Data-efficient U-Net for Segmentation of Carbide Microstructures in SEM Images of Steel Alloys

The paper presents the Selectively Suppressed Perfect Reconstruction (SUPER) Decoder Block, designed to enhance U-Net variants used in inverse problems. This method addresses the issue of information loss that limits the recovery of fine details in images. By leveraging the perfect reconstruction property of wavelets, SUPER selectively suppresses redundant features, thus improving representational richness and maintaining computational efficiency. Experiments demonstrate its effectiveness across various benchmarks, particularly in thin-crack segmentation and image denoising tasks.

The article presents CLUE (Controllable Latent space of Unprompted Embeddings), a generative model framework designed for text-to-image synthesis. CLUE aims to generate diverse images while ensuring stability, utilizing fixed-format prompts without the need for additional data. Built on the Stable Diffusion architecture, it incorporates a Style Encoder to create style embeddings, which are processed through a new attention layer in the U-Net. This approach addresses challenges faced in specialized fields like medicine, where data is often limited.

The article discusses a novel method for unsupervised segmentation of Micro-CT scans of polyurethane structures by integrating Hidden Markov Random Fields (HMRF) with a U-Net architecture. This approach aims to enhance segmentation accuracy and speed without the need for large labeled datasets, which are typically required for supervised learning. The integration of HMRF theory with convolutional neural networks (CNNs) represents a significant advancement in the field of material property analysis.