CV - 计算机视觉 | ML - 机器学习 | RL - 强化学习 | NLP 自然语言处理
Subjects: cs.LG、cs.AI
1.Neuro Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept Rehearsal
标题：神经象征性的持续学习：知识、推理捷径和概念排练
作者：Emanuele Marconato, Gianpaolo Bontempo, Elisa Ficarra, Simone Calderara, Andrea Passerini, Stefano Teso
文章链接：https://arxiv.org/abs/2302.01242v1
项目代码：https://github.com/ema-marconato/nesy-cl
摘要：
我们引入了神经符号持续学习，在这种情况下，一个模型必须解决一连串的神经符号任务，也就是说，它必须将亚符号输入映射到高级概念，并通过与先前知识一致的推理来计算预测。我们的关键观察是，神经符号任务虽然不同，但往往共享概念，其语义随着时间的推移保持稳定。传统的方法有不足之处：现有的持续策略完全忽略了知识，而库存的神经符号架构则遭受了灾难性的遗忘。我们表明，通过将神经符号架构与持续策略相结合来利用先前的知识确实有助于避免灾难性遗忘，但这样做也会产生受推理捷径影响的模型。这些会破坏所获得的概念的语义，即使是在前期提供了详细的先验知识并且推理准确的情况下，也会反过来破坏持续的性能。为了克服这些问题，我们介绍了COOL，一个为神经符号持续问题量身定做的概念级持续学习策略，它可以获得高质量的概念并随着时间的推移记住它们。我们在三个新的基准上的实验强调了COOL是如何在其他策略失败的情况下在神经符号持续学习任务上获得持续的高性能。
We introduce Neuro-Symbolic Continual Learning, where a model has to solve a sequence of neuro-symbolic tasks, that is, it has to map sub-symbolic inputs to high-level concepts and compute predictions by reasoning consistently with prior knowledge. Our key observation is that neuro-symbolic tasks, although different, often share concepts whose semantics remains stable over time. Traditional approaches fall short: existing continual strategies ignore knowledge altogether, while stock neuro-symbolic architectures suffer from catastrophic forgetting. We show that leveraging prior knowledge by combining neuro-symbolic architectures with continual strategies does help avoid catastrophic forgetting, but also that doing so can yield models affected by reasoning shortcuts. These undermine the semantics of the acquired concepts, even when detailed prior knowledge is provided upfront and inference is exact, and in turn continual performance. To overcome these issues, we introduce COOL, a COncept-level cOntinual Learning strategy tailored for neuro-symbolic continual problems that acquires high-quality concepts and remembers them over time. Our experiments on three novel benchmarks highlights how COOL attains sustained high performance on neuro-symbolic continual learning tasks in which other strategies fail.
2.STEPS: Joint Self-supervised Nighttime Image Enhancement and Depth Estimation
标题：STEPS:联合自我监督的夜间图像增强和深度评估
作者：Yupeng Zheng, Chengliang Zhong, Pengfei Li, Huan-ang Gao, Yuhang Zheng, Bu Jin, Ling Wang, Hao Zhao, Guyue Zhou, Qichao Zhang, Dongbin Zhao
文章链接：https://arxiv.org/abs/2302.01334v1
项目代码：https://github.com/ucaszyp/steps
摘要：
自监督深度估计最近引起了很多关注，因为它可以促进自动驾驶车辆的三维传感能力。然而，它本质上依赖于光度测量的一致性假设，而这一假设在夜间很难成立。尽管各种有监督的夜间图像增强方法已经被提出，但它们在具有挑战性的驾驶场景中的通用性能并不令人满意。为此，我们提出了第一个联合学习夜间图像增强器和深度估计器的方法，这两个任务都不需要使用地面真相。我们的方法使用新提出的不确定像素遮蔽策略，将两个自我监督的任务紧密地纠缠在一起。这一策略源于这样的观察：夜间图像不仅存在曝光不足的区域，也存在曝光过度的区域。通过对照度图分布进行桥形曲线拟合，这两个区域都得到了抑制，两个任务也就自然衔接起来。我们在两个既定的数据集上对该方法进行了基准测试：NuScenes和RobotCar，并在这两个数据集上展示了最先进的性能。详细的消融也揭示了我们建议的机制。最后但并非最不重要的是，为了缓解现有数据集稀疏的地面真相问题，我们提供了一个基于CARLA的新的照片逼真的夜间数据集。它给社区带来了有意义的新挑战。
Self-supervised depth estimation draws a lot of attention recently as it can promote the 3D sensing capabilities of self-driving vehicles. However, it intrinsically relies upon the photometric consistency assumption, which hardly holds during nighttime. Although various supervised nighttime image enhancement methods have been proposed, their generalization performance in challenging driving scenarios is not satisfactory. To this end, we propose the first method that jointly learns a nighttime image enhancer and a depth estimator, without using ground truth for either task. Our method tightly entangles two self-supervised tasks using a newly proposed uncertain pixel masking strategy. This strategy originates from the observation that nighttime images not only suffer from underexposed regions but also from overexposed regions. By fitting a bridge-shaped curve to the illumination map distribution, both regions are suppressed and two tasks are bridged naturally. We benchmark the method on two established datasets: nuScenes and RobotCar and demonstrate state-of-the-art performance on both of them. Detailed ablations also reveal the mechanism of our proposal. Last but not least, to mitigate the problem of sparse ground truth of existing datasets, we provide a new photo-realistically enhanced nighttime dataset based upon CARLA. It brings meaningful new challenges to the community. Codes, data, and models are available at this https URL.
3.GraphReg: Dynamical Point Cloud Registration with Geometry-aware Graph Signal Processing
标题：GraphReg：利用几何感知的图形信号处理进行动态点云注册
作者： Zhao Mingyang, Ma Lei, Jia Xiaohong, Yan Dong-Ming, Huang Tiejun
文章链接：https://arxiv.org/abs/2301.12689v1
项目代码：https://github.com/zikai1/graphreg
摘要：
本研究提出了一种高精度、高效率和物理诱导的三维点云注册方法，这是许多重要的三维视觉问题的核心。与现有的仅仅考虑空间点信息而忽视表面几何的基于物理的方法相比，我们探索了几何感知的刚体动力学来调节粒子（点）的运动，这导致了更精确和稳健的注册。我们提出的方法由四个主要模块组成。首先，我们利用图形信号处理（GSP）框架来定义一个新的签名，（即每个点的点响应强度），通过它我们成功地描述了局部表面的变化，重新采样关键点，并区分不同的粒子。然后，为了解决目前基于物理学的方法对异常值敏感的缺点，我们将定义的点响应强度适应于稳健统计学中的中位绝对偏差（MAD），并采用X84原则进行自适应异常值抑制，确保稳健和稳定的登记。随后，我们提出了一种新的刚性变换下的几何不变性，以纳入点云的高阶特征，这被进一步嵌入到力的建模中，以指导成对扫描之间的可信的对应。最后，我们引入了自适应模拟退火法（ASA）来搜索全局最优，并大大加快了注册过程。我们进行了全面的实验，在从测距仪到LiDAR采集的各种数据集上评估所提出的方法。结果表明，我们提出的方法在精度上优于有代表性的最先进的方法，更适合于注册大规模的点云。此外，它比大多数竞争者要快得多，也更稳健。
This study presents a high-accuracy, efficient, and physically induced method for 3D point cloud registration, which is the core of many important 3D vision problems. In contrast to existing physics-based methods that merely consider spatial point information and ignore surface geometry, we explore geometry aware rigid-body dynamics to regulate the particle (point) motion, which results in more precise and robust registration. Our proposed method consists of four major modules. First, we leverage the graph signal processing (GSP) framework to define a new signature, (i.e., point response intensity for each point), by which we succeed in describing the local surface variation, resampling keypoints, and distinguishing different particles. Then, to address the shortcomings of current physics-based approaches that are sensitive to outliers, we accommodate the defined point response intensity to median absolute deviation (MAD) in robust statistics and adopt the X84 principle for adaptive outlier depression, ensuring a robust and stable registration. Subsequently, we propose a novel geometric invariant under rigid transformations to incorporate higher-order features of point clouds, which is further embedded for force modeling to guide the correspondence between pairwise scans credibly. Finally, we introduce an adaptive simulated annealing (ASA) method to search for the global optimum and substantially accelerate the registration process. We perform comprehensive experiments to evaluate the proposed method on various datasets captured from range scanners to LiDAR. Results demonstrate that our proposed method outperforms representative state-of-the-art approaches in terms of accuracy and is more suitable for registering large-scale point clouds. Furthermore, it is considerably faster and more robust than most competitors.
