Make-It-4D: Synthesizing a Consistent Long-Term Dynamic Scene Video from a Single Image

We study the problem of synthesizing a long-term dynamic video from only a single image. This is challenging since it requires consistent visual content movements given large camera motions. Existing methods either hallucinate inconsistent perpetual views or struggle with long camera trajectories. To address these issues, it is essential to estimate the underlying 4D (including 3D geometry and scene motion) and fill in the occluded regions. To this end, we present Make-It-4D, a novel method that can generate a consistent long-term dynamic video from a single image. On the one hand, we utilize layered depth images (LDIs) to represent a scene, and they are then unprojected to form a feature point cloud. To animate the visual content, the feature point cloud is displaced based on the scene flow derived from motion estimation and the corresponding camera pose. Such 4D representation enables our method to maintain the global consistency of the generated dynamic video. On the other hand, we fill in the occluded regions by using a pretrained diffusion model to inpaint and outpaint the input image. This enables our method to work under large camera motions. Benefiting from our design, our method can be training-free which saves a significant amount of training time. Experimental results demonstrate the effectiveness of our approach, which showcases compelling rendering results.

EndoDepthL: Lightweight Endoscopic Monocular Depth Estimation with CNN-Transformer

In this study, we address the key challenges concerning the accuracy and effectiveness of depth estimation for endoscopic imaging, with a particular emphasis on real-time inference and the impact of light reflections. We propose a novel lightweight solution named EndoDepthL that integrates Convolutional Neural Networks (CNN) and Transformers to predict multi-scale depth maps. Our approach includes optimizing the network architecture, incorporating multi-scale dilated convolution, and a multi-channel attention mechanism. We also introduce a statistical confidence boundary mask to minimize the impact of reflective areas. To better evaluate the performance of monocular depth estimation in endoscopic imaging, we propose a novel complexity evaluation metric that considers network parameter size, floating-point operations, and inference frames per second. We comprehensively evaluate our proposed method and compare it with existing baseline solutions. The results demonstrate that EndoDepthL ensures depth estimation accuracy with a lightweight structure.

Clustering Method for Time-Series Images Using Quantum-Inspired Computing Technology

Time-series clustering serves as a powerful data mining technique for time-series data in the absence of prior knowledge about clusters. A large amount of time-series data with large size has been acquired and used in various research fields. Hence, clustering method with low computational cost is required. Given that a quantum-inspired computing technology, such as a simulated annealing machine, surpasses conventional computers in terms of fast and accurately solving combinatorial optimization problems, it holds promise for accomplishing clustering tasks that are challenging to achieve using existing methods. This study proposes a novel time-series clustering method that leverages an annealing machine. The proposed method facilitates an even classification of time-series data into clusters close to each other while maintaining robustness against outliers. Moreover, its applicability extends to time-series images. We compared the proposed method with a standard existing method for clustering an online distributed dataset. In the existing method, the distances between each data are calculated based on the Euclidean distance metric, and the clustering is performed using the k-means++ method. We found that both methods yielded comparable results. Furthermore, the proposed method was applied to a flow measurement image dataset containing noticeable noise with a signal-to-noise ratio of approximately 1. Despite a small signal variation of approximately 2%, the proposed method effectively classified the data without any overlap among the clusters. In contrast, the clustering results by the standard existing method and the conditional image sampling (CIS) method, a specialized technique for flow measurement data, displayed overlapping clusters. Consequently, the proposed method provides better results than the other two methods, demonstrating its potential as a superior clustering method.

DNFOMP: Dynamic Neural Field Optimal Motion Planner for Navigation of Autonomous Robots in Cluttered Environment

Motion planning in dynamically changing environments is one of the most complex challenges in autonomous driving. Safety is a crucial requirement, along with driving comfort and speed limits. While classical sampling-based, lattice-based, and optimization-based planning methods can generate smooth and short paths, they often do not consider the dynamics of the environment. Some techniques do consider it, but they rely on updating the environment on-the-go rather than explicitly accounting for the dynamics, which is not suitable for self-driving. To address this, we propose a novel method based on the Neural Field Optimal Motion Planner (NFOMP), which outperforms state-of-the-art approaches in terms of normalized curvature and the number of cusps. Our approach embeds previously known moving obstacles into the neural field collision model to account for the dynamics of the environment. We also introduce time profiling of the trajectory and non-linear velocity constraints by adding Lagrange multipliers to the trajectory loss function. We applied our method to solve the optimal motion planning problem in an urban environment using the BeamNG.tech driving simulator. An autonomous car drove the generated trajectories in three city scenarios while sharing the road with the obstacle vehicle. Our evaluation shows that the maximum acceleration the passenger can experience instantly is -7.5 m/s^2 and that 89.6% of the driving time is devoted to normal driving with accelerations below 3.5 m/s^2. The driving style is characterized by 46.0% and 31.4% of the driving time being devoted to the light rail transit style and the moderate driving style, respectively.

BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion

Recent text-to-image diffusion models have demonstrated an astonishing capacity to generate high-quality images. However, researchers mainly studied the way of synthesizing images with only text prompts. While some works have explored using other modalities as conditions, considerable paired data, e.g., box/mask-image pairs, and fine-tuning time are required for nurturing models. As such paired data is time-consuming and labor-intensive to acquire and restricted to a closed set, this potentially becomes the bottleneck for applications in an open world. This paper focuses on the simplest form of user-provided conditions, e.g., box or scribble. To mitigate the aforementioned problem, we propose a training-free method to control objects and contexts in the synthesized images adhering to the given spatial conditions. Specifically, three spatial constraints, i.e., Inner-Box, Outer-Box, and Corner Constraints, are designed and seamlessly integrated into the denoising step of diffusion models, requiring no additional training and massive annotated layout data. Extensive results show that the proposed constraints can control what and where to present in the images while retaining the ability of the Stable Diffusion model to synthesize with high fidelity and diverse concept coverage. The code is publicly available at https://github.com/Sierkinhane/BoxDiff.

Composable Core-sets for Diversity Approximation on Multi-Dataset Streams

Core-sets refer to subsets of data that maximize some function that is commonly a diversity or group requirement. These subsets are used in place of the original data to accomplish a given task with comparable or even enhanced performance if biases are removed. Composable core-sets are core-sets with the property that subsets of the core set can be unioned together to obtain an approximation for the original data; lending themselves to be used for streamed or distributed data. Recent work has focused on the use of core-sets for training machine learning models. Preceding solutions such as CRAIG have been proven to approximate gradient descent while providing a reduced training time. In this paper, we introduce a core-set construction algorithm for constructing composable core-sets to summarize streamed data for use in active learning environments. If combined with techniques such as CRAIG and heuristics to enhance construction speed, composable core-sets could be used for real time training of models when the amount of sensor data is large. We provide empirical analysis by considering extrapolated data for the runtime of such a brute force algorithm. This algorithm is then analyzed for efficiency through averaged empirical regression and key results and improvements are suggested for further research on the topic.

A Forecaster's Review of Judea Pearl's Causality: Models, Reasoning and Inference, Second Edition, 2009

With the big popularity and success of Judea Pearl's original causality book, this review covers the main topics updated in the second edition in 2009 and illustrates an easy-to-follow causal inference strategy in a forecast scenario. It further discusses some potential benefits and challenges for causal inference with time series forecasting when modeling the counterfactuals, estimating the uncertainty and incorporating prior knowledge to estimate causal effects in different forecasting scenarios.

A Comparison of Adversarial Learning Techniques for Malware Detection

Machine learning has proven to be a useful tool for automated malware detection, but machine learning models have also been shown to be vulnerable to adversarial attacks. This article addresses the problem of generating adversarial malware samples, specifically malicious Windows Portable Executable files. We summarize and compare work that has focused on adversarial machine learning for malware detection. We use gradient-based, evolutionary algorithm-based, and reinforcement-based methods to generate adversarial samples, and then test the generated samples against selected antivirus products. We compare the selected methods in terms of accuracy and practical applicability. The results show that applying optimized modifications to previously detected malware can lead to incorrect classification of the file as benign. It is also known that generated malware samples can be successfully used against detection models other than those used to generate them and that using combinations of generators can create new samples that evade detection. Experiments show that the Gym-malware generator, which uses a reinforcement learning approach, has the greatest practical potential. This generator achieved an average sample generation time of 5.73 seconds and the highest average evasion rate of 44.11%. Using the Gym-malware generator in combination with itself improved the evasion rate to 58.35%.

GNNPipe: Accelerating Distributed Full-Graph GNN Training with Pipelined Model Parallelism

Current distributed full-graph GNN training methods adopt a variant of data parallelism, namely graph parallelism, in which the whole graph is divided into multiple partitions (subgraphs) and each GPU processes one of them. This incurs high communication overhead because of the inter-partition message passing at each layer. To this end, we proposed a new training method named GNNPipe that adopts model parallelism instead, which has a lower worst-case asymptotic communication complexity than graph parallelism. To ensure high GPU utilization, we proposed to combine model parallelism with a chunk-based pipelined training method, in which each GPU processes a different chunk of graph data at different layers concurrently. We further proposed hybrid parallelism that combines model and graph parallelism when the model-level parallelism is insufficient. We also introduced several tricks to ensure convergence speed and model accuracies to accommodate embedding staleness introduced by pipelining. Extensive experiments show that our method reduces the per-epoch training time by up to 2.45x (on average 2.03x) and reduces the communication volume and overhead by up to 22.51x and 27.21x (on average 10.27x and 14.96x), respectively, while achieving a comparable level of model accuracy and convergence speed compared to graph parallelism.

Practical Anomaly Detection over Multivariate Monitoring Metrics for Online Services

As modern software systems continue to grow in terms of complexity and volume, anomaly detection on multivariate monitoring metrics, which profile systems' health status, becomes more and more critical and challenging. In particular, the dependency between different metrics and their historical patterns plays a critical role in pursuing prompt and accurate anomaly detection. Existing approaches fall short of industrial needs for being unable to capture such information efficiently. To fill this significant gap, in this paper, we propose CMAnomaly, an anomaly detection framework on multivariate monitoring metrics based on collaborative machine. The proposed collaborative machine is a mechanism to capture the pairwise interactions along with feature and temporal dimensions with linear time complexity. Cost-effective models can then be employed to leverage both the dependency between monitoring metrics and their historical patterns for anomaly detection. The proposed framework is extensively evaluated with both public data and industrial data collected from a large-scale online service system of Huawei Cloud. The experimental results demonstrate that compared with state-of-the-art baseline models, CMAnomaly achieves an average F1 score of 0.9494, outperforming baselines by 6.77% to 10.68%, and runs 10X to 20X faster. Furthermore, we also share our experience of deploying CMAnomaly in Huawei Cloud.