Search Results for author: Bruno Olshausen

Found 15 papers, 7 papers with code

URLOST: Unsupervised Representation Learning without Stationarity or Topology

no code implementations6 Oct 2023 Zeyu Yun, Juexiao Zhang, Bruno Olshausen, Yann Lecun, Yubei Chen

Unsupervised representation learning has seen tremendous progress but is constrained by its reliance on data modality-specific stationarity and topology, a limitation not found in biological intelligence systems.

Representation Learning

Learning Internal Representations of 3D Transformations from 2D Projected Inputs

no code implementations31 Mar 2023 Marissa Connor, Bruno Olshausen, Christopher Rozell

When interacting in a three dimensional world, humans must estimate 3D structure from visual inputs projected down to two dimensional retinal images.

PIM: Video Coding using Perceptual Importance Maps

no code implementations20 Dec 2022 Evgenya Pergament, Pulkit Tandon, Oren Rippel, Lubomir Bourdev, Alexander G. Anderson, Bruno Olshausen, Tsachy Weissman, Sachin Katti, Kedar Tatwawadi

The contributions of this work are threefold: (1) we introduce a web-tool which allows scalable collection of fine-grained perceptual importance, by having users interactively paint spatio-temporal maps over encoded videos; (2) we use this tool to collect a dataset with 178 videos with a total of 14443 frames of human annotated spatio-temporal importance maps over the videos; and (3) we use our curated dataset to train a lightweight machine learning model which can predict these spatio-temporal importance regions.

Video Compression

Minimalistic Unsupervised Learning with the Sparse Manifold Transform

no code implementations30 Sep 2022 Yubei Chen, Zeyu Yun, Yi Ma, Bruno Olshausen, Yann Lecun

Though there remains a small performance gap between our simple constructive model and SOTA methods, the evidence points to this as a promising direction for achieving a principled and white-box approach to unsupervised learning.

Self-Supervised Learning Sparse Representation-based Classification +3

Bispectral Neural Networks

1 code implementation7 Sep 2022 Sophia Sanborn, Christian Shewmake, Bruno Olshausen, Christopher Hillar

We present a neural network architecture, Bispectral Neural Networks (BNNs) for learning representations that are invariant to the actions of compact commutative groups on the space over which a signal is defined.

Adversarial Robustness Representation Learning

An Interactive Annotation Tool for Perceptual Video Compression

1 code implementation8 May 2022 Evgenya Pergament, Pulkit Tandon, Kedar Tatwawadi, Oren Rippel, Lubomir Bourdev, Bruno Olshausen, Tsachy Weissman, Sachin Katti, Alexander G. Anderson

We use this tool to collect data in-the-wild (10 videos, 17 users) and utilize the obtained importance maps in the context of x264 coding to demonstrate that the tool can indeed be used to generate videos which, at the same bitrate, look perceptually better through a subjective study - and are 1. 9 times more likely to be preferred by viewers.

Video Compression

Disentangling images with Lie group transformations and sparse coding

1 code implementation11 Dec 2020 Ho Yin Chau, Frank Qiu, Yubei Chen, Bruno Olshausen

Discrete spatial patterns and their continuous transformations are two important regularities contained in natural signals.

RG-Flow: A hierarchical and explainable flow model based on renormalization group and sparse prior

1 code implementation30 Sep 2020 Hong-Ye Hu, Dian Wu, Yi-Zhuang You, Bruno Olshausen, Yubei Chen

In this work, we incorporate the key ideas of renormalization group (RG) and sparse prior distribution to design a hierarchical flow-based generative model, RG-Flow, which can separate information at different scales of images and extract disentangled representations at each scale.

Disentanglement Image Inpainting +2

Dynamic Scale Inference by Entropy Minimization

no code implementations8 Aug 2019 Dequan Wang, Evan Shelhamer, Bruno Olshausen, Trevor Darrell

Given the variety of the visual world there is not one true scale for recognition: objects may appear at drastically different sizes across the visual field.

Diversity Semantic Segmentation

Auditory Separation of a Conversation from Background via Attentional Gating

no code implementations26 May 2019 Shariq Mobin, Bruno Olshausen

Our Attentional Gating Network (AGN) uses a variable attentional context to specify which speakers in the mixture are of interest.

Speaker Separation

Superposition of many models into one

1 code implementation NeurIPS 2019 Brian Cheung, Alex Terekhov, Yubei Chen, Pulkit Agrawal, Bruno Olshausen

We present a method for storing multiple models within a single set of parameters.

Generalization Challenges for Neural Architectures in Audio Source Separation

1 code implementation23 Mar 2018 Shariq Mobin, Brian Cheung, Bruno Olshausen

Recent work has shown that recurrent neural networks can be trained to separate individual speakers in a sound mixture with high fidelity.

Audio Source Separation

Cannot find the paper you are looking for? You can Submit a new open access paper.