Zobrazeno 1 - 10
of 43
pro vyhledávání: '"Chang, Jingfei"'
The detection of abusive language remains a long-standing challenge with the extensive use of social networks. The detection task of abusive language suffers from limited accuracy. We argue that the existing detection methods utilize the fine-tuning
Externí odkaz:
http://arxiv.org/abs/2403.05268
The multi-modal hashing method is widely used in multimedia retrieval. It can fuse multi-source data to generate binary hash code. However, the current multi-modal methods have the problem of low retrieval accuracy. The reason is that the individual
Externí odkaz:
http://arxiv.org/abs/2308.11797
Weight and activation binarization can efficiently compress deep neural networks and accelerate model inference, but cause severe accuracy degradation. Existing optimization methods for binary neural networks (BNNs) focus on fitting full-precision ne
Externí odkaz:
http://arxiv.org/abs/2210.02637
Autor:
Chang, Jingfei, Tao, Liping, Lyu, Bo, Zhu, Xiangming, Liu, Shanyun, Zou, Qiaosha, Chen, Hongyang
Publikováno v:
In Information Sciences September 2024 678
With the increase of structure complexity, convolutional neural networks (CNNs) take a fair amount of computation cost. Meanwhile, existing research reveals the salient parameter redundancy in CNNs. The current pruning methods can compress CNNs with
Externí odkaz:
http://arxiv.org/abs/2108.13591
Publikováno v:
In Information Sciences March 2024 661
In this work, we study the binary neural networks (BNNs) of which both the weights and activations are binary (i.e., 1-bit representation). Feature representation is critical for deep neural networks, while in BNNs, the features only differ in signs.
Externí odkaz:
http://arxiv.org/abs/2103.02394
As the convolutional neural network (CNN) gets deeper and wider in recent years, the requirements for the amount of data and hardware resources have gradually increased. Meanwhile, CNN also reveals salient redundancy in several tasks. The existing ma
Externí odkaz:
http://arxiv.org/abs/2101.06407
Autor:
Chang, Jingfei
The existing convolutional neural network pruning algorithms can be divided into two categories: coarse-grained clipping and fine-grained clipping. This paper proposes a coarse and fine-grained automatic pruning algorithm, which can achieve more effi
Externí odkaz:
http://arxiv.org/abs/2010.06379
To apply deep CNNs to mobile terminals and portable devices, many scholars have recently worked on the compressing and accelerating deep convolutional neural networks. Based on this, we propose a novel uniform channel pruning (UCP) method to prune de
Externí odkaz:
http://arxiv.org/abs/2010.01251