Related papers: GeoContrastNet: Contrastive Key-Value Edge Learnin…

This paper presents a novel attention-based neural network for structured reconstruction, which takes a 2D raster image as an input and reconstructs a planar graph depicting an underlying geometric structure. The approach detects corners…

The recent advent of self-supervised pre-training techniques has led to a surge in the use of multimodal learning in form document understanding. However, existing approaches that extend the mask language modeling to other modalities…

Contrastive learning has been widely applied to graph representation learning, where the view generators play a vital role in generating effective contrastive samples. Most of the existing contrastive learning methods employ pre-defined…

We present a deep learning framework for accurate visual correspondences and demonstrate its effectiveness for both geometric and semantic matching, spanning across rigid motions to intra-class shape or appearance variations. In contrast to…

We propose a method for self-supervised image representation learning under the guidance of 3D geometric consistency. Our intuition is that 3D geometric consistency priors such as smooth regions and surface discontinuities may imply…

Graph representation learning has achieved notable success in encoding graph-structured data into latent vector spaces, enabling a wide range of downstream tasks. However, these node representations remain opaque and difficult to interpret.…

Heterogeneous graph neural networks (HGNNs) have significantly propelled the information retrieval (IR) field. Still, the effectiveness of HGNNs heavily relies on high-quality labels, which are often expensive to acquire. This challenge has…

Geometric deep learning enables the encoding of physical symmetries in modeling 3D objects. Despite rapid progress in encoding 3D symmetries into Graph Neural Networks (GNNs), a comprehensive evaluation of the expressiveness of these…

Accurate and robust image-based geo-localization at a global scale is challenging due to diverse environments, visually ambiguous scenes, and the lack of distinctive landmarks in many regions. While contrastive learning methods show…

Recently, heterogeneous Graph Neural Networks (GNNs) have become a de facto model for analyzing HGs, while most of them rely on a relative large number of labeled data. In this work, we investigate Contrastive Learning (CL), a key component…

Point cloud semantic segmentation from projected views, such as range-view (RV) and bird's-eye-view (BEV), has been intensively investigated. Different views capture different information of point clouds and thus are complementary to each…

Unsupervised learning has recently made exceptional progress because of the development of more effective contrastive learning methods. However, CNNs are prone to depend on low-level features that humans deem non-semantic. This dependency…

Recently, structure-text contrastive learning has shown promising performance on text-attributed graphs by leveraging the complementary strengths of graph neural networks and language models. However, existing methods typically rely on…

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…

Remote sensing segmentation has a wide range of applications in environmental protection, and urban change detection, etc. Despite the success of deep learning-based remote sensing segmentation methods (e.g., CNN and Transformer), they are…

Relational Deep Learning (RDL) is an emerging paradigm that leverages Graph Neural Network principles to learn directly from relational databases by representing them as heterogeneous graphs. However, existing RDL models typically rely on…

Although graph neural networks (GNNs) have achieved impressive achievements in graph classification, they often need abundant task-specific labels, which could be extensively costly to acquire. A credible solution is to explore additional…

Many large-scale knowledge graphs are now available and ready to provide semantically structured information that is regarded as an important resource for question answering and decision support tasks. However, they are built on rigid…

Unsupervised domain adaptation (UDA) has shown remarkable results in bearing fault diagnosis under changing working conditions in recent years. However, most UDA methods do not consider the geometric structure of the data. Furthermore, the…

Pursuing realistic results according to human visual perception is the central concern in the image transformation tasks. Perceptual learning approaches like perceptual loss are empirically powerful for such tasks but they usually rely on…