Self-Supervised Learning with Swin Transformers

Github: https://github.com/SwinTransformer/Transformer-SSL

Paper: https://arxiv.org/abs/2105.04553v2

👉 @bigdata_1

Dynamic Slimmable Network (DS-Net)

Github: https://github.com/M3DV/AlignShift

Paper: https://arxiv.org/abs/2109.10060v1

👉 @bigdata_1

A Large-Scale Benchmark for Food Image Segmentation

Github: https://github.com/XiongweiWu/FoodSeg-Benchmark

Paper: https://arxiv.org/abs/2105.05409v1

👉 @bigdata_1

Language Models are Few-shot Multilingual Learners

Github: https://github.com/gentaiscool/few-shot-lm

Paper: https://arxiv.org/abs/2109.07684v1

👉 @bigdata_1

EL-Attention: Memory Efficient Lossless Attention for Generation

Github: https://github.com/microsoft/fastseq

Paper: https://arxiv.org/abs/2105.04779v1

👉 @bigdata_1

CompilerGym: Robust, Performant Compiler Optimization Environments for AI Research

CompilerGym is a library of easy to use and performant reinforcement learning environments for compiler tasks.

Github: https://github.com/facebookresearch/CompilerGym

Documents: https://facebookresearch.github.io/CompilerGym/

Paper: https://arxiv.org/abs/2109.08267v1

👉 @bigdata_1

SyntheticFur Dataset Description

Gitgub: https://github.com/google-research-datasets/synthetic-fur

Paper: https://arxiv.org/abs/2105.06409

Video: https://youtu.be/5uraQu_5Tyg

👉 @bigdata_1

Building AI that can generate images of things it has never seen before

Github: https://github.com/facebookresearch/ic_gan

Facebook Ai: https://ai.facebook.com/blog/instance-conditioned-gans/

Documents: https://facebookresearch.github.io/CompilerGym/

Paper: https://arxiv.org/abs/2109.05070

👉 @bigdata_1

SAFIN: Arbitrary Style Transfer With Self-Attentive Factorized Instance Normalization

Github: https://github.com/Aaditya-Singh/SAFIN

Paper: https://arxiv.org/abs/2105.06129v1

👉 @bigdata_1

Don’t be Contradicted with Anything!CI-ToD: Towards Benchmarking Consistency for Task-oriented Dialogue System

Github: https://github.com/yizhen20133868/ci-tod

Paper: https://arxiv.org/abs/2109.11292v1

Dataset: https://paperswithcode.com/dataset/kvret-1

👉 @bigdata_1

GAN Prior Embedded Network for Blind Face Restoration in the Wild

Github: https://github.com/yangxy/GPEN

Paper: https://arxiv.org/abs/2105.06070v1

👉 @bigdata_1

Unseen Object Amodal Instance Segmentation (UOAIS)

Github: https://github.com/gist-ailab/uoais

Paper: https://arxiv.org/abs/2109.11103

Dataset: https://paperswithcode.com/dataset/ocid

Project: https://sites.google.com/view/uoais

👉 @bigdata_1

Rethinking "Batch" in BatchNorm

Github: https://github.com/facebookresearch/detectron2/tree/master/projects/Rethinking-BatchNorm

Paper: https://arxiv.org/abs/2105.07576

👉 @bigdata_1

AlphaRotate: A Rotation Detection Benchmark using TensorFlow

Github: https://github.com/yangxue0827/RotationDetection

Paper: https://arxiv.org/abs/2109.11906v1

Dataset: https://paperswithcode.com/dataset/dota

Documentation: https://rotationdetection.readthedocs.io/en/latest/

👉 @bigdata_1

Deep Learning Dataset For Passage and Document Retrieval

Github: https://github.com/grill-lab/DL-Hard

Paper: https://arxiv.org/abs/2105.07975v1

👉 @bigdata_1

PASS: Pictures without humAns for Self-Supervised Pretraining

PASS is a large-scale image dataset that does not include any humans, human parts, or other personally identifiable information.

Github: https://github.com/yukimasano/PASS

Paper: https://arxiv.org/abs/2109.13228v1

Dataset: https://paperswithcode.com/dataset/pass

Documentation: https://www.robots.ox.ac.uk/~vgg/research/pass/

👉 @bigdata_1

Vision Transformer for Fast and Efficient Scene Text Recognition

Github: https://github.com/roatienza/deep-text-recognition-benchmark

Paper: https://arxiv.org/abs/2105.08582

👉 @bigdata_1

Nowcasting the Next Hour of Rain

Github: https://github.com/deepmind/deepmind-research/tree/master/nowcasting

Paper: https://www.nature.com/articles/s41586-021-03854-z

Deepmind blog: https://deepmind.com/blog/article/nowcasting

👉 @bigdata_1

OpenNRE

Reviewing Test Protocols of Distantly Supervised Relation Extraction

Github: https://github.com/thunlp/OpenNRE

Paper: https://arxiv.org/abs/2105.09543v1

👉 @bigdata_1

MiniHack is a sandbox framework for easily designing rich and diverse environments for Reinforcement Learning

Github: https://github.com/facebookresearch/minihack

Facebook AI: https://ai.facebook.com/blog/minihack-a-new-sandbox-for-open-ended-reinforcement-learning/

Paper: https://arxiv.org/abs/2109.13202

Documentation: https://minihack.readthedocs.io/

👉 @bigdata_1