Carton dataset synthesis method for domain shift based on foreground texture decoupling and replacement
Lijun Gou, Shengkai Wu, Jinrong Yang, Hangcheng Yu, Chenxi Lin,, Xiaoping Li, Chao Deng

TL;DR
This paper introduces a novel image synthesis method that replaces foreground textures to address domain shift in object detection, significantly improving model generalization across different scenarios in industrial datasets.
Contribution
A new foreground texture decoupling and replacement technique that enhances dataset diversity and model robustness across domains.
Findings
Boosts AP by 4.3%~6.5% on RetinaNet
Improves AP by 3.4%~6.8% on Faster R-CNN
Effectively reduces domain shift in industrial object detection
Abstract
One major impediment in rapidly deploying object detection models for industrial applications is the lack of large annotated datasets. We currently have presented the Sacked Carton Dataset(SCD) that contains carton images from three scenarios, such as comprehensive pharmaceutical logistics company(CPLC), e-commerce logistics company(ECLC), fruit market(FM). However, due to domain shift, the model trained with one of the three scenarios in SCD has poor generalization ability when applied to the rest scenarios. To solve this problem, a novel image synthesis method is proposed to replace the foreground texture of the source datasets with the texture of the target datasets. Our method can keep the context relationship of foreground objects and backgrounds unchanged and greatly augment the target datasets. We firstly propose a surface segmentation algorithm to achieve texture decoupling of…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Neural Network Applications · Advanced Image and Video Retrieval Techniques · Industrial Vision Systems and Defect Detection
Methods1x1 Convolution · RoIPool · Focal Loss · Feature Pyramid Network · Region Proposal Network · Convolution · Softmax · Faster R-CNN · RetinaNet
