@proceedings {5105, title = {Finding Biological Plausibility for Adversarially Robust Features via Metameric Tasks}, year = {2022}, keywords = {Adversarial Robustness, Metamerism, Perceptual Invariance, Peripheral Computation, Psychophysics, Texture}, url = {https://openreview.net/forum?id=yeP_zx9vqNm}, author = {Anne Harrington and Arturo Deza} } @conference {5106, title = {Joint rotational invariance and adversarial training of a dual-stream Transformer yields state of the art Brain-Score for Area V4}, booktitle = {BrainScore Workshop at COSYNE}, year = {2022}, keywords = {adversarial training, Brain-Score competition, rotation invariance, Vision Transformer}, url = {https://openreview.net/pdf?id=SOulrWP-Xb5}, author = {William Berrios and Arturo Deza} } @article {4769, title = {The Effects of Image Distribution and Task on Adversarial Robustness}, year = {2021}, month = {02/2021}, abstract = {
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 ε-interval [ε0, ε1] (interval of adversarial perturbation strengths) that facilitates unbiased comparisons across models when they have different initial ε0 performance. This can be used to determine how adversarially robust a model is to different image distributions or task (or some other variable); and/or to measure how robust a model is comparatively to other models. We used this adversarial robustness metric on models of an MNIST, CIFAR-10, and a Fusion dataset (CIFAR-10 + MNIST) where trained models performed either a digit or object recognition task using a LeNet, ResNet50, or a fully connected network (FullyConnectedNet) architecture and found the following: 1) CIFAR-10 models are inherently less adversarially robust than MNIST models; 2) Both the image distribution and task that a model is trained on can affect the adversarial robustness of the resultant model. 3) Pretraining with a different image distribution and task sometimes carries over the adversarial robustness induced by that image distribution and task in the resultant model; Collectively, our results imply non-trivial differences of the learned representation space of one perceptual system over another given its exposure to different image statistics or tasks (mainly objects vs digits). Moreover, these results hold even when model systems are equalized to have the same level of performance, or when exposed to approximately matched image statistics of fusion images but with different tasks.
}, author = {Owen Kunhardt and Arturo Deza and Tomaso Poggio} } @article {5072, title = {Evaluating the Adversarial Robustness of a Foveated Texture Transform Module in a CNN}, year = {2021}, month = {12/2021}, url = {https://nips.cc/Conferences/2021/Schedule?showEvent=21868}, author = {Jonathan Gant and Andrzej Banburski and Arturo Deza and Tomaso Poggio} } @conference {5107, title = {On the use of Cortical Magnification and Saccades as Biological Proxies for Data Augmentation}, booktitle = {Shared Visual Representations in Human and Machine Intelligence (SVRHM) Workshop at NeurIPS}, year = {2021}, keywords = {Active Perception, Data-Augmentation, Foveation, Self-Supervised Learning}, url = {https://openreview.net/forum?id=Rpazl253IHb}, author = {Binxu Wang and David Mayo and Arturo Deza and Andrei Barbu and Colin Conwell} } @conference {5108, title = {What Matters In Branch Specialization? Using a Toy Task to Make Predictions}, booktitle = {Shared Visual Representations in Human and Machine Intelligence (SVRHM) Workshop at NeurIPS}, year = {2021}, keywords = {branch specialization, computational vision, curriculum learning}, url = {https://openreview.net/forum?id=0kPS1i6wict}, author = {Chenguang Li and Arturo Deza} } @conference {4697, title = {CUDA-Optimized real-time rendering of a Foveated Visual System}, booktitle = {Shared Visual Representations in Human and Machine Intelligence (SVRHM) workshop at NeurIPS 2020}, year = {2020}, month = {12/2020}, abstract = {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. The computational demands of high resolution rendering desired for VR can be offset by savings in the periphery [16], while neural networks trained with foveated input have shown perceptual gains in i.i.d and o.o.d generalization [25, 6]. In this paper, we present a technique that exploits the CUDA GPU architecture to efficiently generate Gaussian-based foveated images at high definition (1920px {\texttimes} 1080px) in real-time (165 Hz), with a larger number of pooling regions than previous Gaussian-based foveation algorithms by several orders of magnitude [10, 25], producing a smoothly foveated image that requires no further blending or stitching, and that can be well fit for any contrast sensitivity function. The approach described can be adapted from Gaussian blurring to any eccentricity-dependent image processing and our algorithm can meet demand for experimentation to evaluate the role of spatially-varying processing across biological and artificial agents, so that foveation can be added easily on top of existing systems rather than forcing their redesign ({\textquotedblleft}emulated foveated renderer{\textquotedblright} [22]). Altogether, this paper demonstrates how a GPU, with a CUDA block-wise architecture, can be employed for radially-variant rendering, with opportunities for more complex post-processing to ensure a metameric foveation scheme [33].
}, url = {https://arxiv.org/abs/2012.08655}, author = {Elian Malkin and Arturo Deza and Tomaso Poggio} } @article {4570, title = {Hierarchically Local Tasks and Deep Convolutional Networks}, year = {2020}, month = {06/2020}, abstract = {The main success stories of deep learning, starting with ImageNet, depend on convolutional networks, which on certain tasks perform significantly better than traditional shallow classifiers, such as support vector machines. Is there something special about deep convolutional networks that other learning machines do not possess? Recent results in approximation theory have shown that there is an exponential advantage of deep convolutional-like networks in approximating functions with hierarchical locality in their compositional structure. These mathematical results, however, do not say which tasks are expected to have input-output functions with hierarchical locality. Among all the possible hierarchically local tasks in vision, text and speech we explore a few of them experimentally by studying how they are affected by disrupting locality in the input images. We also discuss a taxonomy of tasks ranging from local, to hierarchically local, to global and make predictions about the type of networks required to perform\ efficiently on these different types of tasks.
}, keywords = {Compositionality, Inductive Bias, perception, Theory of Deep Learning}, author = {Arturo Deza and Qianli Liao and Andrzej Banburski and Tomaso Poggio} }