Related papers: Sup3r: A Semi-Supervised Algorithm for increasing …

This paper proposes an unsupervised address event representation (AER) object recognition approach. The proposed approach consists of a novel multiscale spatio-temporal feature (MuST) representation of input AER events and a spiking neural…

Weight sharing promises to make neural architecture search (NAS) tractable even on commodity hardware. Existing methods in this space rely on a diverse set of heuristics to design and train the shared-weight backbone network, a.k.a. the…

Time series are ubiquitous and therefore inherently hard to analyze and ultimately to label or cluster. With the rise of the Internet of Things (IoT) and its smart devices, data is collected in large amounts any given second. The collected…

Post-training Sparsity (PTS) is a recently emerged avenue that chases efficient network sparsity with limited data in need. Existing PTS methods, however, undergo significant performance degradation compared with traditional methods that…

Self-supervised learning has been shown to be very effective in learning useful representations, and yet much of the success is achieved in data types such as images, audio, and text. The success is mainly enabled by taking advantage of…

Accurate and robust weather forecasting remains a fundamental challenge due to the inherent spatio-temporal complexity of atmospheric systems. In this paper, we propose a novel self-supervised learning framework that leverages…

By driving models to converge to flat minima, sharpness-aware learning algorithms (such as SAM) have shown the power to achieve state-of-the-art performances. However, these algorithms will generally incur one extra forward-backward…

This paper explores the promising interplay between spiking neural networks (SNNs) and event-based cameras for privacy-preserving human action recognition (HAR). The unique feature of event cameras in capturing only the outlines of motion,…

Recent progress in neural forecasting accelerated improvements in the performance of large-scale forecasting systems. Yet, long-horizon forecasting remains a very difficult task. Two common challenges afflicting the task are the volatility…

Neuromorphic Systems-on-Chip (NSoCs) are becoming heterogeneous by integrating general-purpose processors (GPPs) and neural processing units (NPUs) on the same SoC. For embedded systems, an NSoC may need to execute user applications built…

3D image reconstruction from a limited number of 2D images has been a long-standing challenge in computer vision and image analysis. While deep learning-based approaches have achieved impressive performance in this area, existing deep…

We explore the task of zero-shot semantic segmentation of 3D shapes by using large-scale off-the-shelf 2D image recognition models. Surprisingly, we find that modern zero-shot 2D object detectors are better suited for this task than…

Crop type classification using optical satellite time series remains limited in its ability to generalize across seasons, particularly when crop phenology shifts due to inter-annual weather variability. This hampers real-world applicability…

Hypergraph-based machine learning methods are now widely recognized as important for modeling and using higher-order and multiway relationships between data objects. Local hypergraph clustering and semi-supervised learning specifically…

Most recent neural semi-supervised learning algorithms rely on adding small perturbation to either the input vectors or their representations. These methods have been successful on computer vision tasks as the images form a continuous…

Radar-based Human Activity Recognition (HAR) offers privacy and robustness over camera-based methods, yet remains computationally demanding for edge deployment. We present the first use of Spiking Neural Networks (SNNs) for radar-based HAR…

Developing neuromorphic intelligence on event-based datasets with Spiking Neural Networks (SNNs) has recently attracted much research attention. However, the limited size of event-based datasets makes SNNs prone to overfitting and unstable…

This paper presents HITNet, a novel neural network architecture for real-time stereo matching. Contrary to many recent neural network approaches that operate on a full cost volume and rely on 3D convolutions, our approach does not…

In the recent years, there is a growing interest in semi-supervised learning, since, in many learning tasks, there is a plentiful supply of unlabeled data, but insufficient labeled ones. Hence, Semi-Supervised learning models can benefit…

3D object detection from LiDAR point cloud is of critical importance for autonomous driving and robotics. While sequential point cloud has the potential to enhance 3D perception through temporal information, utilizing these temporal…