Related papers: SynthSet: Generative Diffusion Model for Semantic …

Accurate single cell detection in brightfield microscopy is crucial for biological research, yet data scarcity and annotation bottlenecks limit the progress of deep learning methods. We investigate the use of unconditional models to…

Effectively addressing the challenge of industrial Anomaly Detection (AD) necessitates an ample supply of defective samples, a constraint often hindered by their scarcity in industrial contexts. This paper introduces a novel algorithm…

In this study, we introduce a novel approach to synthesizing subsurface velocity models using diffusion generative models. Conventional methods rely on extensive, high-quality datasets, which are often inaccessible in subsurface…

Recent advancements in deep learning for medical image segmentation are often limited by the scarcity of high-quality training data.While diffusion models provide a potential solution by generating synthetic images, their effectiveness in…

The diffusion model is capable of generating high-quality data through a probabilistic approach. However, it suffers from the drawback of slow generation speed due to the requirement of a large number of time steps. To address this…

Recently, diffusion models have increasingly demonstrated their capabilities in vision understanding. By leveraging prompt-based learning to construct sentences, these models have shown proficiency in classification and visual grounding…

Supervised machine learning algorithms play a crucial role in optical quality control within industrial production. These approaches require representative datasets for effective model training. However, while non-defective components are…

The scale and quality of a dataset significantly impact the performance of deep models. However, acquiring large-scale annotated datasets is both a costly and time-consuming endeavor. To address this challenge, dataset expansion…

Semantic segmentation has witnessed tremendous progress due to the proposal of various advanced network architectures. However, they are extremely hungry for delicate annotations to train, and the acquisition is laborious and unaffordable.…

Automated semantic segmentation of cell nuclei in microscopic images is crucial for disease diagnosis and tissue microenvironment analysis. Nonetheless, this task presents challenges due to the complexity and heterogeneity of cells. While…

This paper presents a novel methodology for generating realistic abundance maps from hyperspectral imagery using an unsupervised, deep-learning-driven approach. Our framework integrates blind linear hyperspectral unmixing with…

In this paper, we propose a new dataset distillation method that considers balancing global structure and local details when distilling the information from a large dataset into a generative model. Dataset distillation has been proposed to…

While originally designed for image generation, diffusion models have recently shown to provide excellent pretrained feature representations for semantic segmentation. Intrigued by this result, we set out to explore how well…

Dataset distillation provides an effective approach to reduce memory and computational costs by optimizing a compact dataset that achieves performance comparable to the full original. However, for large-scale datasets and complex deep…

Speech super-resolution (SR) is the task that restores high-resolution speech from low-resolution input. Existing models employ simulated data and constrained experimental settings, which limit generalization to real-world SR. Predictive…

Diffusion-based image super-resolution (SR) methods have demonstrated remarkable performance. Recent advancements have introduced deterministic sampling processes that reduce inference from 15 iterative steps to a single step, thereby…

Training medical image segmentation models for rare yet clinically important imaging modalities is challenging due to the scarcity of annotated data, and manual mask annotations can be costly and labor-intensive to acquire. This paper…

In this study, we introduce a generative model that can synthesize a large number of radiographical image/label pairs, and thus is asymptotically favorable to downstream activities such as segmentation in bio-medical image analysis.…

Despite remarkable progress having been made on the problem of 3D human pose and shape estimation (HPS), current state-of-the-art methods rely heavily on either confined indoor mocap datasets or datasets generated by a rendering engine…

Medical image segmentation models struggle with rare abnormalities due to scarce annotated pathological data. We propose DiffAug a novel framework that combines textguided diffusion-based generation with automatic segmentation validation to…