A New Knowledge Distillation Network for Incremental Few-Shot Surface Defect Detection

• URL: http://arxiv.org/abs/2209.00519v1
• Date: Thu, 1 Sep 2022 15:08:44 GMT
• Title: A New Knowledge Distillation Network for Incremental Few-Shot Surface Defect Detection
• Authors: Chen Sun, Liang Gao, Xinyu Li, Yiping Gao
• Abstract summary: 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.
• Score: 20.712532953953808
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Surface defect detection is one of the most essential processes for industrial quality inspection. Deep learning-based surface defect detection methods have shown great potential. However, the well-performed models usually require large training data and can only detect defects that appeared in the training stage. When facing incremental few-shot data, defect detection models inevitably suffer from catastrophic forgetting and misclassification problem. To solve these problems, 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. Specifically, an Incremental RCNN is proposed to achieve decoupled stable feature representation of different categories. Under this framework, a Feature Knowledge Align (FKA) loss is designed between class-agnostic feature maps to deal with catastrophic forgetting problems, and a Logit Knowledge Align (LKA) loss is deployed between logit distributions to tackle misclassification problems. 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, up to 6.65% on the mean Average Precision metric, which proves the effectiveness of the proposed method.

Related papers

• Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration [74.09687562334682]
  We introduce a novel training data attribution method called Debias and Denoise Attribution (DDA) Our method significantly outperforms existing approaches, achieving an averaged AUC of 91.64%. DDA exhibits strong generality and scalability across various sources and different-scale models like LLaMA2, QWEN2, and Mistral.
  arXiv  Detail & Related papers  (2024-10-02T07:14:26Z)
• A Reusable AI-Enabled Defect Detection System for Railway Using Ensembled CNN [5.381374943525773]
  Defect detection is crucial for ensuring the trustworthiness of railway systems. Current approaches rely on single deep-learning models, like CNNs. We propose a reusable AI-enabled defect detection approach.
  arXiv  Detail & Related papers  (2023-11-24T19:45:55Z)
• CINFormer: Transformer network with multi-stage CNN feature injection for surface defect segmentation [73.02218479926469]
  We propose a transformer network with multi-stage CNN feature injection for surface defect segmentation. CINFormer presents a simple yet effective feature integration mechanism that injects the multi-level CNN features of the input image into different stages of the transformer network in the encoder. In addition, CINFormer presents a Top-K self-attention module to focus on tokens with more important information about the defects.
  arXiv  Detail & Related papers  (2023-09-22T06:12:02Z)
• SEMI-DiffusionInst: A Diffusion Model Based Approach for Semiconductor Defect Classification and Segmentation [0.11999555634662631]
  This work is the first demonstration to accurately detect and precisely segment semiconductor defect patterns by using a diffusion model. Our proposed approach outperforms previous work on overall mAP and performs comparatively better or as per for almost all defect classes.
  arXiv  Detail & Related papers  (2023-07-17T17:53:36Z)
• SCLIFD:Supervised Contrastive Knowledge Distillation for Incremental Fault Diagnosis under Limited Fault Data [8.354404360859263]
  It is difficult to extract discriminative features from limited fault data. A well-trained model must be retrained from scratch to classify the samples from new classes. The model decision is biased toward the new classes due to the class imbalance.
  arXiv  Detail & Related papers  (2023-02-12T14:50:12Z)
• Diffusion Denoising Process for Perceptron Bias in Out-of-distribution Detection [67.49587673594276]
  We introduce a new perceptron bias assumption that suggests discriminator models are more sensitive to certain features of the input, leading to the overconfidence problem. We demonstrate that the diffusion denoising process (DDP) of DMs serves as a novel form of asymmetric, which is well-suited to enhance the input and mitigate the overconfidence problem. Our experiments on CIFAR10, CIFAR100, and ImageNet show that our method outperforms SOTA approaches.
  arXiv  Detail & Related papers  (2022-11-21T08:45:08Z)
• 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)
• Few-shot Action Recognition with Prototype-centered Attentive Learning [88.10852114988829]
  Prototype-centered Attentive Learning (PAL) model composed of two novel components. First, a prototype-centered contrastive learning loss is introduced to complement the conventional query-centered learning objective. Second, PAL integrates a attentive hybrid learning mechanism that can minimize the negative impacts of outliers.
  arXiv  Detail & Related papers  (2021-01-20T11:48:12Z)
• NADS: Neural Architecture Distribution Search for Uncertainty Awareness [79.18710225716791]
  Machine learning (ML) systems often encounter Out-of-Distribution (OoD) errors when dealing with testing data coming from a distribution different from training data. Existing OoD detection approaches are prone to errors and even sometimes assign higher likelihoods to OoD samples. We propose Neural Architecture Distribution Search (NADS) to identify common building blocks among all uncertainty-aware architectures.
  arXiv  Detail & Related papers  (2020-06-11T17:39:07Z)
• Rectified Meta-Learning from Noisy Labels for Robust Image-based Plant Disease Diagnosis [64.82680813427054]
  Plant diseases serve as one of main threats to food security and crop production. One popular approach is to transform this problem as a leaf image classification task, which can be addressed by the powerful convolutional neural networks (CNNs) We propose a novel framework that incorporates rectified meta-learning module into common CNN paradigm to train a noise-robust deep network without using extra supervision information.
  arXiv  Detail & Related papers  (2020-03-17T09:51:30Z)

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.