A Waste Classification model in Low-illumination scenes based on ConvNeXt

Article Environmental Sciences

Waste classification using vision transformer based on multilayer hybrid convolution neural network

Fatma S. Alrayes et al.

Summary: The rapid advancement of deep learning technology has led to the development of various network architectures for classification, making it easier to implement intelligent waste classification systems. However, existing waste classification models suffer from issues such as low accuracy and slow processing. This study proposes a Vision Transformer based on Multilayer Hybrid Convolution Neural Network (VT-MLH-CNN) for automatic waste classification, which improves classification accuracy and reduces processing time. The simulation results show that the proposed method outperforms certain current techniques with a simplified network model and higher waste categorization accuracy, achieving a classification accuracy of up to 95.8% on the TrashNet dataset.

URBAN CLIMATE (2023)

添加到收藏夹

Article Engineering, Environmental

A multi-label waste detection model based on transfer learning

Qiang Zhang et al.

Summary: Accurate and efficient treatment of domestic waste is crucial for urban management, and the effectiveness of waste classification directly impacts the sustainable development of human society. This study proposes a YOLO-WASTE multi-label waste classification model based on transfer learning, which enables fast recognition and classification of multiple wastes.

RESOURCES CONSERVATION AND RECYCLING (2022)

添加到收藏夹

Article Construction & Building Technology

Robot for automatic waste sorting on construction sites

Xinxing Chen et al.

Summary: This paper presents a robot for recycling C&D waste, which achieves real-time navigation through SLAM and utilizes deep learning and high-precision object pickup strategy for accurate identification and stable grasping of waste items.

AUTOMATION IN CONSTRUCTION (2022)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

A ConvNet for the 2020s

Zhuang Liu et al.

Summary: The development of visual recognition has gone through stages from ConvNets to ViTs and then to hybrid approaches. In this work, the design of a pure ConvNet is reexamined and several key components are discovered, resulting in the construction of the ConvNeXt model series. These models compete with Transformers in terms of accuracy and performance while maintaining the simplicity and efficiency of ConvNets.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2022)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Toward Fast, Flexible, and Robust Low-Light Image Enhancement

Long Ma et al.

Summary: This paper proposes a new Self-Calibrated Illumination (SCI) learning framework for enhancing image brightness in real-world low-light scenarios. The framework achieves a balance between computational efficiency and visual quality through cascaded illumination learning, weight sharing, and a self-calibrated module.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022) (2022)

添加到收藏夹

Article Computer Science, Information Systems