相关论文: Pattern Integration and Enhancement Vision Transfo…

Remote sensing projects typically generate large amounts of imagery that can be used to train powerful deep neural networks. However, the amount of labeled images is often small, as remote sensing applications generally require expert…

Vision Transformers (ViTs) have revolutionized computer vision by leveraging self-attention to model long-range dependencies. However, ViTs face challenges such as high computational costs due to the quadratic scaling of self-attention and…

Recent approaches have shown that training deep neural networks directly on large-scale image-text pair collections enables zero-shot transfer on various recognition tasks. One central issue is how this can be generalized to object…

The Vision Transformer (ViT) architecture has become widely recognized in computer vision, leveraging its self-attention mechanism to achieve remarkable success across various tasks. Despite its strengths, ViT's optimization remains…

Masked autoencoders are scalable vision learners, as the title of MAE \cite{he2022masked}, which suggests that self-supervised learning (SSL) in vision might undertake a similar trajectory as in NLP. Specifically, generative pretext tasks…

3D object representation learning is a fundamental challenge in computer vision to infer about the 3D world. Recent advances in deep learning have shown their efficiency in 3D object recognition, among which view-based methods have…

Self-supervised learning methods are gaining increasing traction in computer vision due to their recent success in reducing the gap with supervised learning. In natural language processing (NLP) self-supervised learning and transformers are…

Fine-grained visual categorization (FGVC) aims at recognizing objects from similar subordinate categories, which is challenging and practical for human's accurate automatic recognition needs. Most FGVC approaches focus on the attention…

Depth estimation, visual odometry (VO), and bird's-eye-view (BEV) scene layout estimation present three critical tasks for driving scene perception, which is fundamental for motion planning and navigation in autonomous driving. Though they…

The major drawbacks with Satellite Images are low resolution, Low resolution makes it difficult to identify the objects present in Satellite images. We have experimented with several deep models available for Single Image Superresolution on…

Advances in high resolution remote sensing image analysis are currently hampered by the difficulty of gathering enough annotated data for training deep learning methods, giving rise to a variety of small datasets and associated…

Semantic segmentation is essential for analyzing highdefinition remote sensing images (HRSIs) because it allows the precise classification of objects and regions at the pixel level. However, remote sensing data present challenges owing to…

In this work, we address the problem of cross-view geo-localization, which estimates the geospatial location of a street view image by matching it with a database of geo-tagged aerial images. The cross-view matching task is extremely…

Vision Transformer (ViT) has been widely used in computer vision tasks with excellent results by providing representations for a whole image or image patches. However, ViT lacks detailed localized image representations at arbitrary…

Remote sensing visual grounding (RSVG) aims to localize objects in remote sensing imagery according to natural language expressions. Previous methods typically rely on sentence-level vision-language alignment, which struggles to exploit…

In recent years, deep learning methods bring incredible progress to the field of object detection. However, in the field of remote sensing image processing, existing methods neglect the relationship between imaging configuration and…

The GelSight-like visual tactile (VT) sensor has gained popularity as a high-resolution tactile sensing technology for robots, capable of measuring touch geometry using a single RGB camera. However, the development of multi-modal perception…

Collecting large-scale medical datasets with fully annotated samples for training of deep networks is prohibitively expensive, especially for 3D volume data. Recent breakthroughs in self-supervised learning (SSL) offer the ability to…

This paper addresses the land cover classification task for remote sensing images by deep self-taught learning. Our self-taught learning approach learns suitable feature representations of the input data using sparse representation and…

This paper presents an innovative framework for remote sensing image analysis by fusing deep learning techniques, specifically Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks, with Geographic Information…