Representation Learning

by Synced 2022-06-02 0

Google Brain’s UViM: A Unified Approach for Modelling Diverse Vision Tasks Without Modifications

In the new paper UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes, a Google Brain research team proposes UViM, a unified approach that leverages language modelling and discrete representation learning to enable the modelling of a wide range of computer vision tasks without task-specific modifications.

by Synced 2022-03-22 0

AI Machine Learning & Data Science Popular Research

DeepMind Proposes Symmetry-Based Representations as a Fundamental Principle for Learning Good Representations in General Intelligence

A DeepMind research team argues that the mathematical description of symmetries in group theory is an important foundation that determines the structure of the universe, constrains the nature of natural tasks, and consequently shapes both biological and artificial intelligence. The study proposes symmetry transformations as a fundamental principle for defining what makes good representations.

by Synced 2022-01-27 0

AI Machine Learning & Data Science Research

Yann LeCun Team’s Neural Manifold Clustering and Embedding Method Surpasses High-Dimensional Clustering Algorithm Benchmarks

A team from UC Berkeley and Facebook AI Research proposes a Neural Manifold Clustering and Embedding (NMCE) method for general-purpose manifold clustering that significantly outperforms autoencoder-based deep subspace clustering approaches.

by Synced 2021-12-06 1

AI Machine Learning & Data Science Popular Research

Integrating Self-Attention and Convolution: Tsinghua, Huawei & BAAI’s ACmix Achieves SOTA Performance on CV Tasks With Minimum Cost

In the new paper On the Integration of Self-Attention and Convolution, a research team from Tsinghua University, Huawei Technologies Ltd. and the Beijing Academy of Artificial Intelligence proposes ACmix, a mixed model that leverages the benefits of both self-attention and convolution for computer vision representation tasks while achieving minimum computational overhead compared to its pure convolution or self-attention counterparts.

by Synced 2021-05-07 4

AI Machine Learning & Data Science Research

MIT & IBM ‘Curiosity’ Framework Explores Embodied Environments to Learn Task-Agnostic Visual Representations

A research team from MIT and MIT-IBM Watson AI Lab proposes Curious Representation Learning (CRL), a framework that learns to understand the surrounding environment by training a reinforcement learning (RL) agent to maximize the error of a representation learner to gain an incentive to explore the environment.

by Synced 2021-05-06 3

AI Machine Learning & Data Science Research

Facebook AI Conducts Large-Scale Study on Unsupervised Spatiotemporal Representation Learning

A research team from Facebook AI conducts a large-scale study on unsupervised spatiotemporal representation learning from videos. The work takes a unified perspective on four recent image-based frameworks (MoCo, SimCLR, BYOL, SwAV) and investigates a simple objective that can easily generalize unsupervised representation learning methodologies to space-time.