Attention mechanisms have played a crucial role in the development of complex architectures such as Transformers in natural language processing. However, Transformers remain hard to interpret and are considered as black-boxes. This paper aims to assess how attention coefficients from Transformers can help in providing interpretability. A new attention-based interpretability method called CLaSsification-Attention (CLS-A) is proposed. CLS-A computes an interpretability score for each word based on the attention coefficient distribution related to the part specific to the classification task within the Transformer architecture. A human-grounded experiment is conducted to evaluate and compare CLS-A to other interpretability methods. The experimental protocol relies on the capacity of an interpretability method to provide explanation in line with human reasoning. Experiment design includes measuring reaction times and correct response rates by human subjects. CLS-A performs comparably to usual interpretability methods regarding average participant reaction time and accuracy. The lower computational cost of CLS-A compared to other interpretability methods and its availability by design within the classifier make it particularly interesting. Data analysis also highlights the link between the probability score of a classifier prediction and adequate explanations. Finally, our work confirms the relevancy of the use of CLS-A and shows to which extent self-attention contains rich information to explain Transformer classifiers.
Neuromorphic (event-based) image sensors draw inspiration from the human-retina to create an electronic device that can process visual stimuli in a way that closely resembles its biological counterpart. These sensors process information significantly different than the traditional RGB sensors. Specifically, the sensory information generated by event-based image sensors are orders of magnitude sparser compared to that of RGB sensors. The first generation of neuromorphic image sensors, Dynamic Vision Sensor (DVS), are inspired by the computations confined to the photoreceptors and the first retinal synapse. In this work, we highlight the capability of the second generation of neuromorphic image sensors, Integrated Retinal Functionality in CMOS Image Sensors (IRIS), which aims to mimic full retinal computations from photoreceptors to output of the retina (retinal ganglion cells) for targeted feature-extraction. The feature of choice in this work is Object Motion Sensitivity (OMS) that is processed locally in the IRIS sensor. We study the capability of OMS in solving the ego-motion problem of the event-based cameras. Our results show that OMS can accomplish standard computer vision tasks with similar efficiency to conventional RGB and DVS solutions but offers drastic bandwidth reduction. This cuts the wireless and computing power budgets and opens up vast opportunities in high-speed, robust, energy-efficient, and low-bandwidth real-time decision making.
The introduction of image-guided surgical navigation (IGSN) has greatly benefited technically demanding surgical procedures by providing real-time support and guidance to the surgeon during surgery. To develop effective IGSN, a careful selection of the information provided to the surgeon is needed. However, identifying optimal feedback modalities is challenging due to the broad array of available options. To address this problem, we have developed an open-source library that facilitates the development of multimodal navigation systems in a wide range of surgical procedures relying on medical imaging data. To provide guidance, our system calculates the minimum distance between the surgical instrument and the anatomy and then presents this information to the user through different mechanisms. The real-time performance of our approach is achieved by calculating Signed Distance Fields at initialization from segmented anatomical volumes. Using this framework, we developed a multimodal surgical navigation system to help surgeons navigate anatomical variability in a skull-base surgery simulation environment. Three different feedback modalities were explored: visual, auditory, and haptic. To evaluate the proposed system, a pilot user study was conducted in which four clinicians performed mastoidectomy procedures with and without guidance. Each condition was assessed using objective performance and subjective workload metrics. This pilot user study showed improvements in procedural safety without additional time or workload. These results demonstrate our pipeline's successful use case in the context of mastoidectomy.
Time Series Forecasting has been an active area of research due to its many applications ranging from network usage prediction, resource allocation, anomaly detection, and predictive maintenance. Numerous publications published in the last five years have proposed diverse sets of objective loss functions to address cases such as biased data, long-term forecasting, multicollinear features, etc. In this paper, we have summarized 14 well-known regression loss functions commonly used for time series forecasting and listed out the circumstances where their application can aid in faster and better model convergence. We have also demonstrated how certain categories of loss functions perform well across all data sets and can be considered as a baseline objective function in circumstances where the distribution of the data is unknown. Our code is available at GitHub: https://github.com/aryan-jadon/Regression-Loss-Functions-in-Time-Series-Forecasting-Tensorflow.
Artificial intelligence is creating one of the biggest revolution across technology driven application fields. For the finance sector, it offers many opportunities for significant market innovation and yet broad adoption of AI systems heavily relies on our trust in their outputs. Trust in technology is enabled by understanding the rationale behind the predictions made. To this end, the concept of eXplainable AI emerged introducing a suite of techniques attempting to explain to users how complex models arrived at a certain decision. For cross-sectional data classical XAI approaches can lead to valuable insights about the models' inner workings, but these techniques generally cannot cope well with longitudinal data (time series) in the presence of dependence structure and non-stationarity. We here propose a novel XAI technique for deep learning methods which preserves and exploits the natural time ordering of the data.
The current approach to marking attendance in colleges is tedious and time consuming. I propose AttenFace, a standalone system to analyze, track and grant attendance in real time using face recognition. Using snapshots of class from live camera feed, the system identifies students and marks them as present in a class based on their presence in multiple snapshots taken throughout the class duration. Face recognition for each class is performed independently and in parallel, ensuring that the system scales with number of concurrent classes. Further, the separation of the face recognition server from the back-end server for attendance calculation allows the face recognition module to be integrated with existing attendance tracking software like Moodle. The face recognition algorithm runs at 10 minute intervals on classroom snapshots, significantly reducing computation compared to direct processing of live camera feed. This method also provides students the flexibility to leave class for a short duration (such as for a phone call) without losing attendance for that class. Attendance is granted to a student if he remains in class for a number of snapshots above a certain threshold. The system is fully automatic and requires no professor intervention or any form of manual attendance or even camera set-up, since the back-end directly interfaces with in-class cameras. AttenFace is a first-of-its-kind one-stop solution for face-recognition-enabled attendance in educational institutions that prevents proxy, handling all aspects from students checking attendance to professors deciding their own attendance policy, to college administration enforcing default attendance rules.
Denoising diffusion models are a popular class of generative models providing state-of-the-art results in many domains. One adds gradually noise to data using a diffusion to transform the data distribution into a Gaussian distribution. Samples from the generative model are then obtained by simulating an approximation of the time-reversal of this diffusion initialized by Gaussian samples. Practically, the intractable score terms appearing in the time-reversed process are approximated using score matching techniques. We explore here a similar idea to sample approximately from unnormalized probability density functions and estimate their normalizing constants. We consider a process where the target density diffuses towards a Gaussian. Denoising Diffusion Samplers (DDS) are obtained by approximating the corresponding time-reversal. While score matching is not applicable in this context, we can leverage many of the ideas introduced in generative modeling for Monte Carlo sampling. Existing theoretical results from denoising diffusion models also provide theoretical guarantees for DDS. We discuss the connections between DDS, optimal control and Schr\"odinger bridges and finally demonstrate DDS experimentally on a variety of challenging sampling tasks.
Effective use of camera-based vision systems is essential for robust performance in autonomous off-road driving, particularly in the high-speed regime. Despite success in structured, on-road settings, current end-to-end approaches for scene prediction have yet to be successfully adapted for complex outdoor terrain. To this end, we present TerrainNet, a vision-based terrain perception system for semantic and geometric terrain prediction for aggressive, off-road navigation. The approach relies on several key insights and practical considerations for achieving reliable terrain modeling. The network includes a multi-headed output representation to capture fine- and coarse-grained terrain features necessary for estimating traversability. Accurate depth estimation is achieved using self-supervised depth completion with multi-view RGB and stereo inputs. Requirements for real-time performance and fast inference speeds are met using efficient, learned image feature projections. Furthermore, the model is trained on a large-scale, real-world off-road dataset collected across a variety of diverse outdoor environments. We show how TerrainNet can also be used for costmap prediction and provide a detailed framework for integration into a planning module. We demonstrate the performance of TerrainNet through extensive comparison to current state-of-the-art baselines for camera-only scene prediction. Finally, we showcase the effectiveness of integrating TerrainNet within a complete autonomous-driving stack by conducting a real-world vehicle test in a challenging off-road scenario.
Whilst the availability of 3D LiDAR point cloud data has significantly grown in recent years, annotation remains expensive and time-consuming, leading to a demand for semi-supervised semantic segmentation methods with application domains such as autonomous driving. Existing work very often employs relatively large segmentation backbone networks to improve segmentation accuracy, at the expense of computational costs. In addition, many use uniform sampling to reduce ground truth data requirements for learning needed, often resulting in sub-optimal performance. To address these issues, we propose a new pipeline that employs a smaller architecture, requiring fewer ground-truth annotations to achieve superior segmentation accuracy compared to contemporary approaches. This is facilitated via a novel Sparse Depthwise Separable Convolution module that significantly reduces the network parameter count while retaining overall task performance. To effectively sub-sample our training data, we propose a new Spatio-Temporal Redundant Frame Downsampling (ST-RFD) method that leverages knowledge of sensor motion within the environment to extract a more diverse subset of training data frame samples. To leverage the use of limited annotated data samples, we further propose a soft pseudo-label method informed by LiDAR reflectivity. Our method outperforms contemporary semi-supervised work in terms of mIoU, using less labeled data, on the SemanticKITTI (59.5@5%) and ScribbleKITTI (58.1@5%) benchmark datasets, based on a 2.3x reduction in model parameters and 641x fewer multiply-add operations whilst also demonstrating significant performance improvement on limited training data (i.e., Less is More).
It has long been hypothesized that operating close to the critical state is beneficial for natural, artificial and their evolutionary systems. We put this hypothesis to test in a system of evolving foraging agents controlled by neural networks that can adapt agents' dynamical regime throughout evolution. Surprisingly, we find that all populations that discover solutions, evolve to be subcritical. By a resilience analysis, we find that there are still benefits of starting the evolution in the critical regime. Namely, initially critical agents maintain their fitness level under environmental changes (for example, in the lifespan) and degrade gracefully when their genome is perturbed. At the same time, initially subcritical agents, even when evolved to the same fitness, are often inadequate to withstand the changes in the lifespan and degrade catastrophically with genetic perturbations. Furthermore, we find the optimal distance to criticality depends on the task complexity. To test it we introduce a hard and simple task: for the hard task, agents evolve closer to criticality whereas more subcritical solutions are found for the simple task. We verify that our results are independent of the selected evolutionary mechanisms by testing them on two principally different approaches: a genetic algorithm and an evolutionary strategy. In summary, our study suggests that although optimal behaviour in the simple task is obtained in a subcritical regime, initializing near criticality is important to be efficient at finding optimal solutions for new tasks of unknown complexity.