# Learning Robust Deep Visual Representations from EEG Brain Recordings

arXiv: https://arxiv.org/abs/2310.16532 · HTML: https://mlsanity.com/paper/2310.16532/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 50 references that are in the map.
- First posted on arXiv 25 Oct 2023.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets](https://mlsanity.com/paper/2202.00273/) (2022)
- [Differentiable Augmentation for Data-Efficient GAN Training](https://mlsanity.com/paper/2006.10738/) (2020)
- [Decoding speech perception from non-invasive brain recordings](https://mlsanity.com/paper/2208.12266/) (2022)
- [Deep Learning Human Mind for Automated Visual Classification](https://mlsanity.com/paper/1609.00344/) (2016)
- [EEG2IMAGE: Image Reconstruction from EEG Brain Signals](https://mlsanity.com/paper/2302.10121/) (2023)
- [NoisyTwins: Class-Consistent and Diverse Image Generation through StyleGANs](https://mlsanity.com/paper/2304.05866/) (2023)
- [Cogni-Net: Cognitive Feature Learning through Deep Visual Perception](https://mlsanity.com/paper/1811.00201/) (2018)
- [An Evoked Potential-Guided Deep Learning Brain Representation For Visual Classification](https://mlsanity.com/paper/2006.15357/) (2020)
- [See What You See: Self-supervised Cross-modal Retrieval of Visual Stimuli from Brain Activity](https://mlsanity.com/paper/2208.03666/) (2022)

## Built on by (most cited first, 26 of 26)

- [BrainVis: Exploring the Bridge between Brain and Visual Signals via Image Reconstruction](https://mlsanity.com/paper/2312.14871/) (2023)
- [Mind's Eye: Image Recognition by EEG via Multimodal Similarity-Keeping Contrastive Learning](https://mlsanity.com/paper/2406.16910/) (2024)
- [Guess What I Think: Streamlined EEG-to-Image Generation with Latent Diffusion Models](https://mlsanity.com/paper/2410.02780/) (2024)
- [BrainDreamer: Reasoning-Coherent and Controllable Image Generation from EEG Brain Signals via Language Guidance](https://mlsanity.com/paper/2409.14021/) (2024)
- [Foundation Models for Cross-Domain EEG Analysis Application: A Survey](https://mlsanity.com/paper/2508.15716/) (2025)
- [A Survey of Spatio-Temporal EEG data Analysis: from Models to Applications](https://mlsanity.com/paper/2410.08224/) (2024)
- [EEG-Driven 3D Object Reconstruction with Style Consistency and Diffusion Prior](https://mlsanity.com/paper/2410.20981/) (2024)
- [A Survey on Bridging EEG Signals and Generative AI: From Image and Text to Beyond](https://mlsanity.com/paper/2502.12048/) (2025)
- [Alljoined1 -- A dataset for EEG-to-Image decoding](https://mlsanity.com/paper/2404.05553/) (2024)
- [EIT-1M: One Million EEG-Image-Text Pairs for Human Visual-textual Recognition and More](https://mlsanity.com/paper/2407.01884/) (2024)
- [Neural Brain Fields: A NeRF-Inspired Approach for Generating Nonexistent EEG Electrodes](https://mlsanity.com/paper/2601.00012/) (2025)
- [BrainDecoder: Style-Based Visual Decoding of EEG Signals](https://mlsanity.com/paper/2409.05279/) (2024)
- [FairSSL: Fair Multimodal Self-Supervised Learning](https://mlsanity.com/paper/2508.16748/) (2025)
- [DeHate: A Stable Diffusion-based Multimodal Approach to Mitigate Hate Speech in Images](https://mlsanity.com/paper/2509.21787/) (2025)
- [SYNAPSE: Synergizing an Adapter and Finetuning for High-Fidelity EEG Synthesis from a CLIP-Aligned Encoder](https://mlsanity.com/paper/2511.17547/) (2025)
- [Hierarchic-EEG2Text: Assessing EEG-To-Text Decoding across Hierarchical Abstraction Levels](https://mlsanity.com/paper/2602.20932/) (2026)
- [EEG2Vision: A Multimodal EEG-Based Framework for 2D Visual Reconstruction in Cognitive Neuroscience](https://mlsanity.com/paper/2604.08063/) (2026)
- [EAD: An EEG Adapter for Automated Classification](https://mlsanity.com/paper/2505.23107/) (2025)
- [Interpretable EEG-to-Image Generation with Semantic Prompts](https://mlsanity.com/paper/2507.07157/) (2025)
- [CATVis: Context-Aware Thought Visualization](https://mlsanity.com/paper/2507.11522/) (2025)
- [The Repeated-Stimulus Confound in Electroencephalography](https://mlsanity.com/paper/2508.00531/) (2025)
- [Uni-Neur2Img: Unified Neural Signal-Guided Image Generation, Editing, and Stylization via Diffusion Transformers](https://mlsanity.com/paper/2512.18635/) (2025)
- [Brain-Gen: Towards Interpreting Neural Signals for Stimulus Reconstruction Using Transformers and Latent Diffusion Models](https://mlsanity.com/paper/2512.18843/) (2025)
- [Brain3D: EEG-to-3D Decoding of Visual Representations via Multimodal Reasoning](https://mlsanity.com/paper/2604.08068/) (2026)
- [Structure-Guided Diffusion Model for EEG-Based Visual Cognition Reconstruction](https://mlsanity.com/paper/2604.22649/) (2026)
- [EEG-EditBench: Probing Visual Information in EEG-Image Retrieval Models with Controlled Image Edits](https://mlsanity.com/paper/2607.27857/) (2026)

## Abstract (arXiv)

Decoding the human brain has been a hallmark of neuroscientists and Artificial Intelligence researchers alike. Reconstruction of visual images from brain Electroencephalography (EEG) signals has garnered a lot of interest due to its applications in brain-computer interfacing. This study proposes a two-stage method where the first step is to obtain EEG-derived features for robust learning of deep representations and subsequently utilize the learned representation for image generation and classification. We demonstrate the generalizability of our feature extraction pipeline across three different datasets using deep-learning architectures with supervised and contrastive learning methods. We have performed the zero-shot EEG classification task to support the generalizability claim further. We observed that a subject invariant linearly separable visual representation was learned using EEG data alone in an unimodal setting that gives better k-means accuracy as compared to a joint representation learning between EEG and images. Finally, we propose a novel framework to transform unseen images into the EEG space and reconstruct them with approximation, showcasing the potential for image reconstruction from EEG signals. Our proposed image synthesis method from EEG shows 62.9% and 36.13% inception score improvement on the EEGCVPR40 and the Thoughtviz datasets, which is better than state-of-the-art performance in GAN.