Search Results for author:
Found 6 papers, 5 papers with code
Matching the Neuronal Representations of V1 is Necessary to Improve Robustness in CNNs with V1-like Front-ends
Here, we further explore this result and show that the neuronal representations that emerge from precisely matching the distribution of RF properties found in primate V1 is key for this improvement in robustness.
Connecting metrics for shape-texture knowledge in computer vision
Finally, we observed that while in general there is a correlation between performance and shape bias, there are significant variations between architecture families.
Neural Population Geometry Reveals the Role of Stochasticity in Robust Perception
Adversarial examples are often cited by neuroscientists and machine learning researchers as an example of how computational models diverge from biological sensory systems.
Combining Different V1 Brain Model Variants to Improve Robustness to Image Corruptions in CNNs
Finally, we show that using distillation, it is possible to partially compress the knowledge in the ensemble model into a single model with a V1 front-end.
Wiring Up Vision: Minimizing Supervised Synaptic Updates Needed to Produce a Primate Ventral Stream
Relative to the current leading model of the adult ventral stream, we here demonstrate that the total number of supervised weight updates can be substantially reduced using three complementary strategies: First, we find that only 2% of supervised updates (epochs and images) are needed to achieve ~80% of the match to adult ventral stream.
Simulating a Primary Visual Cortex at the Front of CNNs Improves Robustness to Image Perturbations
Current state-of-the-art object recognition models are largely based on convolutional neural network (CNN) architectures, which are loosely inspired by the primate visual system.
