Related papers: PlankFormer: Robust Plankton Instance Segmentation…

Diffusion models have emerged as state-of-the-art generative methods for image synthesis, yet their potential as general-purpose feature encoders remains underexplored. Trained for denoising and generation without labels, they can be…

Polyp segmentation is still known as a difficult problem due to the large variety of polyp shapes, scanning and labeling modalities. This prevents deep learning model to generalize well on unseen data. However, Transformer-based approach…

Transformers have recently gained attention in the computer vision domain due to their ability to model long-range dependencies. However, the self-attention mechanism, which is the core part of the Transformer model, usually suffers from…

Universal Image Segmentation is not a new concept. Past attempts to unify image segmentation in the last decades include scene parsing, panoptic segmentation, and, more recently, new panoptic architectures. However, such panoptic…

In this paper, we aim to tackle the challenging few-shot segmentation task from a new perspective. Typical methods follow the paradigm to firstly learn prototypical features from support images and then match query features in pixel-level…

Instance segmentation of ships in synthetic aperture radar (SAR) imagery is critical for applications such as maritime monitoring, environmental analysis, and national security. SAR ship images present challenges including scale variation,…

We introduce CellSegmenter, a structured deep generative model and an amortized inference framework for unsupervised representation learning and instance segmentation tasks. The proposed inference algorithm is convolutional and…

Masked Autoencoders (MAEs) have been shown to be effective in pre-training Vision Transformers (ViTs) for natural and medical image analysis problems. By reconstructing missing pixel/voxel information in visible patches, a ViT encoder can…

Instance segmentation is a core computer vision task with great practical significance. Recent advances, driven by large-scale benchmark datasets, have yielded good general-purpose Convolutional Neural Network (CNN)-based methods. Natural…

Masked autoencoder (MAE) is a promising self-supervised pre-training technique that can improve the representation learning of a neural network without human intervention. However, applying MAE directly to volumetric medical images poses…

Planktonic organisms are of fundamental importance to marine ecosystems: they form the basis of the food web, provide the link between the atmosphere and the deep ocean, and influence global-scale biogeochemical cycles. Scientists are…

Oceans are the essential lifeblood of the Earth: they provide over 70% of the oxygen and over 97% of the water. Plankton and corals are two of the most fundamental components of ocean ecosystems, the former due to their function at many…

Autoencoders have been widely used for dimensional reduction and feature extraction. Various types of autoencoders have been proposed by introducing regularization terms. Most of these regularizations improve representation learning by…

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…

Current semantic segmentation models have achieved great success under the independent and identically distributed (i.i.d.) condition. However, in real-world applications, test data might come from a different domain than training data.…

Strong gravitational lensing can reveal the influence of dark-matter substructure in galaxies, but analyzing these effects from noisy, low-resolution images poses a significant challenge. In this work, we propose a masked autoencoder (MAE)…

Most recent transformer-based models show impressive performance on vision tasks, even better than Convolution Neural Networks (CNN). In this work, we present a novel, flexible, and effective transformer-based model for high-quality…

Recent transformer-based architectures have shown impressive results in the field of image segmentation. Thanks to their flexibility, they obtain outstanding performance in multiple segmentation tasks, such as semantic and panoptic, under a…

A major obstacle in instance segmentation is that existing methods often need many per-pixel labels in order to be effective. These labels require large human effort and for certain applications, such labels are not readily available. To…

Recently, a variety of vision transformers have been developed as their capability of modeling long-range dependency. In current transformer-based backbones for medical image segmentation, convolutional layers were replaced with pure…