The paper explores the industrial multimodal Anomaly Detection (AD) task, which exploits point clouds and RGB images to localize anomalies. We introduce a novel light and fast framework that learns to map features from one modality to the other on nominal samples. At test time, anomalies are detected by pinpointing inconsistencies between observed and mapped features. Extensive experiments show that our approach achieves state-of-the-art detection and segmentation performance in both the standard and few-shot settings on the MVTec 3D-AD dataset while achieving faster inference and occupying less memory than previous multimodal AD methods. Moreover, we propose a layer-pruning technique to improve memory and time efficiency with a marginal sacrifice in performance.
Time series data is ubiquitous across various domains such as finance, healthcare, and manufacturing, but their properties can vary significantly depending on the domain they originate from. The ability to perform Content-based Time Series Retrieval (CTSR) is crucial for identifying unknown time series examples. However, existing CTSR works typically focus on retrieving time series from a single domain database, which can be inadequate if the user does not know the source of the query time series. This limitation motivates us to investigate the CTSR problem in a scenario where the database contains time series from multiple domains. To facilitate this investigation, we introduce a CTSR benchmark dataset that comprises time series data from a variety of domains, such as motion, power demand, and traffic. This dataset is sourced from a publicly available time series classification dataset archive, making it easily accessible to researchers in the field. We compare several popular methods for modeling and retrieving time series data using this benchmark dataset. Additionally, we propose a novel distance learning model that outperforms the existing methods. Overall, our study highlights the importance of addressing the CTSR problem across multiple domains and provides a useful benchmark dataset for future research.
Likelihood-free inference is quickly emerging as a powerful tool to perform fast/effective parameter estimation. We demonstrate a technique of optimizing likelihood-free inference to make it even faster by marginalizing symmetries in a physical problem. In this approach, physical symmetries, for example, time-translation are learned using joint-embedding via self-supervised learning with symmetry data augmentations. Subsequently, parameter inference is performed using a normalizing flow where the embedding network is used to summarize the data before conditioning the parameters. We present this approach on two simple physical problems and we show faster convergence in a smaller number of parameters compared to a normalizing flow that does not use a pre-trained symmetry-informed representation.
One of the main challenges of multimodal learning is the need to combine heterogeneous modalities (e.g., video, audio, text). For example, video and audio are obtained at much higher rates than text and are roughly aligned in time. They are often not synchronized with text, which comes as a global context, e.g., a title, or a description. Furthermore, video and audio inputs are of much larger volumes, and grow as the video length increases, which naturally requires more compute dedicated to these modalities and makes modeling of long-range dependencies harder. We here decouple the multimodal modeling, dividing it into separate, focused autoregressive models, processing the inputs according to the characteristics of the modalities. We propose a multimodal model, called Mirasol3B, consisting of an autoregressive component for the time-synchronized modalities (audio and video), and an autoregressive component for the context modalities which are not necessarily aligned in time but are still sequential. To address the long-sequences of the video-audio inputs, we propose to further partition the video and audio sequences in consecutive snippets and autoregressively process their representations. To that end, we propose a Combiner mechanism, which models the audio-video information jointly within a timeframe. The Combiner learns to extract audio and video features from raw spatio-temporal signals, and then learns to fuse these features producing compact but expressive representations per snippet. Our approach achieves the state-of-the-art on well established multimodal benchmarks, outperforming much larger models. It effectively addresses the high computational demand of media inputs by both learning compact representations, controlling the sequence length of the audio-video feature representations, and modeling their dependencies in time.
With the help of Score Distillation Sampling(SDS) and the rapid development of various trainable 3D representations, Text-to-Image(T2I) diffusion models have been applied to 3D generation tasks and achieved considerable results. There are also some attempts toward the task of editing 3D objects leveraging this Text-to-3D pipeline. However, most methods currently focus on adding additional geometries, overwriting textures or both. But few of them can perform non-rigid transformation of 3D objects. For those who can perform non-rigid editing, on the other hand, suffer from low-resolution, lack of fidelity and poor flexibility. In order to address these issues, we present: Plasticine3D, a general, high-fidelity, photo-realistic and controllable non-rigid editing pipeline. Firstly, our work divides the editing process into a geometry editing stage and a texture editing stage to achieve more detailed and photo-realistic results ; Secondly, in order to perform non-rigid transformation with controllable results while maintain the fidelity towards original 3D models in the same time, we propose a multi-view-embedding(MVE) optimization strategy to ensure that the diffusion model learns the overall features of the original object and an embedding-fusion(EF) to control the degree of editing by adjusting the value of the fusing rate. We also design a geometry processing step before optimizing on the base geometry to cope with different needs of various editing tasks. Further more, to fully leverage the geometric prior from the original 3D object, we provide an optional replacement of score distillation sampling named score projection sampling(SPS) which enables us to directly perform optimization from the origin 3D mesh in most common median non-rigid editing scenarios. We demonstrate the effectiveness of our method on both the non-rigid 3D editing task and general 3D editing task.
Designing reward functions that guide generative molecular design (GMD) algorithms to desirable areas of chemical space is of critical importance in AI-driven drug discovery. Traditionally, this has been a manual and error-prone task; the selection of appropriate computational methods to approximate biological assays is challenging and the aggregation of computed values into a single score even more so, leading to potential reliance on trial-and-error approaches. We propose a novel approach for automated reward configuration that relies solely on experimental data, mitigating the challenges of manual reward adjustment on drug discovery projects. Our method achieves this by constructing a ranking over experimental data based on Pareto dominance over the multi-objective space, then training a neural network to approximate the reward function such that rankings determined by the predicted reward correlate with those determined by the Pareto dominance relation. We validate our method using two case studies. In the first study we simulate Design-Make-Test-Analyse (DMTA) cycles by alternating reward function updates and generative runs guided by that function. We show that the learned function adapts over time to yield compounds that score highly with respect to evaluation functions taken from the literature. In the second study we apply our algorithm to historical data from four real drug discovery projects. We show that our algorithm yields reward functions that outperform the predictive accuracy of human-defined functions, achieving an improvement of up to 0.4 in Spearman's correlation against a ground truth evaluation function that encodes the target drug profile for that project. Our method provides an efficient data-driven way to configure reward functions for GMD, and serves as a strong baseline for future research into transformative approaches for the automation of drug discovery.
Recently proposed perceptually optimized per-title video encoding methods provide better BD-rate savings than fixed bitrate-ladder approaches that have been employed in the past. However, a disadvantage of per-title encoding is that it requires significant time and energy to compute bitrate ladders. Over the past few years, a variety of methods have been proposed to construct optimal bitrate ladders including using low-level features to predict cross-over bitrates, optimal resolutions for each bitrate, predicting visual quality, etc. Here, we deploy features drawn from Visual Information Fidelity (VIF) (VIF features) extracted from uncompressed videos to predict the visual quality (VMAF) of compressed videos. We present multiple VIF feature sets extracted from different scales and subbands of a video to tackle the problem of bitrate ladder construction. Comparisons are made against a fixed bitrate ladder and a bitrate ladder obtained from exhaustive encoding using Bjontegaard delta metrics.
Quadratic programs (QP) subject to multiple time-dependent control barrier function (CBF) based constraints have been used to design safety-critical controllers. However, ensuring the existence of a solution at all times to the QP subject to multiple CBF constraints is non-trivial. We quantify the feasible solution space of the QP in terms of its volume. We introduce a novel feasible space volume monitoring control barrier function that promotes compatibility of barrier functions and, hence, existence of a solution at all times. We show empirically that our approach not only enhances feasibility but also exhibits reduced sensitivity to changes in the hyperparameters such as gains of nominal controller. Finally, paired with a global planner, we evaluate our controller for navigation among humans in the AWS Hospital gazebo environment. The proposed controller is demonstrated to outperform the standard CBF-QP controller in maintaining feasibility.
In the field of federated learning, addressing non-independent and identically distributed (non-i.i.d.) data remains a quintessential challenge for improving global model performance. This work introduces the Feature Norm Regularized Federated Learning (FNR-FL) algorithm, which uniquely incorporates class average feature norms to enhance model accuracy and convergence in non-i.i.d. scenarios. Our comprehensive analysis reveals that FNR-FL not only accelerates convergence but also significantly surpasses other contemporary federated learning algorithms in test accuracy, particularly under feature distribution skew scenarios. The novel modular design of FNR-FL facilitates seamless integration with existing federated learning frameworks, reinforcing its adaptability and potential for widespread application. We substantiate our claims through rigorous empirical evaluations, demonstrating FNR-FL's exceptional performance across various skewed data distributions. Relative to FedAvg, FNR-FL exhibits a substantial 66.24\% improvement in accuracy and a significant 11.40\% reduction in training time, underscoring its enhanced effectiveness and efficiency.
Foundation models are currently driving a paradigm shift in computer vision tasks for various fields including biology, astronomy, and robotics among others, leveraging user-generated prompts to enhance their performance. In the manufacturing domain, accurate image-based defect segmentation is imperative to ensure product quality and facilitate real-time process control. However, such tasks are often characterized by multiple challenges including the absence of labels and the requirement for low latency inference among others. To address these issues, we construct a framework for image segmentation using a state-of-the-art Vision Transformer (ViT) based Foundation model (Segment Anything Model) with a novel multi-point prompt generation scheme using unsupervised clustering. We apply our framework to perform real-time porosity segmentation in a case study of laser base powder bed fusion (L-PBF) and obtain high Dice Similarity Coefficients (DSC) without the necessity for any supervised fine-tuning in the model. Using such lightweight foundation model inference in conjunction with unsupervised prompt generation, we envision the construction of a real-time anomaly detection pipeline that has the potential to revolutionize the current laser-based additive manufacturing processes, thereby facilitating the shift towards Industry 4.0 and promoting defect-free production along with operational efficiency.