相关论文: High-Quality Entity Segmentation

Deep learning has gained significant attention in medical image segmentation. However, the limited availability of annotated training data presents a challenge to achieving accurate results. In efforts to overcome this challenge, data…

Computed Tomography (CT) based precise prostate segmentation for treatment planning is challenging due to (1) the unclear boundary of the prostate derived from CT's poor soft tissue contrast and (2) the limitation of convolutional neural…

We present a framework for efficient perceptual inference that explicitly reasons about the segmentation of its inputs and features. Rather than being trained for any specific segmentation, our framework learns the grouping process in an…

While foundation models drive steady progress in image segmentation and diffusion algorithms compose always more realistic images, the seemingly simple problem of identifying recurrent patterns in a collection of images remains very much…

We propose an approach to instance-level image segmentation that is built on top of category-level segmentation. Specifically, for each pixel in a semantic category mask, its corresponding instance bounding box is predicted using a deep…

Accurate medical image segmentation is crucial for precise anatomical delineation. Deep learning models like U-Net have shown great success but depend heavily on large datasets and struggle with domain shifts, complex structures, and…

Semantic segmentation of microscopy cell images by deep learning is a significant technique. We considered that the Transformers, which have recently outperformed CNNs in image recognition, could also be improved and developed for cell…

Semantic segmentation, which refers to pixel-wise classification of an image, is a fundamental topic in computer vision owing to its growing importance in robot vision and autonomous driving industries. It provides rich information about…

Most dense recognition approaches bring a separate decision in each particular pixel. These approaches deliver competitive performance in usual closed-set setups. However, important applications in the wild typically require strong…

Quantifying the predictive uncertainty emerged as a possible solution to common challenges like overconfidence or lack of explainability and robustness of deep neural networks, albeit one that is often computationally expensive. Many…

Medical image segmentation is crucial for disease diagnosis and monitoring. Though effective, the current segmentation networks such as UNet struggle with capturing long-range features. More accurate models such as TransUNet, Swin-UNet, and…

Segmentation is one of the most significant steps in image processing. Segmenting an image is a technique that makes it possible to separate a digital image into various areas based on the different characteristics of pixels in the image.…

Referring image segmentation aims to segment an object referred to by natural language expression from an image. The primary challenge lies in the efficient propagation of fine-grained semantic information from textual features to visual…

We propose the Topology-Preserving Segmentation Network, a deformation-based model that can extract objects in an image while maintaining their topological properties. This network generates segmentation masks that have the same topology as…

Hyperspectral images (HSIs) contain rich spectral and spatial information. Motivated by the success of transformers in the field of natural language processing and computer vision where they have shown the ability to learn long range…

Long-term weather forecasting is critical for socioeconomic planning and disaster preparedness. While recent approaches employ finetuning to extend prediction horizons, they remain constrained by the issues of catastrophic forgetting, error…

Automatic image cropping is a method for maximizing the human-perceived quality of cropped regions in photographs. Although several works have proposed techniques for producing singular crops, little work has addressed the problem of…

Moving object segmentation (MOS) in dynamic scenes is an important, challenging, but under-explored research topic for autonomous driving, especially for sequences obtained from moving ego vehicles. Most segmentation methods leverage motion…

Hair artifacts in dermoscopic images present significant challenges for accurate skin lesion analysis, potentially obscuring critical diagnostic features in dermatological assessments. This work introduces a fine-tuned SegFormer model…

This paper presents CLUSTERFORMER, a universal vision model that is based on the CLUSTERing paradigm with TransFORMER. It comprises two novel designs: 1. recurrent cross-attention clustering, which reformulates the cross-attention mechanism…