BAGUA: Scaling up Distributed Learning with System Relaxations

BaguaSys/bagua 3 Jul 2021

Recent years have witnessed a growing list of systems for distributed data-parallel training.

Distributed Optimization Quantization

497
0.39 stars / hour

Liquid Time-constant Networks

raminmh/liquid_time_constant_networks 8 Jun 2020

We introduce a new class of time-continuous recurrent neural network models.

Time Series Time Series Prediction

363
0.37 stars / hour

Pixel-Perfect Structure-from-Motion with Featuremetric Refinement

cvg/pixel-perfect-sfm ICCV 2021

Finding local features that are repeatable across multiple views is a cornerstone of sparse 3D reconstruction.

3D Reconstruction Structure from Motion

288
0.35 stars / hour

MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer

xmu-xiaoma666/External-Attention-pytorch 5 Oct 2021

In this paper, we ask the following question: is it possible to combine the strengths of CNNs and ViTs to build a light-weight and low latency network for mobile vision tasks?

Image Classification Object Detection

2,115
0.32 stars / hour

Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data

xinntao/Real-ESRGAN 22 Jul 2021

Though many attempts have been made in blind super-resolution to restore low-resolution images with unknown and complex degradations, they are still far from addressing general real-world degraded images.

Video Super-Resolution

5,389
0.32 stars / hour

Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation

hkchengrex/STCN 9 Jun 2021

This paper presents a simple yet effective approach to modeling space-time correspondences in the context of video object segmentation.

Semantic Segmentation Semi-Supervised Video Object Segmentation +1

295
0.31 stars / hour

CoAtNet: Marrying Convolution and Attention for All Data Sizes

xmu-xiaoma666/External-Attention-pytorch 9 Jun 2021

Transformers have attracted increasing interests in computer vision, but they still fall behind state-of-the-art convolutional networks.

 Ranked #1 on Image Classification on ImageNet (using extra training data)

Image Classification

2,110
0.30 stars / hour

DEUP: Direct Epistemic Uncertainty Prediction

google/uncertainty-baselines ICLR 2022 (in review)

Epistemic uncertainty is the part of out-of-sample prediction error due to the lack of knowledge of the learner.

Active Learning

649
0.30 stars / hour

General-Purpose Question-Answering with Macaw

allenai/macaw 6 Sep 2021

Despite the successes of pretrained language models, there are still few high-quality, general-purpose QA systems that are freely available.

Generative Question Answering

72
0.30 stars / hour

On Mixup Regularization

google/uncertainty-baselines 10 Jun 2020

Mixup is a data augmentation technique that creates new examples as convex combinationsof training points and labels.

Data Augmentation

647
0.30 stars / hour