Related papers: SDPL: Shifting-Dense Partition Learning for UAV-Vi…
This paper describes an effective and efficient image classification framework nominated distributed deep representation learning model (DDRL). The aim is to strike the balance between the computational intensive deep learning approaches…
Subspace clustering techniques have shown promise in hyperspectral image segmentation. The fundamental assumption in subspace clustering is that the samples belonging to different clusters/segments lie in separable subspaces. What if this…
Recent advances in image-level self-supervised learning (SSL) have made significant progress, yet learning dense representations for patches remains challenging. Mainstream methods encounter an over-dispersion phenomenon that patches from…
Self-supervised learning (SSL) has made enormous progress and largely narrowed the gap with the supervised ones, where the representation learning is mainly guided by a projection into an embedding space. During the projection, current…
Supervised deep learning models depend on massive labeled data. Unfortunately, it is time-consuming and labor-intensive to collect and annotate bitemporal samples containing desired changes. Transfer learning from pre-trained models is…
Accurate semantic segmentation of remote sensing imagery is critical for various Earth observation applications, such as land cover mapping, urban planning, and environmental monitoring. However, individual data sources often present…
Decentralized training enables learning with distributed datasets generated at different locations without relying on a central server. In realistic scenarios, the data distribution across these sparsely connected learning agents can be…
We propose a lightweight and scalable Regional Point-Language Contrastive learning framework, namely \textbf{RegionPLC}, for open-world 3D scene understanding, aiming to identify and recognize open-set objects and categories. Specifically,…
Camera localization is a classical computer vision task that serves various Artificial Intelligence and Robotics applications. With the rapid developments of Deep Neural Networks (DNNs), end-to-end visual localization methods are prosperous…
Semi-supervised learning (SSL), thanks to the significant reduction of data annotation costs, has been an active research topic for large-scale 3D scene understanding. However, the existing SSL-based methods suffer from severe training…
Semi-supervised continual learning (SSCL) seeks to leverage both labeled and unlabeled data in a sequential learning setup, aiming to reduce annotation costs while managing continual data arrival. SSCL introduces complex challenges,…
The goal of moving object segmentation is separating moving objects from stationary backgrounds in videos. One major challenge in this problem is how to develop a universal model for videos from various natural scenes since previous methods…
Aiming at improving performance of visual classification in a cost-effective manner, this paper proposes an incremental semi-supervised learning paradigm called Deep Co-Space (DCS). Unlike many conventional semi-supervised learning methods…
The large variation of viewpoint and irrelevant content around the target always hinder accurate image retrieval and its subsequent tasks. In this paper, we investigate an extremely challenging task: given a ground-view image of a landmark,…
Automatic airplane detection in aerial imagery has a variety of applications. Two of the significant challenges in this task are variations in the scale and direction of the airplanes. To solve these challenges, we present a…
Learning discriminative representations is a central goal of supervised deep learning. While cross-entropy (CE) remains the dominant objective for classification, it does not explicitly enforce desirable geometric properties in the…
Prompt learning has emerged as an efficient and effective approach for transferring foundational Vision-Language Models (e.g., CLIP) to downstream tasks. However, current methods tend to overfit to seen categories, thereby limiting their…
Classical pixel-based Visual Servoing (VS) approaches offer high accuracy but suffer from a limited convergence area due to optimization nonlinearity. Modern deep learning-based VS methods overcome traditional vision issues but lack…
It has been widely recognized that the success of deep learning in image segmentation relies overwhelmingly on a myriad amount of densely annotated training data, which, however, are difficult to obtain due to the tremendous labor and…
In this paper we propose novel Deformable Part Networks (DPNs) to learn {\em pose-invariant} representations for 2D object recognition. In contrast to the state-of-the-art pose-aware networks such as CapsNet \cite{sabour2017dynamic} and STN…