Finding Biological Plausibility for Adversarially Robust Features via
Metameric Tasks
- URL: http://arxiv.org/abs/2202.00838v2
- Date: Fri, 4 Feb 2022 00:24:45 GMT
- Title: Finding Biological Plausibility for Adversarially Robust Features via
Metameric Tasks
- Authors: Anne Harrington and Arturo Deza
- Abstract summary: We show that adversarially robust representations capture peripheral computation better than non-robust representations.
Our findings support the idea that localized texture summary statistic representations may drive human in robustness to adversarials.
- Score: 3.3504365823045044
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recent work suggests that representations learned by adversarially robust
networks are more human perceptually-aligned than non-robust networks via image
manipulations. Despite appearing closer to human visual perception, it is
unclear if the constraints in robust DNN representations match biological
constraints found in human vision. 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. To understand how adversarially robust
optimizations/representations compare to human vision, we performed a
psychophysics experiment using a set of metameric discrimination tasks where we
evaluated how well human observers could distinguish between images synthesized
to match adversarially robust representations compared to non-robust
representations and a texture synthesis model of peripheral vision (Texforms).
We found that the discriminability of robust representation and texture model
images decreased to near chance performance as stimuli were presented farther
in the periphery. Moreover, performance on robust and texture-model images
showed similar trends within participants, while performance on non-robust
representations changed minimally across the visual field. These results
together suggest that (1) adversarially robust representations capture
peripheral computation better than non-robust representations and (2) robust
representations capture peripheral computation similar to current
state-of-the-art texture peripheral vision models. More broadly, our findings
support the idea that localized texture summary statistic representations may
drive human invariance to adversarial perturbations and that the incorporation
of such representations in DNNs could give rise to useful properties like
adversarial robustness.
Related papers
- Towards Evaluating the Robustness of Visual State Space Models [63.14954591606638]
Vision State Space Models (VSSMs) have demonstrated remarkable performance in visual perception tasks.
However, their robustness under natural and adversarial perturbations remains a critical concern.
We present a comprehensive evaluation of VSSMs' robustness under various perturbation scenarios.
arXiv Detail & Related papers (2024-06-13T17:59:44Z) - Leveraging the Human Ventral Visual Stream to Improve Neural Network Robustness [8.419105840498917]
Human object recognition exhibits remarkable resilience in cluttered and dynamic visual environments.
Despite their unparalleled performance across numerous visual tasks, Deep Neural Networks (DNNs) remain far less robust than humans.
Here we show that DNNs, when guided by neural representations from a hierarchical sequence of regions in the human ventral visual stream, display increasing robustness to adversarial attacks.
arXiv Detail & Related papers (2024-05-04T04:33:20Z) - Neural Clustering based Visual Representation Learning [61.72646814537163]
Clustering is one of the most classic approaches in machine learning and data analysis.
We propose feature extraction with clustering (FEC), which views feature extraction as a process of selecting representatives from data.
FEC alternates between grouping pixels into individual clusters to abstract representatives and updating the deep features of pixels with current representatives.
arXiv Detail & Related papers (2024-03-26T06:04:50Z) - Deep Domain Adaptation: A Sim2Real Neural Approach for Improving Eye-Tracking Systems [80.62854148838359]
Eye image segmentation is a critical step in eye tracking that has great influence over the final gaze estimate.
We use dimensionality-reduction techniques to measure the overlap between the target eye images and synthetic training data.
Our methods result in robust, improved performance when tackling the discrepancy between simulation and real-world data samples.
arXiv Detail & Related papers (2024-03-23T22:32:06Z) - Zero-shot visual reasoning through probabilistic analogical mapping [2.049767929976436]
We present visiPAM (visual Probabilistic Analogical Mapping), a model of visual reasoning that synthesizes two approaches.
We show that without any direct training, visiPAM outperforms a state-of-the-art deep learning model on an analogical mapping task.
In addition, visiPAM closely matches the pattern of human performance on a novel task involving mapping of 3D objects across disparate categories.
arXiv Detail & Related papers (2022-09-29T20:29:26Z) - Guiding Visual Attention in Deep Convolutional Neural Networks Based on
Human Eye Movements [0.0]
Deep Convolutional Neural Networks (DCNNs) were originally inspired by principles of biological vision.
Recent advances in deep learning seem to decrease this similarity.
We investigate a purely data-driven approach to obtain useful models.
arXiv Detail & Related papers (2022-06-21T17:59:23Z) - Proactive Pseudo-Intervention: Causally Informed Contrastive Learning
For Interpretable Vision Models [103.64435911083432]
We present a novel contrastive learning strategy called it Proactive Pseudo-Intervention (PPI)
PPI leverages proactive interventions to guard against image features with no causal relevance.
We also devise a novel causally informed salience mapping module to identify key image pixels to intervene, and show it greatly facilitates model interpretability.
arXiv Detail & Related papers (2020-12-06T20:30:26Z) - DRG: Dual Relation Graph for Human-Object Interaction Detection [65.50707710054141]
We tackle the challenging problem of human-object interaction (HOI) detection.
Existing methods either recognize the interaction of each human-object pair in isolation or perform joint inference based on complex appearance-based features.
In this paper, we leverage an abstract spatial-semantic representation to describe each human-object pair and aggregate the contextual information of the scene via a dual relation graph.
arXiv Detail & Related papers (2020-08-26T17:59:40Z) - Adversarial Semantic Data Augmentation for Human Pose Estimation [96.75411357541438]
We propose Semantic Data Augmentation (SDA), a method that augments images by pasting segmented body parts with various semantic granularity.
We also propose Adversarial Semantic Data Augmentation (ASDA), which exploits a generative network to dynamiclly predict tailored pasting configuration.
State-of-the-art results are achieved on challenging benchmarks.
arXiv Detail & Related papers (2020-08-03T07:56:04Z) - Seeing eye-to-eye? A comparison of object recognition performance in
humans and deep convolutional neural networks under image manipulation [0.0]
This study aims towards a behavioral comparison of visual core object recognition performance between humans and feedforward neural networks.
Analyses of accuracy revealed that humans not only outperform DCNNs on all conditions, but also display significantly greater robustness towards shape and most notably color alterations.
arXiv Detail & Related papers (2020-07-13T10:26:30Z) - A Meta-Bayesian Model of Intentional Visual Search [0.0]
We propose a computational model of visual search that incorporates Bayesian interpretations of the neural mechanisms that underlie categorical perception and saccade planning.
To enable meaningful comparisons between simulated and human behaviours, we employ a gaze-contingent paradigm that required participants to classify occluded MNIST digits through a window that followed their gaze.
Our model is able to recapitulate human behavioural metrics such as classification accuracy while retaining a high degree of interpretability, which we demonstrate by recovering subject-specific parameters from observed human behaviour.
arXiv Detail & Related papers (2020-06-05T16:10:35Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.