With the advancement of maritime unmanned aerial vehicles (UAVs) and deep learning
technologies, the application of UAV-based object detection has become increasingly …

In the past decade, advances in deep learning have resulted in breakthroughs in a variety of
areas, including computer vision, natural language understanding, speech recognition, and …

Abstract AutoML (Automated Machine Learning) is an emerging field that aims to automate
the process of building machine learning models. AutoML emerged to increase productivity …

In this paper, we present Auto-KD, the first automated search framework for optimal
knowledge distillation design. Traditional distillation techniques typically require handcrafted …

Abstract Mixed-Precision Quantization (MQ) can achieve a competitive accuracy-complexity
trade-off for models. Conventional training-based search methods require time-consuming …

Abstract Recently, Vision Transformer (ViT) has achieved remarkable success in several
computer vision tasks. The progresses are highly relevant to the architecture design, then it …

Zero-cost proxies (ZC proxies) are a recent architecture performance prediction technique
aiming to significantly speed up algorithms for neural architecture search (NAS). Recent …

The rapid advances in Vision Transformer (ViT) refresh the state-of-the-art performances in
various vision tasks, overshadowing the conventional CNN-based models. This ignites a few …

Abstract Machine learning influences numerous aspects of modern society, empowers new
technologies, from Alphago to ChatGPT, and increasingly materializes in consumer products …

Conducting efficient performance estimations of neural architectures is a major challenge in
neural architecture search (NAS). To reduce the architecture training costs in NAS, one-shot …