Paper
Publication
BYOL-Explore: Exploration with Bootstrapped Prediction
Paper
Publication
Unlocking High-Accuracy Differentially Private Image Classification through Scale
Paper
Publication
Perceiver AR: general-purpose, long-context autoregressive generation
Paper
Publication
Measuring CLEVRness: Black-box Testing of Visual Reasoning Models
Paper
Publication
More than Words: In-the-Wild Visually-Driven Prosody for Text-to-Speech
Paper
Publication
Efficient Visual Pretraining with Contrastive Detection
Paper
Publication
Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers
Paper
Publication
Data, Architecture, or Losses: What Contributes Most to Multimodal Transformer Success?
Paper
Publication
BYOL works even without batch statistics
Paper
Publication
Bootstrap Your Own Latent: A new approach to self-supervised learning
Paper
Publication
S3K: Self-Supervised Semantic Keypoints for Robotic Manipulation via Multi-View Consistency
Paper
Publication
Counting Out Time: Class Agnostic Video Repetition Counting in the Wild
Paper
Publication
Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions
Paper
Publication
Evolving Normalization-Activation Layers
Paper
Publication
Hybrid Models for Open Set Recognition
Paper
Publication
Batch Normalization Biases Deep Residual Networks Towards Shallow Paths
Paper
Publication
Sideways: Depth-Parallel Training of Video Models
Paper
Publication
International evaluation of an AI system for breast cancer screening
Paper
Publication
End-to-End Learning of Visual Representations from Uncurated Instructional Videos
Paper
Publication
Towards Robust Image Classification Using Sequential Attention Models
Paper
Publication
Controllable Attention for Structured Layered Video Decomposition
Paper
Publication
Imagined Value Gradients: Model-Based Policy Optimization with Transferable Latent Dynamics Models
Paper
Publication
CLEVRER: CoLlision Events for Video REpresentation and Reasoning
Paper
Publication
Large Scale Adversarial Representation Learning
Paper
Publication
Sim2real transfer learning for 3D pose estimation: motion to the rescue