Search Results for author:
Found 16 papers, 15 papers with code
Flamingo: a Visual Language Model for Few-Shot Learning
Building models that can be rapidly adapted to numerous tasks using only a handful of annotated examples is an open challenge for multimodal machine learning research.
Ranked #1 on
Zero-Shot Learning
on iVQA
Perceiver IO: A General Architecture for Structured Inputs & Outputs
A central goal of machine learning is the development of systems that can solve many problems in as many data domains as possible.
Ranked #1 on
Optical Flow Estimation
on KITTI 2015
(Average End-Point Error metric)
Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Error
In this work, we provide a detailed empirical evaluation of how the number of augmentation samples per unique image influences model performance on held out data when training deep ResNets.
Ranked #58 on
Image Classification
on ImageNet
Skillful Precipitation Nowcasting using Deep Generative Models of Radar
To address these challenges, we present a Deep Generative Model for the probabilistic nowcasting of precipitation from radar.
Perceiver: General Perception with Iterative Attention
The perception models used in deep learning on the other hand are designed for individual modalities, often relying on domain-specific assumptions such as the local grid structures exploited by virtually all existing vision models.
Ranked #11 on
Audio Classification
on AudioSet
High-Performance Large-Scale Image Recognition Without Normalization
Batch normalization is a key component of most image classification models, but it has many undesirable properties stemming from its dependence on the batch size and interactions between examples.
Ranked #15 on
Image Classification
on ImageNet
(using extra training data)
Characterizing signal propagation to close the performance gap in unnormalized ResNets
Batch Normalization is a key component in almost all state-of-the-art image classifiers, but it also introduces practical challenges: it breaks the independence between training examples within a batch, can incur compute and memory overhead, and often results in unexpected bugs.
Training Generative Adversarial Networks by Solving Ordinary Differential Equations
From this perspective, we hypothesise that instabilities in training GANs arise from the integration error in discretising the continuous dynamics.
BYOL works even without batch statistics
Bootstrap Your Own Latent (BYOL) is a self-supervised learning approach for image representation.
Evolving Normalization-Activation Layers
Normalization layers and activation functions are fundamental components in deep networks and typically co-locate with each other.
Large Scale GAN Training for High Fidelity Natural Image Synthesis
Despite recent progress in generative image modeling, successfully generating high-resolution, diverse samples from complex datasets such as ImageNet remains an elusive goal.
Ranked #2 on
Conditional Image Generation
on ImageNet 128x128
Implicit Weight Uncertainty in Neural Networks
Modern neural networks tend to be overconfident on unseen, noisy or incorrectly labelled data and do not produce meaningful uncertainty measures.
SMASH: One-Shot Model Architecture Search through HyperNetworks
Designing architectures for deep neural networks requires expert knowledge and substantial computation time.
FreezeOut: Accelerate Training by Progressively Freezing Layers
The early layers of a deep neural net have the fewest parameters, but take up the most computation.
Neural Photo Editing with Introspective Adversarial Networks
The increasingly photorealistic sample quality of generative image models suggests their feasibility in applications beyond image generation.
Generative and Discriminative Voxel Modeling with Convolutional Neural Networks
When working with three-dimensional data, choice of representation is key.
Ranked #6 on
3D Point Cloud Classification
on ModelNet40
(Mean Accuracy metric)
