paper-with-me

홈 › Papers

Extreme Image Transformations Affect Humans and Machines Differently

2022-11-30 · Girik Malik, Dakarai Crowder, Ennio Mingolla

Some recent artificial neural networks (ANNs) claim to model aspects of primate neural and human performance data. Their success in object recognition is, however, dependent on exploiting low-level features for solving visual tasks in a way that humans do not. As a result, out-of-distribution or adversarial input is often challenging for ANNs. Humans instead learn abstract patterns and are mostly unaffected by many extreme image distortions. We introduce a set of novel image transforms inspired by neurophysiological findings and evaluate humans and ANNs on an object recognition task. We show that machines perform better than humans for certain transforms and struggle to perform at par with humans on others that are easy for humans. We quantify the differences in accuracy for humans and machines and find a ranking of difficulty for our transforms for human data. We also suggest how certain characteristics of human visual processing can be adapted to improve the performance of ANNs for our difficult-for-machines transforms.

📄 PDF Abstract BibTeX arXiv:2212.13967

Code (0)

등록된 구현이 없습니다.

Tasks

Object Recognition

Similar Papers 제목 키워드 기반

Robustness of Humans and Machines on Object Recognition with Extreme Image Transformations

2022-05-09 · Dakarai Crowder, Girik Malik

Recent neural network architectures have claimed to explain data from the human visual cortex. Their demonstrated performance is however still limited by the dependence on exploiting low-level features for solving visual…

Object Recognition

Extreme Image Transformations Facilitate Robust Latent Object Representations

2023-09-19 · Girik Malik, Dakarai Crowder, Ennio Mingolla

Adversarial attacks can affect the object recognition capabilities of machines in wild. These can often result from spurious correlations between input and class labels, and are prone to memorization in large networks. W…

feature selectionMemorizationObjectObject Recognition

Forbes: Face Obfuscation Rendering via Backpropagation Refinement Scheme

2024-07-19 · Jintae Kim, Seungwon yang, Seong-Gyun Jeong, Chang-Su Kim

A novel algorithm for face obfuscation, called Forbes, which aims to obfuscate facial appearance recognizable by humans but preserve the identity and attributes decipherable by machines, is proposed in this paper. Forbes…

Finding the unicorn: Predicting early stage startup success through a hybrid intelligence method

2021-05-07 · Dominik Dellermann, Nikolaus Lipusch, Philipp Ebel, Karl Michael Popp 외

Artificial intelligence is an emerging topic and will soon be able to perform decisions better than humans. In more complex and creative contexts such as innovation, however, the question remains whether machines are sup…

On the use of Cortical Magnification and Saccades as Biological Proxies for Data Augmentation

2021-12-14 · NeurIPS Workshop SVRHM 2021 12 · Binxu Wang, David Mayo, Arturo Deza, Andrei Barbu 외

Self-supervised learning is a powerful way to learn useful representations from natural data. It has also been suggested as one possible means of building visual representation in humans, but the specific objective and a…

Data AugmentationRepresentation LearningSelf-Supervised Learning