Related papers: TOV: The Original Vision Model for Optical Remote …

Vision Transformers (ViTs) with self-attention modules have recently achieved great empirical success in many vision tasks. Due to non-convex interactions across layers, however, theoretical learning and generalization analysis is mostly…

Semantic segmentation of remote sensing (RS) images is a challenging yet essential task with broad applications. While deep learning, particularly supervised learning with large-scale labeled datasets, has significantly advanced this field,…

In defense-related remote sensing applications, such as vehicle detection on satellite imagery, supervised learning requires a huge number of labeled examples to reach operational performances. Such data are challenging to obtain as it…

Learning general-purpose representations from multisensor data produced by the omnipresent sensing systems (or IoT in general) has numerous applications in diverse use cases. Existing purely supervised end-to-end deep learning techniques…

One-shot Imitation Learning~(OSIL) aims to imbue AI agents with the ability to learn a new task from a single demonstration. To supervise the learning, OSIL typically requires a prohibitively large number of paired expert demonstrations --…

Visible and infrared image fusion (VIF) has gained significant attention in recent years due to its wide application in tasks such as scene segmentation and object detection. VIF methods can be broadly classified into traditional VIF…

Self-supervised learning (SSL) has emerged as a promising paradigm for addressing the annotation bottleneck in medical imaging by learning representations from unlabeled data. However, its effectiveness depends heavily on the design of the…

Recently, deep learning has experienced rapid expansion, contributing significantly to the progress of supervised learning methodologies. However, acquiring labeled data in real-world settings can be costly, labor-intensive, and sometimes…

Human-centric visual analysis plays a pivotal role in diverse applications, including surveillance, healthcare, and human-computer interaction. With the emergence of large-scale unlabeled human image datasets, there is an increasing need…

The remote sensing image intelligence understanding model is undergoing a new profound paradigm shift which has been promoted by multi-modal large language model (MLLM), i.e. from the paradigm learning a domain model (LaDM) shifts to…

With Transformers achieving outstanding performance on individual remote sensing (RS) tasks, we are now approaching the realization of a unified model that excels across multiple tasks through multi-task learning (MTL). Compared to…

Large-scale labeled data are generally required to train deep neural networks in order to obtain better performance in visual feature learning from images or videos for computer vision applications. To avoid extensive cost of collecting and…

Human-centric visual tasks have attracted increasing research attention due to their widespread applications. In this paper, we aim to learn a general human representation from massive unlabeled human images which can benefit downstream…

Since we can leverage a large amount of unlabeled data without any human supervision to train a model and transfer the knowledge to target tasks, self-supervised learning is a de-facto component for the recent success of deep learning in…

Wildlife re-identification aims to match individuals of the same species across different observations. Current state-of-the-art (SOTA) models rely on class labels to train supervised models for individual classification. This dependence on…

Despite the promising progress made in recent years, person re-identification (re-ID) remains a challenging task due to the complex variations in human appearances from different camera views. For this challenging problem, a large variety…

Remote sensing visual grounding (RSVG) aims to localize objects in remote sensing images based on free-form natural language expressions. Existing approaches are typically constrained to closed-set vocabularies, limiting their applicability…

Self-Supervised Learning (SSL) is a reliable learning mechanism in which a robot uses an original, trusted sensor cue for training to recognize an additional, complementary sensor cue. We study for the first time in SSL how a robot's…

Remote Sensing Vision-Language Models (RS VLMs) have made much progress in the tasks of remote sensing (RS) image comprehension. While performing well in multi-modal reasoning and multi-turn conversations, the existing models lack…

Deep learning models for non-intrusive load monitoring (NILM) tend to require a large amount of labeled data for training. However, it is difficult to generalize the trained models to unseen sites due to different load characteristics and…