A Comparison of Few-Shot Learning Methods for Underwater Optical and Sonar Image Classification

• URL: http://arxiv.org/abs/2005.04621v2
• Date: Mon, 26 Oct 2020 15:18:43 GMT
• Title: A Comparison of Few-Shot Learning Methods for Underwater Optical and Sonar Image Classification
• Authors: Mateusz Ochal, Jose Vazquez, Yvan Petillot, Sen Wang
• Abstract summary: Deep convolutional neural networks generally perform well in underwater object recognition tasks. Few-Shot Learning efforts have produced many promising methods to deal with low data availability. This paper is the first paper to evaluate and compare several supervised and semi-supervised Few-Shot Learning methods using underwater optical and side-scan sonar imagery.
• Score: 10.448481847860705
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep convolutional neural networks generally perform well in underwater object recognition tasks on both optical and sonar images. Many such methods require hundreds, if not thousands, of images per class to generalize well to unseen examples. However, obtaining and labeling sufficiently large volumes of data can be relatively costly and time-consuming, especially when observing rare objects or performing real-time operations. Few-Shot Learning (FSL) efforts have produced many promising methods to deal with low data availability. However, little attention has been given in the underwater domain, where the style of images poses additional challenges for object recognition algorithms. To the best of our knowledge, this is the first paper to evaluate and compare several supervised and semi-supervised Few-Shot Learning (FSL) methods using underwater optical and side-scan sonar imagery. Our results show that FSL methods offer a significant advantage over the traditional transfer learning methods that fine-tune pre-trained models. We hope that our work will help apply FSL to autonomous underwater systems and expand their learning capabilities.

Related papers

• CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations [90.50864830038202]
  We present Contrastive Spatial Pre-Training (CSP), a self-supervised learning framework for geo-tagged images. We use a dual-encoder to separately encode the images and their corresponding geo-locations, and use contrastive objectives to learn effective location representations from images. CSP significantly boosts the model performance with 10-34% relative improvement with various labeled training data sampling ratios.
  arXiv  Detail & Related papers  (2023-05-01T23:11:18Z)
• Spectrum-inspired Low-light Image Translation for Saliency Detection [23.368690302292563]
  We propose a technique that transforms well-lit images to low-light images and use them as a proxy for real low-light images. Unlike popular deep learning approaches which require learning thousands of parameters and enormous amounts of training data, the proposed transformation is fast and simple and easy to extend to other tasks such as low-light depth estimation. Our experiments show that the state-of-the-art saliency detection and depth estimation networks trained on our proxy low-light images perform significantly better on real low-light images than networks trained using existing strategies.
  arXiv  Detail & Related papers  (2023-03-17T17:30:42Z)
• Leveraging the Third Dimension in Contrastive Learning [88.17394309208925]
  Self-Supervised Learning (SSL) methods operate on unlabeled data to learn robust representations useful for downstream tasks. These augmentations ignore the fact that biological vision takes place in an immersive three-dimensional, temporally contiguous environment. We explore two distinct approaches to incorporating depth signals into the SSL framework.
  arXiv  Detail & Related papers  (2023-01-27T15:45:03Z)
• Self Supervised Learning for Few Shot Hyperspectral Image Classification [57.2348804884321]
  We propose to leverage Self Supervised Learning (SSL) for HSI classification. We show that by pre-training an encoder on unlabeled pixels using Barlow-Twins, a state-of-the-art SSL algorithm, we can obtain accurate models with a handful of labels.
  arXiv  Detail & Related papers  (2022-06-24T07:21:53Z)
• Self-supervised Learning for Sonar Image Classification [6.1947705963945845]
  Self-supervised learning has proved to be a powerful approach to learn image representations without the need of large labeled datasets. We present pre-training and transfer learning results on real-life sonar image datasets.
  arXiv  Detail & Related papers  (2022-04-20T08:58:35Z)
• VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition [61.75391989107558]
  We present a visual-linguistic long-tailed recognition framework, termed VL-LTR. Our method can learn visual representation from images and corresponding linguistic representation from noisy class-level text descriptions. Notably, our method achieves 77.2% overall accuracy on ImageNet-LT, which significantly outperforms the previous best method by over 17 points.
  arXiv  Detail & Related papers  (2021-11-26T16:24:03Z)
• Few-Cost Salient Object Detection with Adversarial-Paced Learning [95.0220555274653]
  This paper proposes to learn the effective salient object detection model based on the manual annotation on a few training images only. We name this task as the few-cost salient object detection and propose an adversarial-paced learning (APL)-based framework to facilitate the few-cost learning scenario.
  arXiv  Detail & Related papers  (2021-04-05T14:15:49Z)
• Speckle2Void: Deep Self-Supervised SAR Despeckling with Blind-Spot Convolutional Neural Networks [30.410981386006394]
  despeckling is a crucial preliminary step in scene analysis algorithms. Recent success of deep learning envisions a new generation of despeckling techniques. We propose a self-supervised Bayesian despeckling method.
  arXiv  Detail & Related papers  (2020-07-04T11:38:48Z)
• AdarGCN: Adaptive Aggregation GCN for Few-Shot Learning [112.95742995816367]
  We propose a new few-shot fewshot learning setting termed FSFSL. Under FSFSL, both the source and target classes have limited training samples. We also propose a graph convolutional network (GCN)-based label denoising (LDN) method to remove irrelevant images.
  arXiv  Detail & Related papers  (2020-02-28T10:34:36Z)
• Towards Deep Unsupervised SAR Despeckling with Blind-Spot Convolutional Neural Networks [30.410981386006394]
  Deep learning techniques have outperformed classical model-based despeckling algorithms. In this paper, we propose a self-supervised Bayesian despeckling method. We show that the performance of the proposed network is very close to the supervised training approach on synthetic data and competitive on real data.
  arXiv  Detail & Related papers  (2020-01-15T12:21:12Z)
• Deep Image Feature Learning with Fuzzy Rules [25.4399762282053]
  The paper proposes a more interpretable and scalable feature learning method, i.e., deep image feature learning with fuzzy rules (DIFL-FR) The method progressively learns image features through a layer-by-layer manner based on fuzzy rules, so the feature learning process can be better explained by the generated rules. In addition, the method is under the settings of unsupervised learning and can be easily extended to scenes of supervised and semi-supervised learning.
  arXiv  Detail & Related papers  (2019-05-25T11:33:02Z)

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.