Workshop
Shared Visual Representations in Human and Machine Intelligence
Arturo Deza · Joshua Peterson · N Apurva Ratan Murty · Tom Griffiths
Mon 13 Dec, 6:45 a.m. PST
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.
Schedule
Mon 6:45 a.m. - 7:00 a.m.
|
Opening Remarks
(
Remarks
)
>
SlidesLive Video |
🔗 |
Mon 7:00 a.m. - 7:10 a.m.
|
Modeling Category-Selective Cortical Regions with Topographic Variational Autoencoders
(
Oral
)
>
link
SlidesLive Video |
T. Anderson Keller · Qinghe Gao · Max Welling 🔗 |
Mon 7:10 a.m. - 7:20 a.m.
|
Learning to perceive objects by prediction
(
Oral
)
>
link
SlidesLive Video |
Tushar Arora · Li Erran Li · Mingbo Cai 🔗 |
Mon 7:20 a.m. - 7:40 a.m.
|
Yukiyasu Kamitani: "High-performance DNNs are not brain-like"
(
Invited Talk
)
>
SlidesLive Video |
🔗 |
Mon 7:40 a.m. - 8:00 a.m.
|
Roland Fleming: "Learning to See Stuff"
(
Invited Talk
)
>
SlidesLive Video |
🔗 |
Mon 8:00 a.m. - 8:20 a.m.
|
Gemma Roig: "Modeling the human brain from invariance and robustness to clutter towards multimodal, multi-task and continuous learning models"
(
Invited Talk
)
>
SlidesLive Video |
🔗 |
Mon 8:20 a.m. - 8:40 a.m.
|
Wieland Brendel: "How Well do Feature Visualizations Support Causal Understanding of CNN Activations?"
(
Invited Talk
)
>
SlidesLive Video |
🔗 |
Mon 8:40 a.m. - 9:00 a.m.
|
Stephane Deny: "Learning transformations from data via recurrent latent operators"
(
Invited Talk
)
>
SlidesLive Video |
🔗 |
Mon 9:00 a.m. - 10:00 a.m.
|
KDSalBox: A toolbox of efficient knowledge-distilled saliency models ( Poster ) > link | Ard Kastrati · Zoya Bylinskii · Eli Shechtman 🔗 |
Mon 9:00 a.m. - 10:00 a.m.
|
Seeking the Building Blocks of Visual Imagery and Creativity in a Cognitively Inspired Neural Network ( Poster ) > link | Shekoofeh Hedayati · Roger Beaty · Brad Wyble 🔗 |
Mon 9:00 a.m. - 10:00 a.m.
|
V1 and IT representations are directly accessible to human visual perception ( Poster ) > link | Akshay Jagadeesh · Justin Gardner 🔗 |
Mon 9:00 a.m. - 10:00 a.m.
|
On the use of Cortical Magnification and Saccades as Biological Proxies for Data Augmentation ( Poster ) > link | Binxu Wang · David Mayo · Arturo Deza · Andrei Barbu · Colin Conwell 🔗 |
Mon 9:00 a.m. - 10:00 a.m.
|
Exploring the Structure of Human Adjective Representations ( Poster ) > link | Karan Grewal · Joshua Peterson · Bill Thompson · Tom Griffiths 🔗 |
Mon 9:00 a.m. - 10:00 a.m.
|
Combining Different V1 Brain Model Variants to Improve Robustness to Image Corruptions in CNNs ( Poster ) > link | Avinash Baidya · Joel Dapello · James J DiCarlo · Tiago Marques 🔗 |
Mon 9:00 a.m. - 10:00 a.m.
|
Benchmarking human visual search computational models in natural scenes: models comparison and reference datasets ( Poster ) > link | FermĂn Travi · Gonzalo Ruarte · Gaston Bujia · Juan Esteban Kamienkowski 🔗 |
Mon 9:00 a.m. - 10:00 a.m.
|
Shared Visual Representations of Drawing for Communication: How do different biases affect human interpretability and intent? ( Poster ) > link | Daniela Mihai · Jonathon Hare 🔗 |
Mon 9:00 a.m. - 10:00 a.m.
|
Out-of-distribution robustness: Limited image exposure of a four-year-old is enough to outperform ResNet-50 ( Poster ) > link | Lukas Huber · Robert Geirhos · Felix A. Wichmann 🔗 |
Mon 9:00 a.m. - 10:00 a.m.
|
Contrastive Learning Through Time ( Poster ) > link | Felix Maximilian Schneider · Xia Xu · Markus Ernst · Zhengyang Yu · Jochen Triesch 🔗 |
Mon 9:00 a.m. - 10:01 a.m.
|
Convolutional Networks are Inherently Foveated ( Poster ) > link | Bilal Alsallakh · Vivek Miglani · Narine Kokhlikyan · David Adkins · Orion Reblitz-Richardson 🔗 |
Mon 9:00 a.m. - 10:00 a.m.
|
Neural Structure Mapping For Learning Abstract Visual Analogies ( Poster ) > link | Shashank Shekhar · Graham Taylor 🔗 |
Mon 9:00 a.m. - 10:00 a.m.
|
Bio-inspired Min-Nets Improve the Performance and Robustness of Deep Networks ( Poster ) > link | Philipp Gruening · Erhardt Barth 🔗 |
Mon 9:00 a.m. - 10:00 a.m.
|
Boxhead: A Dataset for Learning Hierarchical Representations ( Poster ) > link | Yukun Chen · Andrea Dittadi · Frederik Träuble · Stefan Bauer · Bernhard Schölkopf 🔗 |
Mon 9:00 a.m. - 10:00 a.m.
|
What Matters In Branch Specialization? Using a Toy Task to Make Predictions ( Poster ) > link | Chenguang Li · Arturo Deza 🔗 |
Mon 9:00 a.m. - 10:00 a.m.
|
Cyclic orthogonal convolutions for long-range integration of features ( Poster ) > link | Federica Freddi · Jezabel Garcia · Michael Bromberg · Sepehr Jalali · Da-shan Shiu · Alvin Chua · Alberto Bernacchia 🔗 |
Mon 9:00 a.m. - 10:00 a.m.
|
Category-orthogonal object features guide information processing in recurrent neural networks trained for object categorization ( Poster ) > link | Sushrut Thorat · Giacomo Aldegheri · Tim Kietzmann 🔗 |
Mon 9:00 a.m. - 10:00 a.m.
|
Modeling Category-Selective Cortical Regions with Topographic Variational Autoencoders ( Poster ) > link | T. Anderson Keller · Qinghe Gao · Max Welling 🔗 |
Mon 9:00 a.m. - 10:00 a.m.
|
Learning to perceive objects by prediction ( Poster ) > link | Tushar Arora · Li Erran Li · Mingbo Cai 🔗 |
Mon 10:00 a.m. - 10:10 a.m.
|
Controlled-rearing studies of newborn chicks and deep neural networks
(
Oral
)
>
link
SlidesLive Video |
Donsuk Lee · Pranav Gujarathi · Justin Wood 🔗 |
Mon 10:10 a.m. - 10:20 a.m.
|
Multimodal neural networks better explain multivoxel patterns in the hippocampus
(
Oral
)
>
link
SlidesLive Video |
Bhavin Choksi · Milad Mozafari · Rufin VanRullen · Leila Reddy 🔗 |
Mon 10:20 a.m. - 10:40 a.m.
|
Michelle Greene: "What we don't see can hurt us: dataset bias and its implications"
(
Invited Talk
)
>
SlidesLive Video |
🔗 |
Mon 10:40 a.m. - 11:00 a.m.
|
Zoya Bylinskii: "Why does where people look matter? New trends & applications of visual attention modeling"
(
Invited Talk
)
>
SlidesLive Video |
🔗 |
Mon 11:00 a.m. - 11:20 a.m.
|
Maryam Vaziri-Pashkam: "Beyond labeling THINGS-In-3D: is one visual pathway enough?"
(
Invited Talk
)
>
SlidesLive Video |
🔗 |
Mon 11:20 a.m. - 11:40 a.m.
|
Xavier Boix: "Robustness to Transformations Across Categories: Is Robustness Driven by Invariant Neural Representations?"
(
Invited Talk
)
>
SlidesLive Video |
🔗 |
Mon 12:00 p.m. - 1:00 p.m.
|
Bio-inspired learnable divisive normalization for ANNs ( Poster ) > link | Vijay Veerabadran · Ritik Raina · Virginia de Sa 🔗 |
Mon 12:00 p.m. - 1:00 p.m.
|
What can 5.17 billion regression fits tell us about artificial models of the human visual system? ( Poster ) > link | Colin Conwell · Jacob Prince · George Alvarez · Talia Konkle 🔗 |
Mon 12:00 p.m. - 1:00 p.m.
|
Unsupervised Representation Learning Facilitates Human-like Spatial Reasoning ( Poster ) > link | Kaushik Lakshminarasimhan · Colin Conwell 🔗 |
Mon 12:00 p.m. - 1:00 p.m.
|
Finding Biological Plausibility for Adversarially Robust Features via Metameric Tasks ( Poster ) > link | Anne Harrington · Arturo Deza 🔗 |
Mon 12:00 p.m. - 1:00 p.m.
|
Exploiting 3D Shape Bias towards Robust Vision ( Poster ) > link | Yutaro Yamada · Yuval Kluger · Sahand Negahban · Ilker Yildirim 🔗 |
Mon 12:00 p.m. - 1:00 p.m.
|
Evaluating the Adversarial Robustness of a Foveated Texture Transform Module in a CNN ( Poster ) > link | Jonathan Gant · Andrzej Banburski · Arturo Deza 🔗 |
Mon 12:00 p.m. - 1:00 p.m.
|
Are models trained on temporally-continuous data streams more adversarially robust? ( Poster ) > link | Nathan Kong · Anthony Norcia 🔗 |
Mon 12:00 p.m. - 1:00 p.m.
|
In Silico Modelling of Neurodegeneration Using Deep Convolutional Neural Networks ( Poster ) > link | Jasmine Moore · Anup Tuladhar · Zahinoor Ismail · Nils Daniel Forkert 🔗 |
Mon 12:00 p.m. - 1:00 p.m.
|
Signal Strength and Noise Drive Feature Preference in CNN Image Classifiers ( Poster ) > link | Max Wolff · Stuart Wolff 🔗 |
Mon 12:00 p.m. - 1:00 p.m.
|
A finer mapping of convolutional neural network layers to the visual cortex ( Poster ) > link | Tom Dupre la Tour · Michael Lu · Michael Eickenberg · Jack Gallant 🔗 |
Mon 12:00 p.m. - 1:00 p.m.
|
Controlled-rearing studies of newborn chicks and deep neural networks ( Poster ) > link | Donsuk Lee · Pranav Gujarathi · Justin Wood 🔗 |
Mon 12:00 p.m. - 1:00 p.m.
|
Multimodal neural networks better explain multivoxel patterns in the hippocampus ( Poster ) > link | Bhavin Choksi · Milad Mozafari · Rufin VanRullen · Leila Reddy 🔗 |
Mon 1:00 p.m. - 1:20 p.m.
|
Tiago Marques: "From primary visual cortex to object recognition | The 2022 Brain-Score competition"
(
Invited Talk
)
>
SlidesLive Video |
🔗 |
Mon 1:20 p.m. - 1:40 p.m.
|
Kohitij Kar: "Role of recurrent computations in primate visual object recognition"
(
Invited Talk
)
>
SlidesLive Video |
🔗 |
Mon 1:40 p.m. - 2:00 p.m.
|
Yalda Mohsenzadeh: "Understanding, Predicting, and Manipulating Image Memorability with Representation Learning"
(
Invited Talk
)
>
SlidesLive Video |
🔗 |
Mon 2:00 p.m. - 2:20 p.m.
|
Ruben Coen-Cagli: "Measuring and modeling perceptual segmentation in natural vision"
(
Invited Talk
)
>
SlidesLive Video |
🔗 |
Mon 2:20 p.m. - 2:40 p.m.
|
Ruth Rosenholtz: "Understanding Peripheral Vision: Lessons Learned About Vision in General"
(
Invited Talk
)
>
SlidesLive Video |
🔗 |
Mon 2:50 p.m. - 3:00 p.m.
|
Closing Remarks + Award Presentation
(
Remarks
)
>
SlidesLive Video |
🔗 |