( events)   Timezone: »  
Workshop
Mon Dec 13 06:45 AM -- 03:00 PM (PST)
Shared Visual Representations in Human and Machine Intelligence
Arturo Deza · Joshua Peterson · N Apurva Ratan Murty · Tom Griffiths





The goal of the 3rd Shared Visual Representations in Human and Machine Intelligence \textit{(SVRHM)} workshop is to disseminate relevant, parallel findings in the fields of computational neuroscience, psychology, and cognitive science that may inform modern machine learning. In the past few years, machine learning methods---especially deep neural networks---have widely permeated the vision science, cognitive science, and neuroscience communities. As a result, scientific modeling in these fields has greatly benefited, producing a swath of potentially critical new insights into the human mind. Since human performance remains the gold standard for many tasks, these cross-disciplinary insights and analytical tools may point towards solutions to many of the current problems that machine learning researchers face (\textit{e.g.,} adversarial attacks, compression, continual learning, and self-supervised learning). Thus we propose to invite leading cognitive scientists with strong computational backgrounds to disseminate their findings to the machine learning community with the hope of closing the loop by nourishing new ideas and creating cross-disciplinary collaborations. In particular, this year's version of the workshop will have a heavy focus on testing new inductive biases on novel datasets as we work on tasks that go beyond object recognition.

Opening Remarks (Remarks)
Modeling Category-Selective Cortical Regions with Topographic Variational Autoencoders (Oral)
Learning to perceive objects by prediction (Oral)
Yukiyasu Kamitani: "High-performance DNNs are not brain-like" (Invited Talk)
Roland Fleming: "Learning to See Stuff" (Invited Talk)
Gemma Roig: "Modeling the human brain from invariance and robustness to clutter towards multimodal, multi-task and continuous learning models" (Invited Talk)
Wieland Brendel: "How Well do Feature Visualizations Support Causal Understanding of CNN Activations?" (Invited Talk)
Stephane Deny: "Learning transformations from data via recurrent latent operators" (Invited Talk)
Bio-inspired Min-Nets Improve the Performance and Robustness of Deep Networks (Poster)
KDSalBox: A toolbox of efficient knowledge-distilled saliency models (Poster)
On the use of Cortical Magnification and Saccades as Biological Proxies for Data Augmentation (Poster)
Out-of-distribution robustness: Limited image exposure of a four-year-old is enough to outperform ResNet-50 (Poster)
Neural Structure Mapping For Learning Abstract Visual Analogies (Poster)
Category-orthogonal object features guide information processing in recurrent neural networks trained for object categorization (Poster)
V1 and IT representations are directly accessible to human visual perception (Poster)
Exploring the Structure of Human Adjective Representations (Poster)
Contrastive Learning Through Time (Poster)
Shared Visual Representations of Drawing for Communication: How do different biases affect human interpretability and intent? (Poster)
Seeking the Building Blocks of Visual Imagery and Creativity in a Cognitively Inspired Neural Network (Poster)
What Matters In Branch Specialization? Using a Toy Task to Make Predictions (Poster)
Modeling Category-Selective Cortical Regions with Topographic Variational Autoencoders (Poster)
Cyclic orthogonal convolutions for long-range integration of features (Poster)
Learning to perceive objects by prediction (Poster)
Boxhead: A Dataset for Learning Hierarchical Representations (Poster)
Benchmarking human visual search computational models in natural scenes: models comparison and reference datasets (Poster)
Convolutional Networks are Inherently Foveated (Poster)
Combining Different V1 Brain Model Variants to Improve Robustness to Image Corruptions in CNNs (Poster)
Controlled-rearing studies of newborn chicks and deep neural networks (Oral)
Multimodal neural networks better explain multivoxel patterns in the hippocampus (Oral)
Michelle Greene: "What we don't see can hurt us: dataset bias and its implications" (Invited Talk)
Zoya Bylinskii: "Why does where people look matter? New trends & applications of visual attention modeling" (Invited Talk)
Maryam Vaziri-Pashkam: "Beyond labeling THINGS-In-3D: is one visual pathway enough?" (Invited Talk)
Xavier Boix: "Robustness to Transformations Across Categories: Is Robustness Driven by Invariant Neural Representations?" (Invited Talk)
Controlled-rearing studies of newborn chicks and deep neural networks (Poster)
Signal Strength and Noise Drive Feature Preference in CNN Image Classifiers (Poster)
Bio-inspired learnable divisive normalization for ANNs (Poster)
Unsupervised Representation Learning Facilitates Human-like Spatial Reasoning (Poster)
Are models trained on temporally-continuous data streams more adversarially robust? (Poster)
Evaluating the Adversarial Robustness of a Foveated Texture Transform Module in a CNN (Poster)
Exploiting 3D Shape Bias towards Robust Vision (Poster)
What can 5.17 billion regression fits tell us about artificial models of the human visual system? (Poster)
Finding Biological Plausibility for Adversarially Robust Features via Metameric Tasks (Poster)
Multimodal neural networks better explain multivoxel patterns in the hippocampus (Poster)
A finer mapping of convolutional neural network layers to the visual cortex (Poster)
In Silico Modelling of Neurodegeneration Using Deep Convolutional Neural Networks (Poster)
Tiago Marques: "From primary visual cortex to object recognition | The 2022 Brain-Score competition" (Invited Talk)
Kohitij Kar: "Role of recurrent computations in primate visual object recognition" (Invited Talk)
Yalda Mohsenzadeh: "Understanding, Predicting, and Manipulating Image Memorability with Representation Learning" (Invited Talk)
Ruben Coen-Cagli: "Measuring and modeling perceptual segmentation in natural vision" (Invited Talk)
Ruth Rosenholtz: "Understanding Peripheral Vision: Lessons Learned About Vision in General" (Invited Talk)
Closing Remarks + Award Presentation (Remarks)