Improved Residual Network based on norm-preservation for visual recognition

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

Article Telecommunications

An Improved DV-maxHop Localization Algorithm for Wireless Sensor Networks

Aishwarya Gupta et al.

Summary: Location information has played a significant role in various Wireless Sensor Network applications in recent years. Our research focuses on range-free algorithms and proposes an Improved DV-maxHop algorithm to accurately localize sensors in anisotropic networks. Simulation results demonstrate that our algorithm efficiently minimizes localization error without the need for additional hardware or increased communication overhead.

WIRELESS PERSONAL COMMUNICATIONS (2021)

添加到收藏夹

Article Computer Science, Hardware & Architecture

Understanding Deep Learning (Still) Requires Rethinking Generalization

Chiyuan Zhang et al.

Summary: Despite traditional explanations falling short in justifying the excellent generalization of large neural networks, experiments show that state-of-the-art convolutional networks can easily adapt to random labeling during training, indicating a different mechanism contributing to their strong performance in practice.

COMMUNICATIONS OF THE ACM (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Optimizing Deeper Spiking Neural Networks for Dynamic Vision Sensing

Youngeun Kim et al.

Summary: Spiking Neural Networks (SNNs) are considered a new generation of low-power deep neural networks due to their sparse, asynchronous, and binary event-driven processing characteristics. To improve the training effectiveness of deep SNNs, novel algorithmic and architectural advances like SALT and Switched-BN have been proposed.

NEURAL NETWORKS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Inductive Structure Consistent Hashing via Flexible Semantic Calibration

Zheng Zhang et al.

Summary: The proposed inductive structure consistent hashing (ISCH) method effectively coordinates semantic correlations between the visual feature space, the binary class space, and the discrete hashing space.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2021)

添加到收藏夹

Review Computer Science, Artificial Intelligence

A survey on modern trainable activation functions

Andrea Apicella et al.

Summary: In recent years, there has been a renewed interest in trainable activation functions, which can be trained during the learning process to improve neural network performance. Various models of trainable activation functions have been proposed in the literature, many of which are equivalent to adding neuron layers with fixed activation functions and simple local rules.

NEURAL NETWORKS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence