Zobrazeno 1 - 10
of 66
pro vyhledávání: '"Peng, Peixi"'
With the benefit of deep learning techniques, recent researches have made significant progress in image compression artifacts reduction. Despite their improved performances, prevailing methods only focus on learning a mapping from the compressed imag
Externí odkaz:
http://arxiv.org/abs/2405.09291
Traffic signal control has a great impact on alleviating traffic congestion in modern cities. Deep reinforcement learning (RL) has been widely used for this task in recent years, demonstrating promising performance but also facing many challenges suc
Externí odkaz:
http://arxiv.org/abs/2404.00886
As a general method for exploration in deep reinforcement learning (RL), NoisyNet can produce problem-specific exploration strategies. Spiking neural networks (SNNs), due to their binary firing mechanism, have strong robustness to noise, making it di
Externí odkaz:
http://arxiv.org/abs/2403.04162
One important desideratum of lifelong learning aims to discover novel classes from unlabelled data in a continuous manner. The central challenge is twofold: discovering and learning novel classes while mitigating the issue of catastrophic forgetting
Externí odkaz:
http://arxiv.org/abs/2403.03382
With the help of special neuromorphic hardware, spiking neural networks (SNNs) are expected to realize artificial intelligence (AI) with less energy consumption. It provides a promising energy-efficient way for realistic control tasks by combining SN
Externí odkaz:
http://arxiv.org/abs/2401.05444
The sparsity of Deep Neural Networks is well investigated to maximize the performance and reduce the size of overparameterized networks as possible. Existing methods focus on pruning parameters in the training process by using thresholds and metrics.
Externí odkaz:
http://arxiv.org/abs/2307.07389
Autor:
Zhai, Yunpeng, Peng, Peixi, Jia, Mengxi, Li, Shiyong, Chen, Weiqiang, Gao, Xuesong, Tian, Yonghong
Unsupervised person re-identification has achieved great success through the self-improvement of individual neural networks. However, limited by the lack of diversity of discriminant information, a single network has difficulty learning sufficient di
Externí odkaz:
http://arxiv.org/abs/2306.05236
Publikováno v:
in IEEE Transactions on Circuits and Systems for Video Technology, vol. 33, no. 4, pp. 1884-1898, April 2023
The sensitivity of deep neural networks to compressed images hinders their usage in many real applications, which means classification networks may fail just after taking a screenshot and saving it as a compressed file. In this paper, we argue that n
Externí odkaz:
http://arxiv.org/abs/2304.10714
Few-shot class-incremental learning (FSCIL) aims at learning to classify new classes continually from limited samples without forgetting the old classes. The mainstream framework tackling FSCIL is first to adopt the cross-entropy (CE) loss for traini
Externí odkaz:
http://arxiv.org/abs/2304.00426
Due to the binary spike signals making converting the traditional high-power multiply-accumulation (MAC) into a low-power accumulation (AC) available, the brain-inspired Spiking Neural Networks (SNNs) are gaining more and more attention. However, the
Externí odkaz:
http://arxiv.org/abs/2301.11929