Search

To extract robust and generalizable skeleton action recognition features, large amounts of well-curated data are typically required, which is a challenging task hindered by annotation and computation costs. Therefore, unsupervised representation learning is of prime importance to leverage unlabeled skeleton data. In this work, we investigate unsupervised representation learning for skeleton action recognition. For this purpose, we designed a lightweight convolutional transformer framework, named ReL-SAR, exploiting the complementarity of convolutional and attention layers for jointly modeling spatial and temporal cues in skeleton sequences. We also use a Selection-Permutation strategy for skeleton joints to ensure more informative descriptions from skeletal data. Finally, we capitalize on Bootstrap Your Own Latent (BYOL) to learn robust representations from unlabeled skeleton sequence data. We achieved very competitive results on limited-size datasets: MCAD, IXMAS, JHMDB, and NW-UCLA, showing the effectiveness of our proposed method against state-of-the-art methods in terms of both performance and computational efficiency. To ensure reproducibility and reusability, the source code including all implementation parameters is provided at: https://github.com/SafwenNaimi/Representation-Learning-for-Skeleton-Action-Recognition-with-Convolutional-Transformers-and-BYOL, Comment: 8 pages, 4 figures, 6 tables

Neuromorphic (brain-inspired) photonics leverages photonic chips to accelerate artificial intelligence, offering high-speed and energy efficient solutions in RF communication, tensor processing, and data classification. However, the limited physical size of integrated photonic hardware constrains network complexity and computational capacity. In light of recent advances in photonic quantum technology, it is natural to utilize quantum exponential speedup to scale photonic neural network capabilities. Here we show a combination of classical network layers with trainable continuous variable quantum circuits yields hybrid networks with improved trainability and accuracy. On a classification task, hybrid networks achieve the same performance when benchmarked against fully classical networks that are twice the size. When the bit precision of the optimized networks is reduced through added noise, the hybrid networks still achieve greater accuracy when evaluated at state of the art bit precision. These hybrid quantum classical networks demonstrate a unique route to improve computational capacity of integrated photonic neural networks without increasing the physical network size.

We propose a novel Transformer-based module to address the data association problem for multi-object tracking. From detections obtained by a pretrained detector, this module uses only coordinates from bounding boxes to estimate an affinity score between pairs of tracks extracted from two distinct temporal windows. This module, named TWiX, is trained on sets of tracks with the objective of discriminating pairs of tracks coming from the same object from those which are not. Our module does not use the intersection over union measure, nor does it requires any motion priors or any camera motion compensation technique. By inserting TWiX within an online cascade matching pipeline, our tracker C-TWiX achieves state-of-the-art performance on the DanceTrack and KITTIMOT datasets, and gets competitive results on the MOT17 dataset. The code will be made available upon publication., Comment: Preprint submitted to Pattern Recognition

Increasing the accuracy of instance segmentation methods is often done at the expense of speed. Using coarser representations, we can reduce the number of parameters and thus obtain real-time masks. In this paper, we take inspiration from the set cover problem to predict mask approximations. Given ground-truth binary masks of objects of interest as training input, our method learns to predict the approximate coverage of these objects by disks without supervision on their location or radius. Each object is represented by a fixed number of disks with different radii. In the learning phase, we consider the radius as proportional to a standard deviation in order to compute the error to propagate on a set of two-dimensional Gaussian functions rather than disks. We trained and tested our instance segmentation method on challenging datasets showing dense urban settings with various road users. Our method achieve state-of-the art results on the IDD and KITTI dataset with an inference time of 0.040 s on a single RTX 3090 GPU.

Urban traffic environments present unique challenges for object detection, particularly with the increasing presence of micromobility vehicles like e-scooters and bikes. To address this object detection problem, this work introduces an adapted detection model that combines the accuracy and speed of single-frame object detection with the richer features offered by video object detection frameworks. This is done by applying aggregated feature maps from consecutive frames processed through motion flow to the YOLOX architecture. This fusion brings a temporal perspective to YOLOX detection abilities, allowing for a better understanding of urban mobility patterns and substantially improving detection reliability. Tested on a custom dataset curated for urban micromobility scenarios, our model showcases substantial improvement over existing state-of-the-art methods, demonstrating the need to consider spatio-temporal information for detecting such small and thin objects. Our approach enhances detection in challenging conditions, including occlusions, ensuring temporal consistency, and effectively mitigating motion blur., Comment: Accepted at the 21st Conference on Robots and Vision (CRV), 2024

Consecutive frames in a video contain redundancy, but they may also contain relevant complementary information for the detection task. The objective of our work is to leverage this complementary information to improve detection. Therefore, we propose a spatio-temporal fusion framework (STF). We first introduce multi-frame and single-frame attention modules that allow a neural network to share feature maps between nearby frames to obtain more robust object representations. Second, we introduce a dual-frame fusion module that merges feature maps in a learnable manner to improve them. Our evaluation is conducted on three different benchmarks including video sequences of moving road users. The performed experiments demonstrate that the proposed spatio-temporal fusion module leads to improved detection performance compared to baseline object detectors. Code is available at https://github.com/noreenanwar/STF-module, Comment: 8 pages,3 figures

Artificial intelligence (AI) has seen remarkable advancements across various domains, including natural language processing, computer vision, autonomous vehicles, and biology. However, the rapid expansion of AI technologies has escalated the demand for more powerful computing resources. As digital computing approaches fundamental limits, neuromorphic photonics emerges as a promising platform to complement existing digital systems. In neuromorphic photonic computing, photonic devices are controlled using analog signals. This necessitates the use of digital-to-analog converters (DAC) and analog-to-digital converters (ADC) for interfacing with these devices during inference and training. However, data movement between memory and these converters in conventional von Neumann computing architectures consumes energy. To address this, analog memory co-located with photonic computing devices is proposed. This approach aims to reduce the reliance on DACs and ADCs and minimize data movement to enhance compute efficiency. This paper demonstrates a monolithically integrated neuromorphic photonic circuit with co-located capacitive analog memory and compares various analog memory technologies for neuromorphic photonic computing using the MNIST dataset as a benchmark., Comment: 23 pages, 10 figures

High-throughput computational materials discovery has promised significant acceleration of the design and discovery of new materials for many years. Despite a surge in interest and activity, the constraints imposed by large-scale computational resources present a significant bottleneck. Furthermore, examples of large-scale computational discovery carried through experimental validation remain scarce, especially for materials with product applicability. Here we demonstrate how this vision became reality by first combining state-of-the-art artificial intelligence (AI) models and traditional physics-based models on cloud high-performance computing (HPC) resources to quickly navigate through more than 32 million candidates and predict around half a million potentially stable materials. By focusing on solid-state electrolytes for battery applications, our discovery pipeline further identified 18 promising candidates with new compositions and rediscovered a decade's worth of collective knowledge in the field as a byproduct. By employing around one thousand virtual machines (VMs) in the cloud, this process took less than 80 hours. We then synthesized and experimentally characterized the structures and conductivities of our top candidates, the Na$_x$Li$_{3-x}$YCl$_6$ ($0 < x < 3$) series, demonstrating the potential of these compounds to serve as solid electrolytes. Additional candidate materials that are currently under experimental investigation could offer more examples of the computational discovery of new phases of Li- and Na-conducting solid electrolytes. We believe that this unprecedented approach of synergistically integrating AI models and cloud HPC not only accelerates materials discovery but also showcases the potency of AI-guided experimentation in unlocking transformative scientific breakthroughs with real-world applications.

Predicting future frames of a video is challenging because it is difficult to learn the uncertainty of the underlying factors influencing their contents. In this paper, we propose a novel video prediction model, which has infinite-dimensional latent variables over the spatio-temporal domain. Specifically, we first decompose the video motion and content information, then take a neural stochastic differential equation to predict the temporal motion information, and finally, an image diffusion model autoregressively generates the video frame by conditioning on the predicted motion feature and the previous frame. The better expressiveness and stronger stochasticity learning capability of our model lead to state-of-the-art video prediction performances. As well, our model is able to achieve temporal continuous prediction, i.e., predicting in an unsupervised way the future video frames with an arbitrarily high frame rate. Our code is available at \url{https://github.com/XiYe20/STDiffProject}.

This paper presents an efficient deep neural network model for diagnosing Parkinson's disease from gait. More specifically, we introduce a hybrid ConvNet-Transformer architecture to accurately diagnose the disease by detecting the severity stage. The proposed architecture exploits the strengths of both Convolutional Neural Networks and Transformers in a single end-to-end model, where the former is able to extract relevant local features from Vertical Ground Reaction Force (VGRF) signal, while the latter allows to capture long-term spatio-temporal dependencies in data. In this manner, our hybrid architecture achieves an improved performance compared to using either models individually. Our experimental results show that our approach is effective for detecting the different stages of Parkinson's disease from gait data, with a final accuracy of 88%, outperforming other state-of-the-art AI methods on the Physionet gait dataset. Moreover, our method can be generalized and adapted for other classification problems to jointly address the feature relevance and spatio-temporal dependency problems in 1D signals. Our source code and pre-trained models are publicly available at https://github.com/SafwenNaimi/1D-Convolutional-transformer-for-Parkinson-disease-diagnosis-from-gait., Comment: 17 pages, 5 Figures, 6 Tables. Accepted for publication in Neural Computing and Applications (NCAA) 2023

Lichens are symbiotic organisms composed of fungi, algae, and/or cyanobacteria that thrive in a variety of environments. They play important roles in carbon and nitrogen cycling, and contribute directly and indirectly to biodiversity. Ecologists typically monitor lichens by using them as indicators to assess air quality and habitat conditions. In particular, epiphytic lichens, which live on trees, are key markers of air quality and environmental health. A new method of monitoring epiphytic lichens involves using time-lapse cameras to gather images of lichen populations. These cameras are used by ecologists in Newfoundland and Labrador to subsequently analyze and manually segment the images to determine lichen thalli condition and change. These methods are time-consuming and susceptible to observer bias. In this work, we aim to automate the monitoring of lichens over extended periods and to estimate their biomass and condition to facilitate the task of ecologists. To accomplish this, our proposed framework uses semantic segmentation with an effective training approach to automate monitoring and biomass estimation of epiphytic lichens on time-lapse images. We show that our method has the potential to significantly improve the accuracy and efficiency of lichen population monitoring, making it a valuable tool for forest ecologists and environmental scientists to evaluate the impact of climate change on Canada's forests. To the best of our knowledge, this is the first time that such an approach has been used to assist ecologists in monitoring and analyzing epiphytic lichens., Comment: 6 pages, 3 Figures, 8 Tables, Accepted for publication in IEEE International Conference on Machine Learning and Applications (ICMLA), copyright IEEE

In this paper, we propose a novel deep learning method based on a new Hybrid ConvNet-Transformer architecture to detect and stage Parkinson's disease (PD) from gait data. We adopt a two-step approach by dividing the problem into two sub-problems. Our Hybrid ConvNet-Transformer model first distinguishes healthy versus parkinsonian patients. If the patient is parkinsonian, a multi-class Hybrid ConvNet-Transformer model determines the Hoehn and Yahr (H&Y) score to assess the PD severity stage. Our hybrid architecture exploits the strengths of both Convolutional Neural Networks (ConvNets) and Transformers to accurately detect PD and determine the severity stage. In particular, we take advantage of ConvNets to capture local patterns and correlations in the data, while we exploit Transformers for handling long-term dependencies in the input signal. We show that our hybrid method achieves superior performance when compared to other state-of-the-art methods, with a PD detection accuracy of 97% and a severity staging accuracy of 87%. Our source code is available at: https://github.com/SafwenNaimi, Comment: 6 pages, 6 figures, 3 tables, Accepted for publication in IEEE International Conference on Machine Learning and Applications (ICMLA), copyright IEEE

Radio-frequency interference is a growing concern as wireless technology advances, with potentially life-threatening consequences like interference between radar altimeters and 5G cellular networks. Mobile transceivers mix signals with varying ratios over time, posing challenges for conventional digital signal processing (DSP) due to its high latency. These challenges will worsen as future wireless technologies adopt higher carrier frequencies and data rates. However, conventional DSPs, already on the brink of their clock frequency limit, are expected to offer only marginal speed advancements. This paper introduces a photonic processor to address dynamic interference through blind source separation (BSS). Our system-on-chip processor employs a fully integrated photonic signal pathway in the analogue domain, enabling rapid demixing of received mixtures and recovering the signal-of-interest in under 15 picoseconds. This reduction in latency surpasses electronic counterparts by more than three orders of magnitude. To complement the photonic processor, electronic peripherals based on field-programmable gate array (FPGA) assess the effectiveness of demixing and continuously update demixing weights at a rate of up to 305 Hz. This compact setup features precise dithering weight control, impedance-controlled circuit board and optical fibre packaging, suitable for handheld and mobile scenarios. We experimentally demonstrate the processor's ability to suppress transmission errors and maintain signal-to-noise ratios in two scenarios, radar altimeters and mobile communications. This work pioneers the real-time adaptability of integrated silicon photonics, enabling online learning and weight adjustments, and showcasing practical operational applications for photonic processing.

How do neural networks extract patterns from pixels? Feature visualizations attempt to answer this important question by visualizing highly activating patterns through optimization. Today, visualization methods form the foundation of our knowledge about the internal workings of neural networks, as a type of mechanistic interpretability. Here we ask: How reliable are feature visualizations? We start our investigation by developing network circuits that trick feature visualizations into showing arbitrary patterns that are completely disconnected from normal network behavior on natural input. We then provide evidence for a similar phenomenon occurring in standard, unmanipulated networks: feature visualizations are processed very differently from standard input, casting doubt on their ability to "explain" how neural networks process natural images. This can be used as a sanity check for feature visualizations. We underpin our empirical findings by theory proving that the set of functions that can be reliably understood by feature visualization is extremely small and does not include general black-box neural networks. Therefore, a promising way forward could be the development of networks that enforce certain structures in order to ensure more reliable feature visualizations., Comment: ICML 2024 camera ready version

Predicting a binary mask for an object is more accurate but also more computationally expensive than a bounding box. Polygonal masks as developed in CenterPoly can be a good compromise. In this paper, we improve over CenterPoly by enhancing the classical regression L1 loss with a novel region-based loss and a novel order loss, as well as with a new training process for the vertices prediction head. Moreover, the previous methods that predict polygonal masks use different coordinate systems, but it is not clear if one is better than another, if we abstract the architecture requirement. We therefore investigate their impact on the prediction. We also use a new evaluation protocol with oracle predictions for the detection head, to further isolate the segmentation process and better compare the polygonal masks with binary masks. Our instance segmentation method is trained and tested with challenging datasets containing urban scenes, with a high density of road users. Experiments show, in particular, that using a combination of a regression loss and a region-based loss allows significant improvements on the Cityscapes and IDD test set compared to CenterPoly. Moreover the inference stage remains fast enough to reach real-time performance with an average of 0.045 s per frame for 2048$\times$1024 images on a single RTX 2070 GPU. The code is available $\href{https://github.com/KatiaJDL/CenterPoly-v2}{\text{here}}$.

Multiple-input multiple-output (MIMO) mmWave devices broadcast multiple spatially-separated data streams simultaneously in order to increase data transfer rates. Data transfer can, however, be compromised by interference. Conventional techniques for mitigating interference require additional space and power not generally available in handheld mobile devices. Here, we propose a photonic mmWave MIMO receiver architecture capable of interference cancellation with greatly reduced space and power needs. We demonstrate real-time photonic interference cancellation with an integrated FPGA-photonic system that executes a novel zero-calibration micro-ring resonator control algorithm. The system achieves sub-second cancellation weight determination latency with sub-Nyquist sampling. We evaluate the impact of canceller design parameters on performance, establishing that effective photonic cancellation is possible in handheld devices with less than 30 ms weight determination latency.

Spiking neurons and neural networks constitute a fundamental building block for brain-inspired computing, which is posed to benefit significantly from photonic hardware implementations. In this work, we experimentally investigate an interconnected system based on an ultrafast spiking VCSEL-neuron and a silicon photonics (SiPh) integrated micro-ring resonator (MRR) weight bank, and demonstrate two different functional arrangements of these devices. First, we show that MRR weightbanks can be used in conjuction with the spiking VCSEL-neurons to perform amplitude weighting of sub-ns optical spiking signals. Second, we show that a continuous firing VCSEL-neuron can be directly modulated using a locking signal propagated through a single weighting micro-ring, and we utilize this functionality to perform optical spike firing rate-coding via thermal tuning of the micro-ring resonator. Given the significant track record of both integrated weight banks and photonic VCSEL-neurons, we believe these results demonstrate the viability of combining these two classes of devices for use in functional neuromorphic photonic systems., Comment: 9 pages, 6 figures

This paper presents a novel approach for visible-thermal infrared stereoscopy, focusing on the estimation of disparities of human silhouettes. Visible-thermal infrared stereo poses several challenges, including occlusions and differently textured matching regions in both spectra. Finding matches between two spectra with varying colors, textures, and shapes adds further complexity to the task. To address the aforementioned challenges, this paper proposes a novel approach where a high-resolution convolutional neural network is used to better capture relationships between the two spectra. To do so, a modified HRNet backbone is used for feature extraction. This HRNet backbone is capable of capturing fine details and textures as it extracts features at multiple scales, thereby enabling the utilization of both local and global information. For matching visible and thermal infrared regions, our method extracts features on each patch using two modified HRNet streams. Features from the two streams are then combined for predicting the disparities by concatenation and correlation. Results on public datasets demonstrate the effectiveness of the proposed approach by improving the results by approximately 18 percentage points on the $\leq$ 1 pixel error, highlighting its potential for improving accuracy in this task. The code of VisiTherS is available on GitHub at the following link https://github.com/philippeDG/VisiTherS., Comment: 8 pages,3 Figures,CVPR workshop

Sketching out Graphical User Interface (GUI) layout is part of the pipeline of designing a GUI and a crucial task for the success of a software application. Arranging all components inside a GUI layout manually is a time-consuming task. In order to assist designers, we developed a method named GUILGET to automatically generate GUI layouts from positional constraints represented as GUI arrangement graphs (GUI-AGs). The goal is to support the initial step of GUI design by producing realistic and diverse GUI layouts. The existing image layout generation techniques often cannot incorporate GUI design constraints. Thus, GUILGET needs to adapt existing techniques to generate GUI layouts that obey to constraints specific to GUI designs. GUILGET is based on transformers in order to capture the semantic in relationships between elements from GUI-AG. Moreover, the model learns constraints through the minimization of losses responsible for placing each component inside its parent layout, for not letting components overlap if they are inside the same parent, and for component alignment. Our experiments, which are conducted on the CLAY dataset, reveal that our model has the best understanding of relationships from GUI-AG and has the best performances in most of evaluation metrics. Therefore, our work contributes to improved GUI layout generation by proposing a novel method that effectively accounts for the constraints on GUI elements and paves the road for a more efficient GUI design pipeline., Comment: 12 pages, 5 figures, Canadian AI Conference 2023

In recent years, the joint detection-and-tracking paradigm has been a very popular way of tackling the multi-object tracking (MOT) task. Many of the methods following this paradigm use the object center keypoint for detection. However, we argue that the center point is not optimal since it is often not visible in crowded scenarios, which results in many missed detections when the objects are partially occluded. We propose TopTrack, a joint detection-and-tracking method that uses the top of the object as a keypoint for detection instead of the center because it is more often visible. Furthermore, TopTrack processes consecutive frames in separate streams in order to facilitate training. We performed experiments to show that using the object top as a keypoint for detection can reduce the amount of missed detections, which in turn leads to more complete trajectories and less lost trajectories. TopTrack manages to achieve competitive results with other state-of-the-art trackers on two MOT benchmarks., Comment: 14 pages, 7 figures, submitted to Machine Vision and Applications