# CINFormer: Transformer network with multi-stage CNN feature injection for surface defect segmentation

arXiv: https://arxiv.org/abs/2309.12639 · HTML: https://mlsanity.com/paper/2309.12639/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 54 references that are in the map.
- First posted on arXiv 22 Sep 2023.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [How Do Vision Transformers Work?](https://mlsanity.com/paper/2202.06709/) (2022)
- [Vision Transformer with Deformable Attention](https://mlsanity.com/paper/2201.00520/) (2022)
- [Focal Self-attention for Local-Global Interactions in Vision Transformers](https://mlsanity.com/paper/2107.00641/) (2021)
- [cosFormer: Rethinking Softmax in Attention](https://mlsanity.com/paper/2202.08791/) (2022)
- [UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning](https://mlsanity.com/paper/2201.04676/) (2022)
- [Visual Saliency Transformer](https://mlsanity.com/paper/2104.12099/) (2021)
- [Understanding Convolution for Semantic Segmentation](https://mlsanity.com/paper/1702.08502/) (2017)
- [Conformer: Local Features Coupling Global Representations for Visual Recognition](https://mlsanity.com/paper/2105.03889/) (2021)
- [Segmentation-Based Deep-Learning Approach for Surface-Defect Detection](https://mlsanity.com/paper/1903.08536/) (2019)
- [CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention](https://mlsanity.com/paper/2108.00154/) (2021)
- [Strip Pooling: Rethinking Spatial Pooling for Scene Parsing](https://mlsanity.com/paper/2003.13328/) (2020)
- [Global Context-Aware Progressive Aggregation Network for Salient Object Detection](https://mlsanity.com/paper/2003.00651/) (2020)
- [Shunted Self-Attention via Multi-Scale Token Aggregation](https://mlsanity.com/paper/2111.15193/) (2021)
- [Document-level Relation Extraction as Semantic Segmentation](https://mlsanity.com/paper/2106.03618/) (2021)
- [Pyramid Grafting Network for One-Stage High Resolution Saliency Detection](https://mlsanity.com/paper/2204.05041/) (2022)
- [ViTKD: Practical Guidelines for ViT feature knowledge distillation](https://mlsanity.com/paper/2209.02432/) (2022)

## Built on by (most cited first, 1 of 1)

- [UniSpector: Towards Universal Open-set Defect Recognition via Spectral-Contrastive Visual Prompting](https://mlsanity.com/paper/2604.02905/) (2026)

## Abstract (arXiv)

Surface defect inspection is of great importance for industrial manufacture and production. Though defect inspection methods based on deep learning have made significant progress, there are still some challenges for these methods, such as indistinguishable weak defects and defect-like interference in the background. To address these issues, we propose a transformer network with multi-stage CNN (Convolutional Neural Network) feature injection for surface defect segmentation, which is a UNet-like structure named CINFormer. 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. This can maintain the merit of CNN capturing detailed features and that of transformer depressing noises in the background, which facilitates accurate defect detection. In addition, CINFormer presents a Top-K self-attention module to focus on tokens with more important information about the defects, so as to further reduce the impact of the redundant background. Extensive experiments conducted on the surface defect datasets DAGM 2007, Magnetic tile, and NEU show that the proposed CINFormer achieves state-of-the-art performance in defect detection.