Search Results for author:
Found 31 papers, 13 papers with code
Towards Efficient Model-Heterogeneity Federated Learning for Large Models
As demand grows for complex tasks and high-performance applications in edge computing, the deployment of large models in federated learning has become increasingly urgent, given their superior representational power and generalization capabilities.
Towards Accurate and Efficient Sub-8-Bit Integer Training
Our integer training framework includes two components: ShiftQuant to realize accurate gradient estimation, and L1 normalization to smoothen the loss landscape.
SeaDATE: Remedy Dual-Attention Transformer with Semantic Alignment via Contrast Learning for Multimodal Object Detection
Multimodal object detection leverages diverse modal information to enhance the accuracy and robustness of detectors.
FusionSAM: Latent Space driven Segment Anything Model for Multimodal Fusion and Segmentation
In this paper, we introduce SAM into multimodal image segmentation for the first time, proposing a novel framework that combines Latent Space Token Generation (LSTG) and Fusion Mask Prompting (FMP) modules to enhance SAM's multimodal fusion and segmentation capabilities.
Reducing Spurious Correlation for Federated Domain Generalization
To comprehensively address this challenge, we introduce FedCD (Cross-Domain Invariant Federated Learning), an overall optimization framework at both the local and global levels.
FoRA: Low-Rank Adaptation Model beyond Multimodal Siamese Network
In this paper, we propose a novel multimodal object detector, named Low-rank Modal Adaptors (LMA) with a shared backbone.
Hyperspectral Anomaly Detection with Self-Supervised Anomaly Prior
The majority of existing hyperspectral anomaly detection (HAD) methods use the low-rank representation (LRR) model to separate the background and anomaly components, where the anomaly component is optimized by handcrafted sparse priors (e. g., $\ell_{2, 1}$-norm).
Diffusion Models Meet Remote Sensing: Principles, Methods, and Perspectives
As a newly emerging advance in deep generative models, diffusion models have achieved state-of-the-art results in many fields, including computer vision, natural language processing, and molecule design.
E2E-MFD: Towards End-to-End Synchronous Multimodal Fusion Detection
Multimodal image fusion and object detection are crucial for autonomous driving.
Domain Adaptation for Large-Vocabulary Object Detectors
Large-vocabulary object detectors (LVDs) aim to detect objects of many categories, which learn super objectness features and can locate objects accurately while applied to various downstream data.
DA-BEV: Unsupervised Domain Adaptation for Bird's Eye View Perception
Camera-only Bird's Eye View (BEV) has demonstrated great potential in environment perception in a 3D space.
SwiMDiff: Scene-wide Matching Contrastive Learning with Diffusion Constraint for Remote Sensing Image
Effectively leveraging this data through self-supervised learning (SSL) is vital in the field of remote sensing.
Distribution-aware Interactive Attention Network and Large-scale Cloud Recognition Benchmark on FY-4A Satellite Image
Accurate cloud recognition and warning are crucial for various applications, including in-flight support, weather forecasting, and climate research.
Multimodal Informative ViT: Information Aggregation and Distribution for Hyperspectral and LiDAR Classification
Additionally, the information distribution flow (IDF) in MIVit enhances performance-awareness by distributing global classification information across different modalities' feature maps.
Exploring Hyperspectral Anomaly Detection with Human Vision: A Small Target Aware Detector
Our method provides a new solution space for HAD that is closer to human visual perception with high confidence.
JointSQ: Joint Sparsification-Quantization for Distributed Learning
In this paper we propose Joint Sparsification-Quantization (JointSQ) inspired by the discovery that sparsification can be treated as 0-bit quantization regardless of architectures.
RS-DGC: Exploring Neighborhood Statistics for Dynamic Gradient Compression on Remote Sensing Image Interpretation
The key component of RS-DGC is a Neighborhood Statistical Indicator (NSI), which can quantify the importance of gradients within a specified neighborhood on each node to sparsify the local gradients before gradient transmission in each iteration.
Multi-scale direction-aware SAR object detection network via global information fusion
Deep learning has driven significant progress in object detection using Synthetic Aperture Radar (SAR) imagery.
Physics Inspired Criterion for Pruning-Quantization Joint Learning
Pruning-quantization joint learning always facilitates the deployment of deep neural networks (DNNs) on resource-constrained edge devices.
Spanning Training Progress: Temporal Dual-Depth Scoring (TDDS) for Enhanced Dataset Pruning
Dataset pruning aims to construct a coreset capable of achieving performance comparable to the original, full dataset.
FedDiff: Diffusion Model Driven Federated Learning for Multi-Modal and Multi-Clients
With the rapid development of imaging sensor technology in the field of remote sensing, multi-modal remote sensing data fusion has emerged as a crucial research direction for land cover classification tasks.
MDFL: Multi-domain Diffusion-driven Feature Learning
High-dimensional images, known for their rich semantic information, are widely applied in remote sensing and other fields.
FedFusion: Manifold Driven Federated Learning for Multi-satellite and Multi-modality Fusion
Multi-satellite, multi-modality in-orbit fusion is a challenging task as it explores the fusion representation of complex high-dimensional data under limited computational resources.
BSDM: Background Suppression Diffusion Model for Hyperspectral Anomaly Detection
We present a novel solution BSDM (background suppression diffusion model) for HAD, which can simultaneously learn latent background distributions and generalize to different datasets for suppressing complex background.
Toward Stable, Interpretable, and Lightweight Hyperspectral Super-Resolution
Specifically, we create a positive cycle between fusion and degradation estimation under a new probabilistic framework.
Guided Hybrid Quantization for Object detection in Multimodal Remote Sensing Imagery via One-to-one Self-teaching
More concretely, we first design a structure called guided quantization self-distillation (GQSD), which is an innovative idea for realizing lightweight through the synergy of quantization and distillation.
Ranked #1 on
Object Detection
on VEDAI
SuperYOLO: Super Resolution Assisted Object Detection in Multimodal Remote Sensing Imagery
Furthermore, we design a simple and flexible SR branch to learn HR feature representations that can discriminate small objects from vast backgrounds with low-resolution (LR) input, thus further improving the detection accuracy.
Ranked #3 on
Object Detection
on VEDAI
Optical Remote Sensing Image Understanding with Weak Supervision: Concepts, Methods, and Perspectives
Therefore, remote sensing image understanding often faces the problems of incomplete, inexact, and inaccurate supervised information, which will affect the breadth and depth of remote sensing applications.
Transcoded Video Restoration by Temporal Spatial Auxiliary Network
In most video platforms, such as Youtube, and TikTok, the played videos usually have undergone multiple video encodings such as hardware encoding by recording devices, software encoding by video editing apps, and single/multiple video transcoding by video application servers.
Sparse Coding-inspired GAN for Weakly Supervised Hyperspectral Anomaly Detection
For solving these problems, this paper proposes a sparse coding-inspired generative adversarial network (GAN) for weakly supervised HAD, named sparseHAD.
MCM-aware Twin-least-square GAN for Hyperspectral Anomaly Detection
Hyperspectral anomaly detection under high-dimensional data and interference of deteriorated bands without any prior information has been challenging and attracted close attention in the exploration of the unknown in real scenarios.
