45Z)

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.