Tuning CLD Maps

Mapping Images with the Coherence Length Diagrams

Statistical pattern recognition methods based on the Coherence Length Diagram (CLD) have been proposed for medical image analyses, such as quantitative characterisation of human skin textures, and for polarized light microscopy of liquid crystal textures. Further investigations are made on image maps originated from such diagram and some examples related to irregularity of microstructures are shown.

Recovering Detail in 3D Shapes Using Disparity Maps

We present a fine-tuning method to improve the appearance of 3D geometries reconstructed from single images. We leverage advances in monocular depth estimation to obtain disparity maps and present a novel approach to transforming 2D normalized disparity maps into 3D point clouds by using shape priors to solve an optimization on the relevant camera parameters. After creating a 3D point cloud from disparity, we introduce a method to combine the new point cloud with existing information to form a more faithful and detailed final geometry. We demonstrate the efficacy of our approach with multiple …

WTF？！基于Wasserstein倾斜流映射的无模拟强化学习

WTF?! Simulation-Free Reinforcement Learning with Wasserstein-Tilted Flow Maps

本文提出WTF框架，通过最优传输正则化将奖励微调转化为确定性最优控制问题，实现无模拟强化学习，在少步推理下提升奖励并减少280倍训练计算。

仅从一张地图学习实现连续历史地图的语义分割

Semantic Segmentation for Sequential Historical Maps by Learning from Only One Map

本文针对历史地图数字化中标注稀缺问题，提出弱监督年龄追踪策略，利用相邻时期地图相似性生成伪标签进行微调，在Hameln数据集上mIoU达77.3%，较基线提升约20%。

RADAM: Texture Recognition through Randomized Aggregated Encoding of Deep Activation Maps

Texture analysis is a classical yet challenging task in computer vision for which deep neural networks are actively being applied. Most approaches are based on building feature aggregation modules around a pre-trained backbone and then fine-tuning the new architecture on specific texture recognition tasks. Here we propose a new method named \textbf{R}andom encoding of \textbf{A}ggregated \textbf{D}eep \textbf{A}ctivation \textbf{M}aps (RADAM) which extracts rich texture representations without ever changing the backbone. The technique consists of encoding the output at different depths of a pr…

道路车道线测绘的进展：基于航空影像的深度学习语义分割方法的微调对比分析

Advancements in Road Lane Mapping: Comparative Fine-Tuning Analysis of Deep Learning-based Semantic Segmentation Methods Using Aerial Imagery

本研究比较了十二种深度学习语义分割模型在部分标注数据集下的迁移学习性能，发现基于Transformer的模型优于卷积神经网络，微调后显著提升了从航空影像提取道路车道线的性能，对自动驾驶HD地图开发具有重要意义。