Visual concept classification on ImageNet-EEG (val)
41.8AccuracyVIT-LENS L
Evaluation results
| Method | Links | |
|---|---|---|
| VIT-LENS Lanchor=I+T2023.11 | 41.8 | |
| VIT-LENS Lanchor=I2023.11 | 29.3 | |
| VIT-LENS Banchor=I2023.11 | 24.6 | |
| DreamDiffusion-Lanchor=I, inference_details=released EEG encoder and paired text encoder2023.11 | 20.4 | |
| ImageBind-Banchor=I, implementation=our implementation2023.11 | 17.3 |