Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation

Yushun Tang1; Ce Zhang1; Heng Xu1; Shuoshuo Chen1; Jie Cheng2; Luziwei Leng2; Qinghai Guo2; Zhihai He1

10.1109/CVPR52729.2023.00363

2023

1063-6919

979-8-3503-0130-4

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

2023-June

3728-3738

17-24 June 2023

Vancouver, BC, Canada

Fully test-time adaptation aims to adapt the network model based on sequential analysis of input samples during the inference stage to address the cross-domain performance degradation problem of deep neural networks. We take inspiration from the biological plausibility learning where the neuron responses are tuned based on a local synapse-change procedure and activated by competitive lateral inhibition rules. Based on these feed-forward learning rules, we design a soft Hebbian learning process which provides an unsupervised and effective mechanism for online adaptation. We observe that the performance of this feed-forward Hebbian learning for fully test-time adaptation can be significantly improved by incorporating a feedback neuromodulation layer. It is able to fine-tune the neuron responses based on the external feedback generated by the error backpropagation from the top inference layers. This leads to our proposed neuro-modulated Hebbian learning (NHL) method for fully test-time adaptation. With the unsupervised feed-forward soft Hebbian learning being combined with a learned neuromodulator to capture feedback from external responses, the source model can be effectively adapted during the testing process. Experimental results on benchmark datasets demonstrate that our proposed method can significantly improve the adaptation performance of network models and outperforms existing state-of-the-art methods.

Transfer meta low-shot continual or long-tail learning

第一

CPCI-S ; EI

WOS:001058542604006

20234114868428

IEEE

1.Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China
2.Advanced Computing and Storage Laboratory, Huawei Technologies Co., Ltd., Shenzhen, China

Yushun Tang,Ce Zhang,Heng Xu,et al. Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation[C],2023:3728-3738.