GeoNet is a recently proposed domain adaptation benchmark consisting of three
challenges (i.e., GeoUniDA, GeoImNet, and GeoPlaces). Each challenge contains
images collected from the USA and Asia where there are huge geographical gaps.
Our solution adopts a two-stage source-free domain adaptation framework with a
Swin Transformer backbone to achieve knowledge transfer from the USA (source)
domain to Asia (target) domain. In the first stage, we train a source model
using labeled source data with a re-sampling strategy and two types of
cross-entropy loss. In the second stage, we generate pseudo labels for
unlabeled target data to fine-tune the model. Our method achieves an H-score of
74.56% and ultimately ranks 1st in the GeoUniDA challenge. In GeoImNet and
GeoPlaces challenges, our solution also reaches a top-3 accuracy of 64.46% and
51.23%, respectively.

GeoNet 是一个最近提出的领域适应基准测试，它包含三个挑战（即 GeoUniDA，GeoImNet 和 GeoPlaces）。我们的解决方案采用了两阶段的无源领域适应框架，使用 Swin Transformer 骨干网络实现了从美国（源）领域到亚洲（目标）领域的知识转移。我们的方法在 GeoUniDA 挑战中取得了 74.56％的 H 分数，最终排名第一。在 GeoImNet 和 GeoPlaces 挑战中，我们的解决方案也分别达到了 64.46％和 51.23％的前三准确率。

ICCV 2023 GeoNet 挑战赛的自训练解决方案

Self-training solutions for the ICCV 2023 GeoNet Challenge

Optimal transport (OT) offers a versatile framework to compare complex data
distributions in a geometrically meaningful way. Traditional methods for
computing the Wasserstein distance and geodesic between probability measures
require mesh-dependent domain discretization and suffer from the
curse-of-dimensionality. We present GeONet, a mesh-invariant deep neural
operator network that learns the non-linear mapping from the input pair of
initial and terminal distributions to the Wasserstein geodesic connecting the
two endpoint distributions. In the offline training stage, GeONet learns the
saddle point optimality conditions for the dynamic formulation of the OT
problem in the primal and dual spaces that are characterized by a coupled PDE
system. The subsequent inference stage is instantaneous and can be deployed for
real-time predictions in the online learning setting. We demonstrate that
GeONet achieves comparable testing accuracy to the standard OT solvers on a
simulation example and the CIFAR-10 dataset with considerably reduced
inference-stage computational cost by orders of magnitude.

GeONet 是一个适用于实时预测的深度神经网络，它通过学习非线性映射来连接 Wasserstein 距离和 geodesic，从而比传统的基于网格的方法具有更高的准确性和更少的计算成本。

GeONet: 用于学习 Wasserstein 测地线的神经算子

GeONet: a neural operator for learning the Wasserstein geodesic

Surface-based geodesic topology provides strong cues for object semantic
analysis and geometric modeling. However, such connectivity information is lost
in point clouds. Thus we introduce GeoNet, the first deep learning architecture
trained to model the intrinsic structure of surfaces represented as point
clouds. To demonstrate the applicability of learned geodesic-aware
representations, we propose fusion schemes which use GeoNet in conjunction with
other baseline or backbone networks, such as PU-Net and PointNet++, for
down-stream point cloud analysis. Our method improves the state-of-the-art on
multiple representative tasks that can benefit from understandings of the
underlying surface topology, including point upsampling, normal estimation,
mesh reconstruction and non-rigid shape classification.

GeoNet 是第一个深度学习结构用于对点云表达的曲面的内在结构建模，通过使用 GeoNet 与 PU-Net 和 PointNet ++ 等基线或骨干网络的融合方案来改善多个代表性任务的现有方法，包括点上采样、法向量估计、网格重建和非刚性形状分类。

GeoNet: 基于深度测地线网络的点云分析

GeoNet: Deep Geodesic Networks for Point Cloud Analysis

We propose GeoNet, a jointly unsupervised learning framework for monocular
depth, optical flow and ego-motion estimation from videos. The three components
are coupled by the nature of 3D scene geometry, jointly learned by our
framework in an end-to-end manner. Specifically, geometric relationships are
extracted over the predictions of individual modules and then combined as an
image reconstruction loss, reasoning about static and dynamic scene parts
separately. Furthermore, we propose an adaptive geometric consistency loss to
increase robustness towards outliers and non-Lambertian regions, which resolves
occlusions and texture ambiguities effectively. Experimentation on the KITTI
driving dataset reveals that our scheme achieves state-of-the-art results in
all of the three tasks, performing better than previously unsupervised methods
and comparably with supervised ones.

本文提出了 GeoNet，这是一个基于联合无监督学习的框架，可用于从视频中估计单眼深度、光流和 Ego-motion。基于 3D 场景几何关系，由我们的框架以端到端的方式联合学习。实验结果表明，在 KITTI 驾驶数据集中，我们的方法在三个任务中均取得了最先进的成果，优于以前的无监督方法，并与受监督方法相当。