Related papers: Efficient Few-Shot Learning for Edge AI via Knowle…
In recent years, deep neural networks have been successful in both industry and academia, especially for computer vision tasks. The great success of deep learning is mainly due to its scalability to encode large-scale data and to maneuver…
With the prosperity of mobile devices, the distributed learning approach enabling model training with decentralized data has attracted wide research. However, the lack of training capability for edge devices significantly limits the energy…
While test-time fine-tuning is beneficial in few-shot learning, the need for multiple backpropagation steps can be prohibitively expensive in real-time or low-resource scenarios. To address this limitation, we propose an approach that…
We propose a novel knowledge distillation approach, CustomKD, that effectively leverages large vision foundation models (LVFMs) to enhance the performance of edge models (e.g., MobileNetV3). Despite recent advancements in LVFMs, such as…
Few-shot learning (FSL) via customization of a deep learning network with limited data has emerged as a promising technique to achieve personalized user experiences on edge devices. However, existing FSL methods primarily assume independent…
Transformer-based reinforcement learning has emerged as a strong candidate for sequential control in residential energy management. In particular, the Decision Transformer can learn effective battery dispatch policies from historical data,…
In recent years, deep learning has been widely applied in communications and achieved remarkable performance improvement. Most of the existing works are based on data-driven deep learning, which requires a significant amount of training…
The deployment of transformer-based models on resource-constrained edge devices represents a critical challenge in enabling real-time artificial intelligence applications. This comprehensive survey examines lightweight transformer…
With the advent of strong pre-trained natural language processing models like BERT, DeBERTa, MiniLM, T5, the data requirement for industries to fine-tune these models to their niche use cases has drastically reduced (typically to a few…
Logit-based knowledge distillation (KD) for classification is cost-efficient compared to feature-based KD but often subject to inferior performance. Recently, it was shown that the performance of logit-based KD can be improved by…
Learn in-situ is a growing trend for Edge AI. Training deep neural network (DNN) on edge devices is challenging because both energy and memory are constrained. Low precision training helps to reduce the energy cost of a single training…
In instance-level detection tasks (e.g., object detection), reducing input resolution is an easy option to improve runtime efficiency. However, this option traditionally hurts the detection performance much. This paper focuses on boosting…
The concept of compressing deep Convolutional Neural Networks (CNNs) is essential to use limited computation, power, and memory resources on embedded devices. However, existing methods achieve this objective at the cost of a drop in…
Current state-of-the-art object detectors are at the expense of high computational costs and are hard to deploy to low-end devices. Knowledge distillation, which aims at training a smaller student network by transferring knowledge from a…
Few-shot Learning aims to learn and distinguish new categories with a very limited number of available images, presenting a significant challenge in the realm of deep learning. Recent researchers have sought to leverage the additional…
Deep neural network compression techniques such as pruning and weight tensor decomposition usually require fine-tuning to recover the prediction accuracy when the compression ratio is high. However, conventional fine-tuning suffers from the…
Edge computation offloading allows mobile end devices to put execution of compute-intensive task on the edge servers. End devices can decide whether offload the tasks to edge servers, cloud servers or execute locally according to current…
Data collected by IoT devices are often private and have a large diversity across users. Therefore, learning requires pre-training a model with available representative data samples, deploying the pre-trained model on IoT devices, and…
Deep learning models have introduced various intelligent applications to edge devices, such as image classification, speech recognition, and augmented reality. There is an increasing need of training such models on the devices in order to…
We applied few-shot in-context learning on the OPT-1.3B model for the natural language inference task and employed knowledge distillation to internalize the context information, reducing model parameter from 1.3B to 125M and achieving a…