Related papers: Assessing the Performance of Analog Training for T…
Transfer learning represents a recent paradigm shift in the way we build artificial intelligence (AI) systems. In contrast to training task-specific models, transfer learning involves pre-training deep learning models on a large corpus of…
Convolutional neural networks have achieved excellent results in compressed video quality enhancement task in recent years. State-of-the-art methods explore the spatiotemporal information of adjacent frames mainly by deformable convolution.…
Multi-Task Learning (MTL) networks have emerged as a promising method for transferring learned knowledge across different tasks. However, MTL must deal with challenges such as: overfitting to low resource tasks, catastrophic forgetting, and…
Non-autoregressive machine translation (NAT) has recently made great progress. However, most works to date have focused on standard translation tasks, even though some edit-based NAT models, such as the Levenshtein Transformer (LevT), seem…
This paper revisits the temporal difference (TD) learning algorithm for the policy evaluation tasks in reinforcement learning. Typically, the performance of TD(0) and TD($\lambda$) is very sensitive to the choice of stepsizes. Oftentimes,…
Inspired by the human brain's ability to adapt to new tasks without erasing prior knowledge, we develop spiking neural networks (SNNs) with dynamic structures for Class Incremental Learning (CIL). Our comparative experiments reveal that…
This article presents a comprehensive survey of online test-time adaptation (OTTA), focusing on effectively adapting machine learning models to distributionally different target data upon batch arrival. Despite the recent proliferation of…
Deep learning models have demonstrated exceptional performance across a wide range of computer vision tasks. However, their performance often degrades significantly when faced with distribution shifts, such as domain or dataset changes.…
Vision Transformers (ViTs) have demonstrated remarkable potential in image processing tasks by utilizing self-attention mechanisms to capture global relationships within data. However, their scalability is hindered by significant…
Action recognition in videos poses a challenge due to its high computational cost, especially for Joint Space-Time video transformers (Joint VT). Despite their effectiveness, the excessive number of tokens in such architectures…
On-device learning remains a formidable challenge, especially when dealing with resource-constrained devices that have limited computational capabilities. This challenge is primarily rooted in two key issues: first, the memory available on…
Deploying sophisticated deep learning models on embedded devices with the purpose of solving real-world problems is a struggle using today's technology. Privacy and data limitations, network connection issues, and the need for fast model…
The planning problem constitutes a fundamental aspect of the autonomous driving framework. Recent strides in representation learning have empowered vehicles to comprehend their surrounding environments, thereby facilitating the integration…
In this paper we present an algorithm-hardware codesign for camera-based autonomous flight in small drones. We show that the large write-latency and write-energy for nonvolatile memory (NVM) based embedded systems makes them unsuitable for…
Vision Transformers has demonstrated competitive performance on computer vision tasks benefiting from their ability to capture long-range dependencies with multi-head self-attention modules and multi-layer perceptron. However, calculating…
Transfer learning (TL) leverages previously obtained knowledge to learn new tasks efficiently and has been used to train deep learning (DL) models with limited amount of data. When TL is applied to DL, pretrained (teacher) models are…
Vision Transformer (ViT) has demonstrated significant potential in various vision tasks due to its strong ability in modelling long-range dependencies. However, such success is largely fueled by training on massive samples. In real…
Although Vision Transformers (ViTs) have become the standard architecture in computer vision, their massive sizes lead to significant computational overhead. Token compression techniques have attracted considerable attention to address this…
Vision Transformers (ViTs) have established new performance benchmarks in vision tasks such as image recognition and object detection. However, these advancements come with significant demands for memory and computational resources,…
Artificial intelligence (AI) based downlink channel state information (CSI) prediction for frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems has attracted growing attention recently. However, existing…