An Augmentation-based Model Re-adaptation Framework for Robust Image Segmentation

TL;DR

This paper introduces an augmentation-based framework for adapting segmentation models to industrial datasets with limited samples and complex textures, significantly improving accuracy over baseline and state-of-the-art models.

Contribution

The proposed AMRF leverages data augmentation to enhance model generalization and adapt to new datasets, outperforming existing models in industrial image segmentation tasks.

Findings

Fine-tuned FCN improves cropping accuracy by over 3% and classification by over 4%.

Fine-tuned U-Net surpasses baseline by over 7% in cropping and 8% in classification.

Our method outperforms top SAM models by an average of 10% in accuracy.

Abstract

Image segmentation is a crucial task in computer vision, with wide-ranging applications in industry. The Segment Anything Model (SAM) has recently attracted intensive attention; however, its application in industrial inspection, particularly for segmenting commercial anti-counterfeit codes, remains challenging. Unlike open-source datasets, industrial settings often face issues such as small sample sizes and complex textures. Additionally, computational cost is a key concern due to the varying number of trainable parameters. To address these challenges, we propose an Augmentation-based Model Re-adaptation Framework (AMRF). This framework leverages data augmentation techniques during training to enhance the generalisation of segmentation models, allowing them to adapt to newly released datasets with temporal disparity. By observing segmentation masks from conventional models (FCN and U-Net) and a pre-trained SAM model, we determine a minimal augmentation set that optimally balances training efficiency and model performance. Our results demonstrate that the fine-tuned FCN surpasses its baseline by 3.29% and 3.02% in cropping accuracy, and 5.27% and 4.04% in classification accuracy on two temporally continuous datasets. Similarly, the fine-tuned U-Net improves upon its baseline by 7.34% and 4.94% in cropping, and 8.02% and 5.52% in classification. Both models outperform the top-performing SAM models (ViT-Large and ViT-Base) by an average of 11.75% and 9.01% in cropping accuracy, and 2.93% and 4.83% in classification accuracy, respectively.