Related papers: SCPNet: Unsupervised Cross-modal Homography Estima…
Camouflaged object detection segments objects with intrinsic similarity and edge disruption. Current detection methods rely on accumulated complex components. Each approach adds components such as boundary modules, attention mechanisms, and…
The joint hyperspectral image (HSI) and LiDAR data classification aims to interpret ground objects at more detailed and precise level. Although deep learning methods have shown remarkable success in the multisource data classification task,…
Image inpainting aims to repair a partially damaged image based on the information from known regions of the images. \revise{Achieving semantically plausible inpainting results is particularly challenging because it requires the…
A road is the skeleton of a city and is a fundamental and important geographical component. Currently, many countries have built geo-information databases and gathered large amounts of geographic data. However, with the extensive…
Few-Shot Remote Sensing Scene Classification (FSRSSC) is an important task, which aims to recognize novel scene classes with few examples. Recently, several studies attempt to address the FSRSSC problem by following few-shot natural image…
Point cloud completion is essential for robotic perception, object reconstruction and supporting downstream tasks like grasp planning, obstacle avoidance, and manipulation. However, incomplete geometry caused by self-occlusion and sensor…
The human brain exhibits a strong ability to spontaneously associate different visual attributes of the same or similar visual scene, such as associating sketches and graffiti with real-world visual objects, usually without supervising…
We present a novel clustering objective that learns a neural network classifier from scratch, given only unlabelled data samples. The model discovers clusters that accurately match semantic classes, achieving state-of-the-art results in…
Compressed sensing (CS) is a promising tool for reducing sampling costs. Current deep neural network (NN)-based CS methods face the challenges of collecting labeled measurement-ground truth (GT) data and generalizing to real applications.…
Multimodal learning leverages complementary information derived from different modalities, thereby enhancing performance in medical image segmentation. However, prevailing multimodal learning methods heavily rely on extensive well-annotated…
Homography estimation is a basic computer vision task, which aims to obtain the transformation from multi-view images for image alignment. Unsupervised learning homography estimation trains a convolution neural network for feature…
Deep network-based image Compressed Sensing (CS) has attracted much attention in recent years. However, the existing deep network-based CS schemes either reconstruct the target image in a block-by-block manner that leads to serious block…
Self-supervised heterogeneous graph learning (SHGL) has shown promising potential in diverse scenarios. However, while existing SHGL methods share a similar essential with clustering approaches, they encounter two significant limitations:…
The presence of non-homogeneous haze can cause scene blurring, color distortion, low contrast, and other degradations that obscure texture details. Existing homogeneous dehazing methods struggle to handle the non-uniform distribution of…
Accurate automatic medical image segmentation relies on high-quality, dense annotations, which are costly and time-consuming. Weakly supervised learning provides a more efficient alternative by leveraging sparse and coarse annotations…
We present a novel method for computing correspondences across 3D shapes using unsupervised learning. Our method computes a non-linear transformation of given descriptor functions, while optimizing for global structural properties of the…
We study the task of semantic mapping - specifically, an embodied agent (a robot or an egocentric AI assistant) is given a tour of a new environment and asked to build an allocentric top-down semantic map ("what is where?") from egocentric…
In this paper, we propose an iterative framework, which consists of two phases: a generation phase and a training phase, to generate realistic training data and yield a supervised homography network. In the generation phase, given an…
Heterogeneous graph neural network (HGNN) is a very popular technique for the modeling and analysis of heterogeneous graphs. Most existing HGNN-based approaches are supervised or semi-supervised learning methods requiring graphs to be…
In this paper we propose a highly scalable convolutional neural network, end-to-end trainable, for real-time 3D human pose regression from still RGB images. We call this approach the Scalable Sequential Pyramid Networks (SSP-Net) as it is…