IEEE

Improving Object Detection of Intelligent Vehicles Through Self-Training with Accurate Labeling and Class Balancing

Abstract: Self-training is a novel learning paradigm that generates pseudolabels for unlabeled data, enabling deep learning models to be trained without the need for humanlabeled data. This article ...
Scientific Research Publishing

A Study on Consumer Preferences for Electric Vehicle Charging and Battery Swapping Based on User-Generated Content Analysis ()

With the rapid expansion of the new energy vehicle (NEV) market, charging and battery swapping have emerged as the two ...
IEEE

SOSNet: Real-Time Small Object Segmentation via Hierarchical Decoding and Example Mining

Abstract: Real-time semantic segmentation plays an important role in auto vehicles. However, most real-time small object segmentation methods fail to obtain satisfactory performance on small objects, ...
GitHub

PyCIL: A Python Toolbox for Class-Incremental Learning

Welcome to PyCIL, perhaps the toolbox for class-incremental learning with the most implemented methods. This is the code repository for "PyCIL: A Python Toolbox for Class-Incremental Learning" [paper] ...
GitHub

Class-agnostic Object Detection with Multi-modal Transformer (ECCV 2022)

(Nov 25, 2021) Evaluation code along with pre-trained models & pre-computed predictions is released. evaluation/README.md Abstract: What constitutes an object? This has been a long-standing question ...