Recent advances in deep learning have led to the development of models approaching human level of accuracy. However, healthcare remains an area lacking in widespread adoption. The safety-critical nature of healthcare results in a natural reticence to put these black-box deep learning models into practice. In this paper, we explore interpretable methods for a clinical decision support system, sleep staging, based on physiological signals such as EEG, EOG, and EMG. A recent work has shown sleep staging using simple models and an exhaustive set of features can perform nearly as well as deep learning approaches but only for certain datasets. Moreover, the utility of these features from a clinical standpoint is unclear. On the other hand, the proposed framework, NormIntSleep shows that by representing deep learning embeddings using normalized features, great performance can be obtained across different datasets. NormIntSleep performs 4.5% better than the exhaustive feature-based approach and 1.5% better than other representation learning approaches. An empirical comparison between the utility of the interpretations of these models highlights the improved alignment with clinical expectations when performance is traded-off slightly.

最近基于深度学习的临床决策支持系统的准确性是有希望的。但是，缺乏模型可解释性仍然是医疗保健中人工智能广泛采用的障碍。使用睡眠作为案例研究，我们提出了一种可推广的方法，将临床解释性与黑盒深度学习得出的高精度相结合。多聚词（PSG）的临床医生确定的睡眠阶段仍然是评估睡眠质量的金标准。但是，专家的PSG手册注释既昂贵又过时。我们建议使用嵌入式，规则和功能来读取PSG的农奴，可解释的睡眠分期。农奴通过从AASM手册中得出的有意义的特征来解释分类的睡眠阶段，用于睡眠和相关事件的评分。在农奴中，从卷积和复发性神经网络的混合体获得的嵌入被转移到可解释的特征空间。这些代表性的可解释功能用于训练简单的模型，例如浅决策树进行分类。模型结果将在两个公开可用的数据集上进行验证。农奴超过了可解释的睡眠分期的当前最新时间。 Serf使用梯度增压树作为分类器，在当前最新的黑盒模型的2％以内，获得了0.766 $ \ kappa $和0.870 AUC-ROC。

Semantic segmentation works on the computer vision algorithm for assigning each pixel of an image into a class. The task of semantic segmentation should be performed with both accuracy and efficiency. Most of the existing deep FCNs yield to heavy computations and these networks are very power hungry, unsuitable for real-time applications on portable devices. This project analyzes current semantic segmentation models to explore the feasibility of applying these models for emergency response during catastrophic events. We compare the performance of real-time semantic segmentation models with non-real-time counterparts constrained by aerial images under oppositional settings. Furthermore, we train several models on the Flood-Net dataset, containing UAV images captured after Hurricane Harvey, and benchmark their execution on special classes such as flooded buildings vs. non-flooded buildings or flooded roads vs. non-flooded roads. In this project, we developed a real-time UNet based model and deployed that network on Jetson AGX Xavier module.

Real-world autonomous missions often require rich interaction with nearby objects, such as doors or switches, along with effective navigation. However, such complex behaviors are difficult to learn because they involve both high-level planning and low-level motor control. We present a novel framework, Cascaded Compositional Residual Learning (CCRL), which learns composite skills by recursively leveraging a library of previously learned control policies. Our framework learns multiplicative policy composition, task-specific residual actions, and synthetic goal information simultaneously while freezing the prerequisite policies. We further explicitly control the style of the motion by regularizing residual actions. We show that our framework learns joint-level control policies for a diverse set of motor skills ranging from basic locomotion to complex interactive navigation, including navigating around obstacles, pushing objects, crawling under a table, pushing a door open with its leg, and holding it open while walking through it. The proposed CCRL framework leads to policies with consistent styles and lower joint torques, which we successfully transfer to a real Unitree A1 robot without any additional fine-tuning.

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

We introduce the MAsked Generative VIdeo Transformer, MAGVIT, to tackle various video synthesis tasks with a single model. We introduce a 3D tokenizer to quantize a video into spatial-temporal visual tokens and propose an embedding method for masked video token modeling to facilitate multi-task learning. We conduct extensive experiments to demonstrate the quality, efficiency, and flexibility of MAGVIT. Our experiments show that (i) MAGVIT performs favorably against state-of-the-art approaches and establishes the best-published FVD on three video generation benchmarks, including the challenging Kinetics-600. (ii) MAGVIT outperforms existing methods in inference time by two orders of magnitude against diffusion models and by 60x against autoregressive models. (iii) A single MAGVIT model supports ten diverse generation tasks and generalizes across videos from different visual domains. The source code and trained models will be released to the public at https://magvit.cs.cmu.edu.

Wireless Sensor Network (WSN) applications reshape the trend of warehouse monitoring systems allowing them to track and locate massive numbers of logistic entities in real-time. To support the tasks, classic Radio Frequency (RF)-based localization approaches (e.g. triangulation and trilateration) confront challenges due to multi-path fading and signal loss in noisy warehouse environment. In this paper, we investigate machine learning methods using a new grid-based WSN platform called Sensor Floor that can overcome the issues. Sensor Floor consists of 345 nodes installed across the floor of our logistic research hall with dual-band RF and Inertial Measurement Unit (IMU) sensors. Our goal is to localize all logistic entities, for this study we use a mobile robot. We record distributed sensing measurements of Received Signal Strength Indicator (RSSI) and IMU values as the dataset and position tracking from Vicon system as the ground truth. The asynchronous collected data is pre-processed and trained using Random Forest and Convolutional Neural Network (CNN). The CNN model with regularization outperforms the Random Forest in terms of localization accuracy with aproximate 15 cm. Moreover, the CNN architecture can be configured flexibly depending on the scenario in the warehouse. The hardware, software and the CNN architecture of the Sensor Floor are open-source under https://github.com/FLW-TUDO/sensorfloor.

The dichotomy between the challenging nature of obtaining annotations for activities, and the more straightforward nature of data collection from wearables, has resulted in significant interest in the development of techniques that utilize large quantities of unlabeled data for learning representations. Contrastive Predictive Coding (CPC) is one such method, learning effective representations by leveraging properties of time-series data to setup a contrastive future timestep prediction task. In this work, we propose enhancements to CPC, by systematically investigating the encoder architecture, the aggregator network, and the future timestep prediction, resulting in a fully convolutional architecture, thereby improving parallelizability. Across sensor positions and activities, our method shows substantial improvements on four of six target datasets, demonstrating its ability to empower a wide range of application scenarios. Further, in the presence of very limited labeled data, our technique significantly outperforms both supervised and self-supervised baselines, positively impacting situations where collecting only a few seconds of labeled data may be possible. This is promising, as CPC does not require specialized data transformations or reconstructions for learning effective representations.

To properly assist humans in their needs, human activity recognition (HAR) systems need the ability to fuse information from multiple modalities. Our hypothesis is that multimodal sensors, visual and non-visual tend to provide complementary information, addressing the limitations of other modalities. In this work, we propose a multi-modal framework that learns to effectively combine features from RGB Video and IMU sensors, and show its robustness for MMAct and UTD-MHAD datasets. Our model is trained in two-stage, where in the first stage, each input encoder learns to effectively extract features, and in the second stage, learns to combine these individual features. We show significant improvements of 22% and 11% compared to video only and IMU only setup on UTD-MHAD dataset, and 20% and 12% on MMAct datasets. Through extensive experimentation, we show the robustness of our model on zero shot setting, and limited annotated data setting. We further compare with state-of-the-art methods that use more input modalities and show that our method outperforms significantly on the more difficult MMact dataset, and performs comparably in UTD-MHAD dataset.

We introduce a Transformer based 6D Object Pose Estimation framework VideoPose, comprising an end-to-end attention based modelling architecture, that attends to previous frames in order to estimate accurate 6D Object Poses in videos. Our approach leverages the temporal information from a video sequence for pose refinement, along with being computationally efficient and robust. Compared to existing methods, our architecture is able to capture and reason from long-range dependencies efficiently, thus iteratively refining over video sequences. Experimental evaluation on the YCB-Video dataset shows that our approach is on par with the state-of-the-art Transformer methods, and performs significantly better relative to CNN based approaches. Further, with a speed of 33 fps, it is also more efficient and therefore applicable to a variety of applications that require real-time object pose estimation. Training code and pretrained models are available at https://github.com/ApoorvaBeedu/VideoPose