Reconstructing seen image from brain activity by visually-guided cognitive representation and adversarial learning

•We combined a dual-VAE structure with GAN to build a D-Vae/Gan framework.•Gan-based inter-modality knowledge distillation was introduced for feature learning.•Model training process was divided into cascade stages with a three-stage strategy.•Reconstructions on four fMRI datasets were objectively and subjectively identifiable. Reconstructing perceived stimulus (image) only from human brain activity measured with functional Magnetic Resonance Imaging (fMRI) is a significant task in brain decoding. However, the inconsistent distribution and representation between fMRI signals and visual images cause great ‘domain gap’. Moreover, the limited fMRI data instances generally suffer from the issues of low signal noise ratio (SNR), extremely high dimensionality, and limited spatial resolution. Existing methods are often affected by these issues so that a satisfactory reconstruction is still an open problem. In this paper, we show that it is possible to obtain a promising solution by learning visually-guided latent cognitive representations from the fMRI signals, and inversely decoding them to the image stimuli. The resulting framework is called Dual-Variational Autoencoder/ Generative Adversarial Network (D-Vae/Gan), which combines the advantages of adversarial representation learning with knowledge distillation. In addition, we introduce a novel three-stage learning strategy which enables the (cognitive) encoder to gradually distill useful knowledge from the paired (visual) encoder during the learning process. Extensive experimental results on both artificial and natural images have demonstrated that our method could achieve surprisingly good results and outperform the available alternatives.