Recently, MLP-like vision models have achieved promising performances on mainstream visual recognition tasks. In contrast with vision transformers and CNNs, the success of MLP-like models shows that simple information fusion operations among tokens and channels can yield a good representation power for deep recognition models. However, existing MLP-like models fuse tokens through static fusion operations, lacking adaptability to the contents of the tokens to be mixed. Thus, customary information fusion procedures are not effective enough. To this end, this paper presents an efficient MLP-like network architecture, dubbed DynaMixer, resorting to dynamic information fusion. Critically, we propose a procedure, on which the DynaMixer model relies, to dynamically generate mixing matrices by leveraging the contents of all the tokens to be mixed. To reduce the time complexity and improve the robustness, a dimensionality reduction technique and a multi-segment fusion mechanism are adopted. Our proposed DynaMixer model (97M parameters) achieves 84.3\% top-1 accuracy on the ImageNet-1K dataset without extra training data, performing favorably against the state-of-the-art vision MLP models. When the number of parameters is reduced to 26M, it still achieves 82.7\% top-1 accuracy, surpassing the existing MLP-like models with a similar capacity. The implementation of DynaMixer will be made available to the public.
In the application of computer-vision based displacement measurement, an optical target is usually required to prove the reference. In the case that the optical target cannot be attached to the measuring objective, edge detection, feature matching and template matching are the most common approaches in target-less photogrammetry. However, their performance significantly relies on parameter settings. This becomes problematic in dynamic scenes where complicated background texture exists and varies over time. To tackle this issue, we propose virtual point tracking for real-time target-less dynamic displacement measurement, incorporating deep learning techniques and domain knowledge. Our approach consists of three steps: 1) automatic calibration for detection of region of interest; 2) virtual point detection for each video frame using deep convolutional neural network; 3) domain-knowledge based rule engine for point tracking in adjacent frames. The proposed approach can be executed on an edge computer in a real-time manner (i.e. over 30 frames per second). We demonstrate our approach for a railway application, where the lateral displacement of the wheel on the rail is measured during operation. We also implement an algorithm using template matching and line detection as the baseline for comparison. The numerical experiments have been performed to evaluate the performance and the latency of our approach in the harsh railway environment with noisy and varying backgrounds.
Brain-computer interfaces (BCIs) still face many challenges to step out of laboratories to be used in real-life applications. A key one persists in the high performance control of diverse effectors for complex tasks, using chronic and safe recorders. This control must be robust over time and of high decoding performance without continuous recalibration of the decoders. In the article, asynchronous control of an exoskeleton by a tetraplegic patient using a chronically implanted epidural electrocorticography (EpiCoG) implant is demonstrated. For this purpose, an adaptive online tensor-based decoder: the Recursive Exponentially Weighted Markov-Switching multi-Linear Model (REW-MSLM) was developed. We demonstrated over a period of 6 months the stability of the 8-dimensional alternative bimanual control of the exoskeleton and its virtual avatar using REW-MSLM without recalibration of the decoder.
Genetic programming (GP) is one of the best approaches today to discover symbolic regression models. To find models that trade off accuracy and complexity, the non-dominated sorting genetic algorithm II (NSGA-II) is widely used. Unfortunately, it has been shown that NSGA-II can be inefficient: in early generations, low-complexity models over-replicate and take over most of the population. Consequently, studies have proposed different approaches to promote diversity. Here, we study the root of this problem, in order to design a superior approach. We find that the over-replication of low complexity-models is due to a lack of evolvability, i.e., the inability to produce offspring with improved accuracy. We therefore extend NSGA-II to track, over time, the evolvability of models of different levels of complexity. With this information, we limit how many models of each complexity level are allowed to survive the generation. We compare this new version of NSGA-II, evoNSGA-II, with the use of seven existing multi-objective GP approaches on ten widely-used data sets, and find that evoNSGA-II is equal or superior to using these approaches in almost all comparisons. Furthermore, our results confirm that evoNSGA-II behaves as intended: models that are more evolvable form the majority of the population.
In the aftermath of disasters, building damage maps are obtained using change detection to plan rescue operations. Current convolutional neural network approaches do not consider the similarities between neighboring buildings for predicting the damage. We present a novel graph-based building damage detection solution to capture these relationships. Our proposed model architecture learns from both local and neighborhood features to predict building damage. Specifically, we adopt the sample and aggregate graph convolution strategy to learn aggregation functions that generalize to unseen graphs which is essential for alleviating the time needed to obtain predictions for new disasters. Our experiments on the xBD dataset and comparisons with a classical convolutional neural network reveal that while our approach is handicapped by class imbalance, it presents a promising and distinct advantage when it comes to cross-disaster generalization.
This paper proposes a deep learning approach to a class of active sensing problems in wireless communications in which an agent sequentially interacts with an environment over a predetermined number of time frames to gather information in order to perform a sensing or actuation task for maximizing some utility function. In such an active learning setting, the agent needs to design an adaptive sensing strategy sequentially based on the observations made so far. To tackle such a challenging problem in which the dimension of historical observations increases over time, we propose to use a long short-term memory (LSTM) network to exploit the temporal correlations in the sequence of observations and to map each observation to a fixed-size state information vector. We then use a deep neural network (DNN) to map the LSTM state at each time frame to the design of the next measurement step. Finally, we employ another DNN to map the final LSTM state to the desired solution. We investigate the performance of the proposed framework for adaptive channel sensing problems in wireless communications. In particular, we consider the adaptive beamforming problem for mmWave beam alignment and the adaptive reconfigurable intelligent surface sensing problem for reflection alignment. Numerical results demonstrate that the proposed deep active sensing strategy outperforms the existing adaptive or nonadaptive sensing schemes.
In the last few years, several deep learning models, especially Generative Adversarial Networks have received a lot of attention for the task of Single Image Super-Resolution (SISR). These methods focus on building an end-to-end framework, which produce a high resolution(SR) image from a given low resolution(LR) image in a single step to achieve state-of-the-art performance. This paper focuses on improving an existing deep-learning based method to perform Super-Resolution Microscopy in real-time using a standard GPU. For this, we first propose a tiling strategy, which takes advantage of parallelism provided by a GPU to speed up the network training process. Further, we suggest simple changes to the architecture of the generator and the discriminator of SRGAN. Subsequently, We compare the quality and the running time for the outputs produced by our model, opening its applications in different areas like low-end benchtop and even mobile microscopy. Finally, we explore the possibility of the trained network to produce High-Resolution HR outputs for different domains.
Real-time estimation of actual object depth is a module that is essential to performing various autonomous system tasks such as 3D reconstruction, scene understanding and condition assessment of machinery parts. During the last decade of machine learning, extensive deployment of deep learning methods to computer vision tasks has yielded approaches that succeed in achieving realistic depth synthesis out of a simple RGB modality. While most of these models are based on paired depth data or availability of video sequences and stereo images, methods for single-view depth synthesis in a fully unsupervised setting have hardly been explored. This study presents the most recent advances in the field of generative neural networks, leveraging them to perform fully unsupervised single-shot depth synthesis. Two generators for RGB-to-depth and depth-to-RGB transfer are implemented and simultaneously optimized using the Wasserstein-1 distance and a novel perceptual reconstruction term. To ensure that the proposed method is plausible, we comprehensively evaluate the models using industrial surface depth data as well as the Texas 3D Face Recognition Database and the SURREAL dataset that records body depth. The success observed in this study suggests the great potential for unsupervised single-shot depth estimation in real-world applications.
Understanding the relation between anatomy andgait is key to successful predictive gait simulation. Inthis paper, we present Generative GaitNet, which isa novel network architecture based on deep reinforce-ment learning for controlling a comprehensive, full-body, musculoskeletal model with 304 Hill-type mus-culotendons. The Generative Gait is a pre-trained, in-tegrated system of artificial neural networks learnedin a 618-dimensional continuous domain of anatomyconditions (e.g., mass distribution, body proportion,bone deformity, and muscle deficits) and gait condi-tions (e.g., stride and cadence). The pre-trained Gait-Net takes anatomy and gait conditions as input andgenerates a series of gait cycles appropriate to theconditions through physics-based simulation. We willdemonstrate the efficacy and expressive power of Gen-erative GaitNet to generate a variety of healthy andpathologic human gaits in real-time physics-based sim-ulation.
With increasing physical threats in recent years targeted at critical infrastructures, it is crucial to establish a reliable threat monitoring system integrating video surveillance and digital sensors based on cutting-edge technologies. A physical threat monitoring solution unifying the floorplan, cameras, and sensors for smart buildings has been set up in our study. Computer vision and deep learning models are used for video streams analysis. When a threat is detected by a rule engine based on the real-time analysis results combining with feedback from related digital sensors, an alert is sent to the Video Management System so that human operators can take further action. A physical threat monitoring system typically needs to address complex and even destructive incidents, such as fire, which is unrealistic to simulate in real life. Restrictions imposed during the Covid-19 pandemic and privacy concerns have added to the challenges. Our study utilises the Unreal Engine to simulate some typical suspicious and intrusion scenes with photorealistic qualities in the context of a virtual building. Add-on programs are implemented to transfer the video stream from virtual PTZ cameras to the Milestone Video Management System and enable users to control those cameras from the graphic client application. Virtual sensors such as fire alarms, temperature sensors and door access controls are implemented similarly, fulfilling the same programmatic VMS interface as real-life sensors. Thanks to this simulation system's extensibility and repeatability, we have consolidated this unified physical threat monitoring system and verified its effectiveness and user-friendliness. Both the simulated Unreal scenes and the software add-ons developed during this study are highly modulated and thereby are ready for reuse in future projects in this area.