Search Results for author:
Found 16 papers, 5 papers with code
AgMTR: Agent Mining Transformer for Few-shot Segmentation in Remote Sensing
At this point, different query pixels can selectively aggregate the fine-grained local semantics of different agents, thereby enhancing the semantic clarity between query FG and BG pixels.
RingMo-Aerial: An Aerial Remote Sensing Foundation Model With A Affine Transformation Contrastive Learning
Furthermore, the ARS-Adapter, an efficient parameter fine-tuning method, is proposed to improve the model's adaptability and effectiveness in various ARS vision tasks.
Prompt-and-Transfer: Dynamic Class-aware Enhancement for Few-shot Segmentation
For more efficient generalization to unseen domains (classes), most Few-shot Segmentation (FSS) would directly exploit pre-trained encoders and only fine-tune the decoder, especially in the current era of large models.
TAFormer: A Unified Target-Aware Transformer for Video and Motion Joint Prediction in Aerial Scenes
To address this issue, we introduce a novel task called Target-Aware Aerial Video Prediction, aiming to simultaneously predict future scenes and motion states of the target.
Self-guided Few-shot Semantic Segmentation for Remote Sensing Imagery Based on Large Vision Models
The Segment Anything Model (SAM) exhibits remarkable versatility and zero-shot learning abilities, owing largely to its extensive training data (SA-1B).
Not Just Learning from Others but Relying on Yourself: A New Perspective on Few-Shot Segmentation in Remote Sensing
In addition, to prevent the co-existence of multiple classes in remote sensing scenes from exacerbating the collapse of FSS generalization, we also propose a new Known-class Meta Suppressor (KMS) module to suppress the activation of known-class objects in the sample.
HeightFormer: A Multilevel Interaction and Image-adaptive Classification-regression Network for Monocular Height Estimation with Aerial Images
MIB supplements the fixed sample grid in CNN of the conventional backbone network with tokens of different interaction ranges.
Rethinking the Open-Loop Evaluation of End-to-End Autonomous Driving in nuScenes
Modern autonomous driving systems are typically divided into three main tasks: perception, prediction, and planning.
Ranked #1 on
Trajectory Planning
on nuScenes
OGMN: Occlusion-guided Multi-task Network for Object Detection in UAV Images
One interaction for the guide is between two task decoders to address the feature confusion problem, and an occlusion decoupling head (ODH) is proposed to replace the general detection head.
LIGHT: Joint Individual Building Extraction and Height Estimation from Satellite Images through a Unified Multitask Learning Network
Building extraction and height estimation are two important basic tasks in remote sensing image interpretation, which are widely used in urban planning, real-world 3D construction, and other fields.
Elevation Estimation-Driven Building 3D Reconstruction from Single-View Remote Sensing Imagery
Our Building3D is rooted in the SFFDE network for building elevation prediction, synchronized with a building extraction network for building masks, and then sequentially performs point cloud reconstruction, surface reconstruction (or CityGML model reconstruction).
Breaking Immutable: Information-Coupled Prototype Elaboration for Few-Shot Object Detection
Few-shot object detection, expecting detectors to detect novel classes with a few instances, has made conspicuous progress.
Learning to Evaluate Performance of Multi-modal Semantic Localization
Finally, we analyze the SeLo performance of RS cross-modal retrieval models in detail, explore the impact of different variables on this task, and provide a complete benchmark for the SeLo task.
Bidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud Scenes
With prototype-to-point globalization (Pr2PoG), the global perception is embedded to local point features based on similarity weights from sparse prototypes to dense point features.
Beyond single receptive field: A receptive field fusion-and-stratification network for airborne laser scanning point cloud classification
With receptive field fusion-and-stratification, RFFS-Net is more adaptable to the classification of regions with complex structures and extreme scale variations in large-scale ALS point clouds.
Semantic Segmentation for Point Cloud Scenes via Dilated Graph Feature Aggregation and Pyramid Decoders
Due to the unicity of receptive field, semantic segmentation of point clouds remains challenging for the expression of multi-receptive field features, which brings about the misclassification of instances with similar spatial structures.
