Search Results for author:
Found 13 papers, 7 papers with code
Joint rotational invariance and adversarial training of a dual-stream Transformer yields state of the art Brain-Score for Area V4
However, in this paper, we provide evidence against the unexpected trend of Vision Transformers (ViT) being not perceptually aligned with human visual representations by showing how a dual-stream Transformer, a CrossViT$~\textit{a la}$ Chen et al. (2021), under a joint rotationally-invariant and adversarial optimization procedure yields 2nd place in the aggregate Brain-Score 2022 competition(Schrimpf et al., 2020b) averaged across all visual categories, and at the time of the competition held 1st place for the highest explainable variance of area V4.
Finding Biological Plausibility for Adversarially Robust Features via Metameric Tasks
Human vision seems to rely on texture-based/summary statistic representations in the periphery, which have been shown to explain phenomena such as crowding and performance on visual search tasks.
On the use of Cortical Magnification and Saccades as Biological Proxies for Data Augmentation
Critically, we find that random cropping can be substituted by cortical magnification, and saccade-like sampling of the image could also assist the representation learning.
Evaluating the Adversarial Robustness of a Foveated Texture Transform Module in a CNN
The FTT module was added to a VGG-11 CNN architecture and ten random initializations were trained on 20-class subsets of the Places and EcoSet datasets for scene and object classification respectively.
What Matters In Branch Specialization? Using a Toy Task to Make Predictions
What motivates the brain to allocate tasks to different regions and what distinguishes multiple-demand brain regions and the tasks they perform from ones in highly specialized areas?
The Effects of Image Distribution and Task on Adversarial Robustness
In this paper, we propose an adaptation to the area under the curve (AUC) metric to measure the adversarial robustness of a model over a particular $\epsilon$-interval $[\epsilon_0, \epsilon_1]$ (interval of adversarial perturbation strengths) that facilitates unbiased comparisons across models when they have different initial $\epsilon_0$ performance.
CUDA-Optimized real-time rendering of a Foveated Visual System
The spatially-varying field of the human visual system has recently received a resurgence of interest with the development of virtual reality (VR) and neural networks.
Hierarchically Compositional Tasks and Deep Convolutional Networks
For object recognition we find, as expected, that scrambling does not affect the performance of shallow or deep fully connected networks contrary to the out-performance of convolutional networks.
Emergent Properties of Foveated Perceptual Systems
The primary model has a foveated-textural input stage, which we compare to a model with foveated-blurred input and a model with spatially-uniform blurred input (both matched for perceptual compression), and a final reference model with minimal input-based compression.
Assessment of Faster R-CNN in Man-Machine collaborative search
With the advent of modern expert systems driven by deep learning that supplement human experts (e. g. radiologists, dermatologists, surveillance scanners), we analyze how and when do such expert systems enhance human performance in a fine-grained small target visual search task.
Towards Metamerism via Foveated Style Transfer
The problem of $\textit{visual metamerism}$ is defined as finding a family of perceptually indistinguishable, yet physically different images.
Can Peripheral Representations Improve Clutter Metrics on Complex Scenes?
Here, we introduce a new foveated clutter model to predict the detrimental effects in target search utilizing a forced fixation search task.
Understanding Image Virality
We train classifiers with state-of-the-art image features to predict virality of individual images, relative virality in pairs of images, and the dominant topic of a viral image.
