相关论文: Homeomorphism Prior for False Positive and Negativ…

Recently, self-supervised methods show remarkable achievements in image-level representation learning. Nevertheless, their image-level self-supervisions lead the learned representation to sub-optimal for dense prediction tasks, such as…

Many contrastive representation learning methods learn a single global representation of an entire image. However, dense contrastive representation learning methods such as DenseCL (Wang et al., 2021) can learn better representations for…

Deformable shape representations, parameterized by deformations relative to a given template, have proven effective for improved image analysis tasks. However, their broader applicability is hindered by two major challenges. First, existing…

Well-annotated medical datasets enable deep neural networks (DNNs) to gain strong power in extracting lesion-related features. Building such large and well-designed medical datasets is costly due to the need for high-level expertise. Model…

Purpose: Deformable Image Registration (DIR) can benefit from additional guidance using corresponding landmarks in the images. However, the benefits thereof are largely understudied, especially due to the lack of automatic landmark…

Dense correspondence across semantically related images has been extensively studied, but still faces two challenges: 1) large variations in appearance, scale and pose exist even for objects from the same category, and 2) labeling…

Dense prediction tasks such as segmentation and detection of pathological entities hold crucial clinical value in computational pathology workflows. However, obtaining dense annotations on large cohorts is usually tedious and expensive.…

Learning inter-image similarity is crucial for 3D medical images self-supervised pre-training, due to their sharing of numerous same semantic regions. However, the lack of the semantic prior in metrics and the semantic-independent variation…

Recently many efforts have been devoted to applying graph neural networks (GNNs) to molecular property prediction which is a fundamental task for computational drug and material discovery. One of major obstacles to hinder the successful…

Satellite imagery is being leveraged for many societally critical tasks across climate, economics, and public health. Yet, because of heterogeneity in landscapes (e.g. how a road looks in different places), models can show disparate…

This paper addresses the problem of determining dense pixel correspondences between two images and its application to geometric correspondence verification in image retrieval. The main contribution is a geometric correspondence verification…

In this paper, we address the problem of building dense correspondences between human images under arbitrary camera viewpoints and body poses. Prior art either assumes small motion between frames or relies on local descriptors, which cannot…

Contrastive learning has achieved great success in skeleton-based representation learning recently. However, the prevailing methods are predominantly negative-based, necessitating additional momentum encoder and memory bank to get negative…

Learning scientific document representations can be substantially improved through contrastive learning objectives, where the challenge lies in creating positive and negative training samples that encode the desired similarity semantics.…

We propose a Deep learning-based weak label learning method for analyzing whole slide images (WSIs) of Hematoxylin and Eosin (H&E) stained tumor tissue not requiring pixel-level or tile-level annotations using Self-supervised pre-training…

Self-supervised representation learning for visual pre-training has achieved remarkable success with sample (instance or pixel) discrimination and semantics discovery of instance, whereas there still exists a non-negligible gap between…

Establishing dense anatomical correspondence across distinct imaging modalities is a foundational yet challenging procedure for numerous medical image analysis studies and image-guided radiotherapy. Existing multi-modality image…

In this work we use deep learning to establish dense correspondences between a 3D object model and an image "in the wild". We introduce "DenseReg", a fully-convolutional neural network (F-CNN) that densely regresses at every foreground…

High-resolution (HR) magnetic resonance images (MRI) provide detailed anatomical information important for clinical application and quantitative image analysis. However, HR MRI conventionally comes at the cost of longer scan time, smaller…

Deep clustering has shown its promising capability in joint representation learning and clustering via deep neural networks. Despite the significant progress, the existing deep clustering works mostly utilize some distribution-based…