Self-supervised learning (SSL) for WiFi-based human activity recognition
(HAR) holds great promise due to its ability to address the challenge of
insufficient labeled data. However, directly transplanting SSL algorithms,
especially contrastive learning, originally designed for other domains to CSI
data, often fails to achieve the expected performance. We attribute this issue
to the inappropriate alignment criteria, which disrupt the semantic distance
consistency between the feature space and the input space. To address this
challenge, we introduce \textbf{A}netenna \textbf{R}esponse
\textbf{C}onsistency (ARC) as a solution to define proper alignment criteria.
ARC is designed to retain semantic information from the input space while
introducing robustness to real-world noise. We analyze ARC from the perspective
of CSI data structure, demonstrating that its optimal solution leads to a
direct mapping from input CSI data to action vectors in the feature map.
Furthermore, we provide extensive experimental evidence to validate the
effectiveness of ARC in improving the performance of self-supervised learning
for WiFi-based HAR.

通过引入 Anetenna Response Consistency (ARC) 作为解决方案来定义适当的对准准则，本研究分析了 ARC 的 CSI 数据结构视角，并且通过提供大量的实验证据来验证 ARC 在提高基于 WiFi 的自监督学习在人类活动识别中的性能方面的有效性。

利用天线响应一致性来定义 CSI 数据的对准标准

Exploit the antenna response consistency to define the alignment  criteria for CSI data

A long-held objective in AI is to build systems that understand concepts in a
humanlike way. Setting aside the difficulty of building such a system, even
trying to evaluate one is a challenge, due to present-day AI's relative opacity
and its proclivity for finding shortcut solutions. This is exacerbated by
humans' tendency to anthropomorphize, assuming that a system that can recognize
one instance of a concept must also understand other instances, as a human
would. In this paper, we argue that understanding a concept requires the
ability to use it in varied contexts. Accordingly, we propose systematic
evaluations centered around concepts, by probing a system's ability to use a
given concept in many different instantiations. We present case studies of such
an evaluations on two domains -- RAVEN (inspired by Raven's Progressive
Matrices) and the Abstraction and Reasoning Corpus (ARC) -- that have been used
to develop and assess abstraction abilities in AI systems. Our concept-based
approach to evaluation reveals information about AI systems that conventional
test sets would have left hidden.

本文提出了一种基于概念的评估方法，通过探究一个系统在多个实例中应用给定概念的能力来评估。作者以 RAVEN 和 ARC 为例进行了案例研究。研究发现，这种基于概念的评估方法揭示了传统测试集所隐藏的 AI 系统的信息。

评估概念抽象基准的理解能力

Evaluating Understanding on Conceptual Abstraction Benchmarks

We study the problem of learning the structure of an optimal Bayesian network
when additional constraints are posed on the network or on its moralized graph.
More precisely, we consider the constraint that the network or its moralized
graph are close, in terms of vertex or edge deletions, to a sparse graph class
$\Pi$. For example, we show that learning an optimal network whose moralized
graph has vertex deletion distance at most $k$ from a graph with maximum degree
1 can be computed in polynomial time when $k$ is constant. This extends
previous work that gave an algorithm with such a running time for the vertex
deletion distance to edgeless graphs [Korhonen & Parviainen, NIPS 2015]. We
then show that further extensions or improvements are presumably impossible.
For example, we show that learning optimal networks where the network or its
moralized graph have maximum degree $2$ or connected components of size at most
$c$, $c\ge 3$, is NP-hard. Finally, we show that learning an optimal network
with at most $k$ edges in the moralized graph presumably has no $f(k)\cdot
|I|^{O(1)}$-time algorithm and that, in contrast, an optimal network with at
most $k$ arcs can be computed in $2^{O(k)}\cdot |I|^{O(1)}$ time where $|I|$ is
the total input size.

本文研究在给定的约束条件下，学习最优贝叶斯网络的结构，其中最大程度为 1 的边界至少有距离 k，最大程度为 2 的边界以及具有大小至多为 c（c≥3）的连通分量的网络或其模糊化图的学习被证明是 NP 困难的，而在模糊化图中最多具有 k 个弧可以在两个范围内得到解决：O (k)*|I | 或 2^O (k)*|I|。

稀疏约束下的贝叶斯网络学习：参数化复杂度分析

Learning Bayesian Networks Under Sparsity Constraints: A Parameterized  Complexity Analysis

Leveraging synthetically rendered data offers great potential to improve
monocular depth estimation and other geometric estimation tasks, but closing
the synthetic-real domain gap is a non-trivial and important task. While much
recent work has focused on unsupervised domain adaptation, we consider a more
realistic scenario where a large amount of synthetic training data is
supplemented by a small set of real images with ground-truth. In this setting,
we find that existing domain translation approaches are difficult to train and
offer little advantage over simple baselines that use a mix of real and
synthetic data. A key failure mode is that real-world images contain novel
objects and clutter not present in synthetic training. This high-level domain
shift isn't handled by existing image translation models.
Based on these observations, we develop an attention module that learns to
identify and remove difficult out-of-domain regions in real images in order to
improve depth prediction for a model trained primarily on synthetic data. We
carry out extensive experiments to validate our attend-remove-complete approach
(ARC) and find that it significantly outperforms state-of-the-art domain
adaptation methods for depth prediction. Visualizing the removed regions
provides interpretable insights into the synthetic-real domain gap.

通过注意力模块，学习识别和去除真实图像中的困难部分，以提高合成数据训练的模型对真实图像的景深估计。