Канал: COMPUTER VISION TALKS

Annotation-Efficient Perception For Driving

Annotation-Efficient Perception For Driving

Human-in-the-loop Model Creation

Human-in-the-loop Model Creation

Towards a Truly Unsupervised Image Manipulation in Real World

Towards a Truly Unsupervised Image Manipulation in Real World

Large Scale Visual Representation Learning

Large Scale Visual Representation Learning

Towards Generic Vision Transformers for Supervised and Self-Supervised Representation Learning

Towards Generic Vision Transformers for Supervised and Self-Supervised Representation Learning

Open World Compositional Zero-Shot Learning

Open World Compositional Zero-Shot Learning

Physics-Informed Translation with GANs

Physics-Informed Translation with GANs

Broaden Your Views for Self-Supervised Video Learning

Broaden Your Views for Self-Supervised Video Learning

Visual Deep Learning with Limited Labels or Data

Visual Deep Learning with Limited Labels or Data

Exploring Simple Siamese Representation Learning and Beyond

Exploring Simple Siamese Representation Learning and Beyond

Machine Learning for Deep Image Manipulation

Machine Learning for Deep Image Manipulation

Self-Supervised Learning of Visual Representations with Online Clustering

Self-Supervised Learning of Visual Representations with Online Clustering

Multi-Modal Self-Supervised Learning from Videos

Multi-Modal Self-Supervised Learning from Videos

Contrastive Learning with SimCLR V1/V2 and Some Intriguing Properties

Contrastive Learning with SimCLR V1/V2 and Some Intriguing Properties

A Myth-Busting Attempt for Deep Learning Interpretability

A Myth-Busting Attempt for Deep Learning Interpretability