2024/06/16 by Spandan Madan, Madan, Spandan, Will Xiao +9
Computer Science · Neuroscience · #Advanced Image Processing Techniques #Artificial Intelligence (cs.AI) #Brain Tumor Detection and Classification #FOS: Computer and information sciences #FOS: Electrical engineering #Neural Networks and Applications #Signal Processing (eess.SP) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2406.16935
openalex publication_date 2024/06/16 · openalex created_date 2024/06/27 · openalex updated_date 2026/07/28
We characterized the generalization capabilities of DNN-based encoding models when predicting neuronal responses from the visual cortex. We collected MacaqueITBench, a large-scale dataset of neural population responses from the macaque inferior temporal (IT) cortex to over 300,000 images, comprising 8,233 unique natural images presented to seven monkeys over 109 sessions. Using MacaqueITBench, we investigated the impact of distribution shifts on models predicting neural activity by dividing the images into Out-Of-Distribution (OOD) train and test splits. The OOD splits included several different image-computable types including image contrast, hue, intensity, temperature, and saturation. Compared to the performance on in-distribution test images -- the conventional way these models have been evaluated -- models performed worse at predicting neuronal responses to out-of-distribution images, retaining as little as 20% of the performance on in-distribution test images. The generalization performance under OOD shifts can be well accounted by a simple image similarity metric -- the cosine distance between image representations extracted from a pre-trained object recognition model is a strong predictor of neural predictivity under different distribution shifts. The dataset of images, neuronal firing rate recordings, and computational benchmarks are hosted publicly at: https://bit.ly/3zeutVd.