IncSAR: A Dual Fusion Incremental Learning Framework for SAR Target Recognition

• URL: http://arxiv.org/abs/2410.05820v2
• Date: Fri, 17 Jan 2025 10:01:30 GMT
• Title: IncSAR: A Dual Fusion Incremental Learning Framework for SAR Target Recognition
• Authors: George Karantaidis, Athanasios Pantsios, Ioannis Kompatsiaris, Symeon Papadopoulos,
• Abstract summary: IncSAR is an incremental learning framework designed to tackle catastrophic forgetting in target recognition. To mitigate the speckle noise inherent in SAR images, we employ a denoising module based on a neural network approximation. Experiments on the MSTAR, SAR-AIRcraft-1.0, and OpenSARShip benchmark datasets demonstrate that IncSAR significantly outperforms state-of-the-art approaches.
• Score: 13.783950035836593
• License:
• Abstract: Deep learning techniques have achieved significant success in Synthetic Aperture Radar (SAR) target recognition using predefined datasets in static scenarios. However, real-world applications demand that models incrementally learn new information without forgetting previously acquired knowledge. The challenge of catastrophic forgetting, where models lose past knowledge when adapting to new tasks, remains a critical issue. In this paper, we introduce IncSAR, an incremental learning framework designed to tackle catastrophic forgetting in SAR target recognition. IncSAR combines the power of a Vision Transformer (ViT) and a custom-designed Convolutional Neural Network (CNN) in a dual-branch architecture, integrated via a late-fusion strategy. Additionally, we explore the use of TinyViT to reduce computational complexity and propose an attention mechanism to dynamically enhance feature representation. To mitigate the speckle noise inherent in SAR images, we employ a denoising module based on a neural network approximation of Robust Principal Component Analysis (RPCA), leveraging a simple neural network for efficient noise reduction in SAR imagery. Moreover, a random projection layer improves the linear separability of features, and a variant of Linear Discriminant Analysis (LDA) decorrelates extracted class prototypes for better generalization. Extensive experiments on the MSTAR, SAR-AIRcraft-1.0, and OpenSARShip benchmark datasets demonstrate that IncSAR significantly outperforms state-of-the-art approaches, achieving a 99.63\% average accuracy and a 0.33\% performance drop, representing an 89\% improvement in retention compared to existing techniques. The source code is available at https://github.com/geokarant/IncSAR.

Related papers

• EMWaveNet: Physically Explainable Neural Network Based on Electromagnetic Propagation for SAR Target Recognition [4.251056028888424]
  This study proposes a physically explainable framework for complex-valued SAR image recognition. The network architecture is fully parameterized, with all learnable parameters endowed with clear physical meanings. The proposed method possesses a strong physical decision logic, high physical explainability and robustness, as well as excellent de-aliasing capabilities.
  arXiv  Detail & Related papers  (2024-10-13T07:04:49Z)
• IRASNet: Improved Feature-Level Clutter Reduction for Domain Generalized SAR-ATR [8.857297839399193]
  This study proposes a framework particularly designed for domain-generalized SAR-ATR called IRASNet. IRASNet enables effective feature-level clutter reduction and domain-invariant feature learning. IRASNet not only enhances performance but also significantly improves feature-level clutter reduction, making it a valuable advancement in the field of radar image pattern recognition.
  arXiv  Detail & Related papers  (2024-09-25T11:53:58Z)
• Benchmarking Deep Learning Classifiers for SAR Automatic Target Recognition [7.858656052565242]
  This paper comprehensively benchmarks several advanced deep learning models for SAR ATR with multiple distinct SAR imagery datasets. We evaluate and compare the five classifiers concerning their classification accuracy runtime performance in terms of inference throughput and analytical performance. No clear model winner emerges from all of our chosen metrics and a one model rules all case is doubtful in the domain of SAR ATR.
  arXiv  Detail & Related papers  (2023-12-12T02:20:39Z)
• Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning [52.06176253457522]
  We propose a two-stage framework tailored for small object detection based on the Coarse-to-fine pipeline and Feature Imitation learning. CFINet achieves state-of-the-art performance on the large-scale small object detection benchmarks, SODA-D and SODA-A.
  arXiv  Detail & Related papers  (2023-08-18T13:13:09Z)
• Class Anchor Margin Loss for Content-Based Image Retrieval [97.81742911657497]
  We propose a novel repeller-attractor loss that falls in the metric learning paradigm, yet directly optimize for the L2 metric without the need of generating pairs. We evaluate the proposed objective in the context of few-shot and full-set training on the CBIR task, by using both convolutional and transformer architectures.
  arXiv  Detail & Related papers  (2023-06-01T12:53:10Z)
• Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution [91.3781512926942]
  Image super-resolution (SR) has witnessed extensive neural network designs from CNN to transformer architectures. This work investigates the potential of network pruning for super-resolution iteration to take advantage of off-the-shelf network designs and reduce the underlying computational overhead. We propose a novel Iterative Soft Shrinkage-Percentage (ISS-P) method by optimizing the sparse structure of a randomly network at each and tweaking unimportant weights with a small amount proportional to the magnitude scale on-the-fly.
  arXiv  Detail & Related papers  (2023-03-16T21:06:13Z)
• Learning class prototypes from Synthetic InSAR with Vision Transformers [2.41710192205034]
  Detection of early signs of volcanic unrest is critical for assessing volcanic hazard. We propose a novel deep learning methodology that exploits a rich source of synthetically generated interferograms. We report detection accuracy that surpasses the state of the art on volcanic unrest detection.
  arXiv  Detail & Related papers  (2022-01-09T14:03:00Z)
• Learning A 3D-CNN and Transformer Prior for Hyperspectral Image Super-Resolution [80.93870349019332]
  We propose a novel HSISR method that uses Transformer instead of CNN to learn the prior of HSIs. Specifically, we first use the gradient algorithm to solve the HSISR model, and then use an unfolding network to simulate the iterative solution processes.
  arXiv  Detail & Related papers  (2021-11-27T15:38:57Z)
• Robust lEarned Shrinkage-Thresholding (REST): Robust unrolling for sparse recover [87.28082715343896]
  We consider deep neural networks for solving inverse problems that are robust to forward model mis-specifications. We design a new robust deep neural network architecture by applying algorithm unfolding techniques to a robust version of the underlying recovery problem. The proposed REST network is shown to outperform state-of-the-art model-based and data-driven algorithms in both compressive sensing and radar imaging problems.
  arXiv  Detail & Related papers  (2021-10-20T06:15:45Z)
• Sparse Signal Models for Data Augmentation in Deep Learning ATR [0.8999056386710496]
  We propose a data augmentation approach to incorporate domain knowledge and improve the generalization power of a data-intensive learning algorithm. We exploit the sparsity of the scattering centers in the spatial domain and the smoothly-varying structure of the scattering coefficients in the azimuthal domain to solve the ill-posed problem of over-parametrized model fitting.
  arXiv  Detail & Related papers  (2020-12-16T21:46:33Z)
• Understanding Self-supervised Learning with Dual Deep Networks [74.92916579635336]
  We propose a novel framework to understand contrastive self-supervised learning (SSL) methods that employ dual pairs of deep ReLU networks. We prove that in each SGD update of SimCLR with various loss functions, the weights at each layer are updated by a emphcovariance operator. To further study what role the covariance operator plays and which features are learned in such a process, we model data generation and augmentation processes through a emphhierarchical latent tree model (HLTM)
  arXiv  Detail & Related papers  (2020-10-01T17:51:49Z)

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.