Continual learning for surface defect segmentation by subnetwork creation and selection

• URL: http://arxiv.org/abs/2312.05100v1
• Date: Fri, 8 Dec 2023 15:28:50 GMT
• Title: Continual learning for surface defect segmentation by subnetwork creation and selection
• Authors: Aleksandr Dekhovich and Miguel A. Bessa
• Abstract summary: We introduce a new continual (or lifelong) learning algorithm that performs segmentation tasks without undergoing catastrophic forgetting. The method is applied to two different surface defect segmentation problems that are learned incrementally. Our approach shows comparable results with joint training when all the training data (all defects) are seen simultaneously.
• Score: 55.2480439325792
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce a new continual (or lifelong) learning algorithm called LDA-CP&S that performs segmentation tasks without undergoing catastrophic forgetting. The method is applied to two different surface defect segmentation problems that are learned incrementally, i.e. providing data about one type of defect at a time, while still being capable of predicting every defect that was seen previously. Our method creates a defect-related subnetwork for each defect type via iterative pruning and trains a classifier based on linear discriminant analysis (LDA). At the inference stage, we first predict the defect type with LDA and then predict the surface defects using the selected subnetwork. We compare our method with other continual learning methods showing a significant improvement -- mean Intersection over Union better by a factor of two when compared to existing methods on both datasets. Importantly, our approach shows comparable results with joint training when all the training data (all defects) are seen simultaneously

Related papers

• Efficient Discrepancy Testing for Learning with Distribution Shift [17.472049019016524]
  We provide the first set of provably efficient algorithms for testing localized discrepancy distance. Results imply a broad set of new, efficient learning algorithms in the recently introduced model of Testable Learning with Distribution Shift.
  arXiv  Detail & Related papers  (2024-06-13T17:51:10Z)
• Informative regularization for a multi-layer perceptron RR Lyrae classifier under data shift [3.303002683812084]
  We propose a scalable and easily adaptable approach based on an informative regularization and an ad-hoc training procedure to mitigate the shift problem. Our method provides a new path to incorporate knowledge from characteristic features into artificial neural networks to manage the underlying data shift problem.
  arXiv  Detail & Related papers  (2023-03-12T02:49:19Z)
• A novel approach for wafer defect pattern classification based on topological data analysis [0.0]
  In semiconductor manufacturing, wafer map defect pattern provides critical information for facility maintenance and yield management. We propose a novel way to represent the shape of the defect pattern as a finite-dimensional vector, which will be used as an input for a neural network algorithm for classification.
  arXiv  Detail & Related papers  (2022-09-19T11:54:13Z)
• A New Knowledge Distillation Network for Incremental Few-Shot Surface Defect Detection [20.712532953953808]
  This paper proposes a new knowledge distillation network, called Dual Knowledge Align Network (DKAN) The proposed DKAN method follows a pretraining-finetuning transfer learning paradigm and a knowledge distillation framework is designed for fine-tuning. Experiments have been conducted on the incremental Few-shot NEU-DET dataset and results show that DKAN outperforms other methods on various few-shot scenes.
  arXiv  Detail & Related papers  (2022-09-01T15:08:44Z)
• Intersection of Parallels as an Early Stopping Criterion [64.8387564654474]
  We propose a method to spot an early stopping point in the training iterations without the need for a validation set. For a wide range of learning rates, our method, called Cosine-Distance Criterion (CDC), leads to better generalization on average than all the methods that we compare against.
  arXiv  Detail & Related papers  (2022-08-19T19:42:41Z)
• CAFA: Class-Aware Feature Alignment for Test-Time Adaptation [50.26963784271912]
  Test-time adaptation (TTA) aims to address this challenge by adapting a model to unlabeled data at test time. We propose a simple yet effective feature alignment loss, termed as Class-Aware Feature Alignment (CAFA), which simultaneously encourages a model to learn target representations in a class-discriminative manner.
  arXiv  Detail & Related papers  (2022-06-01T03:02:07Z)
• Simple Stochastic and Online Gradient DescentAlgorithms for Pairwise Learning [65.54757265434465]
  Pairwise learning refers to learning tasks where the loss function depends on a pair instances. Online descent (OGD) is a popular approach to handle streaming data in pairwise learning. In this paper, we propose simple and online descent to methods for pairwise learning.
  arXiv  Detail & Related papers  (2021-11-23T18:10:48Z)
• TL-SDD: A Transfer Learning-Based Method for Surface Defect Detection with Few Samples [17.884998028369026]
  We propose TL-SDD: a novel Transfer Learning-based method for Surface Defect Detection. We adopt a two-phase training scheme to transfer the knowledge from common defect classes to rare defect classes. Compared to the baseline methods, the performance of our proposed method has improved by up to 11.98% for rare defect classes.
  arXiv  Detail & Related papers  (2021-08-16T07:24:00Z)
• High-dimensional separability for one- and few-shot learning [58.8599521537]
  This work is driven by a practical question, corrections of Artificial Intelligence (AI) errors. Special external devices, correctors, are developed. They should provide quick and non-iterative system fix without modification of a legacy AI system. New multi-correctors of AI systems are presented and illustrated with examples of predicting errors and learning new classes of objects by a deep convolutional neural network.
  arXiv  Detail & Related papers  (2021-06-28T14:58:14Z)
• Task-agnostic Continual Learning with Hybrid Probabilistic Models [75.01205414507243]
  We propose HCL, a Hybrid generative-discriminative approach to Continual Learning for classification. The flow is used to learn the data distribution, perform classification, identify task changes, and avoid forgetting. We demonstrate the strong performance of HCL on a range of continual learning benchmarks such as split-MNIST, split-CIFAR, and SVHN-MNIST.
  arXiv  Detail & Related papers  (2021-06-24T05:19:26Z)

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.