Bayesian Active Learning (BaaL)

Github: https://github.com/ElementAI/baal

Documentation: https://baal.readthedocs.io.

Paper: https://arxiv.org/abs/2112.06586v1

Blog: https://www.elementai.com/news/2019/element-ai-makes-its-bayesian-active-learning-library-open-source

👉 @bigdata_1

Vision Transformer Based Video Hashing Retrieval for Tracing the Source of Fake Videos

Github: https://github.com/lajlksdf/vtl

Paper: https://arxiv.org/abs/2112.08117v1

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

👉 @bigdata_1

Extreme Zero-Shot Learning for Extreme Text Classification

Github: https://github.com/amzn/pecos

Paper: https://arxiv.org/abs/2112.08652v1

👉 @bigdata_1

Ensembling Off-the-shelf Models for GAN Training

Github: https://github.com/nupurkmr9/vision-aided-gan

Paper: https://arxiv.org/pdf/2112.09130v1.pdf

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

👉 @bigdata_1

NetKet 3: Machine Learning Toolbox for Many-Body Quantum Systems

NetKet is an open-source project delivering cutting-edge methods for the study of many-body quantum systems with artificial neural networks and machine learning techniques.

Github: https://github.com/netket/netket

Paper: https://arxiv.org/pdf/2112.10526v1.pdf

Homepage: https://www.netket.org

Documentation: https://www.netket.org/documentation

Tutorials: https://www.netket.org/tutorials

👉 @bigdata_1

RepMLPNet: Hierarchical Vision MLP with Re-parameterized Locality (PyTorch)

Github: https://github.com/DingXiaoH/RepMLP

Pre-trained model: https://drive.google.com/drive/folders/1eDFunxOQ67MvBBmJ4Bw01TFh2YVNRrg2?usp=sharing

Paper: https://arxiv.org/abs/2112.11081v1

Task: https://paperswithcode.com/task/semantic-segmentation

👉 @bigdata_1

GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models

Github: https://github.com/openai/glide-text2im

Notebooks: https://github.com/openai/glide-text2im/blob/main/notebooks

Paper: https://arxiv.org/abs/2112.10741

Task: https://paperswithcode.com/task/image-generation

👉 @bigdata_1

MSeg: A Composite Dataset for Multi-domain Semantic Segmentation

Github: https://github.com/mseg-dataset/mseg-api

Paper: https://arxiv.org/abs/2112.13762

Dataset: https://paperswithcode.com/dataset/sun-rgb-d

👉 @bigdata_1

AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition

Github: https://github.com/leaplabthu/adafocusv2

Paper: https://arxiv.org/abs/2112.14238v1

Tasks: https://paperswithcode.com/task/video-recognition

👉 @bigdata_1

Papers with Code 2021 : A Year in Review

https://www.kdnuggets.com/2021/12/2021-year-review-amazing-ai-papers.html

https://medium.com/paperswithcode/papers-with-code-2021-a-year-in-review-de75d5a77b8b

👉 @bigdata_1

PyramidTNT: Improved Transformer-in-Transformer Baselines with Pyramid Architecture

PyramidTNT achieves better performances than the previous state-of-the-art vision transformers such as Swin Transformer

Github: https://github.com/huawei-noah/CV-backbones

Paper: https://arxiv.org/abs/2201.00978v1

GhostNet: https://github.com/huawei-noah/CV-backbones/tree/master/ghostnet_pytorch

👉 @bigdata_1

AV-HuBERT (Audio-Visual Hidden Unit BERT)

AV-HuBERT is a self-supervised representation learning framework for audio-visual speech.

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

Facebook AI: https://ai.facebook.com/blog/ai-that-understands-speech-by-looking-as-well-as-hearing/

Paper: https://arxiv.org/abs/2201.02184

👉 @bigdata_1

pymdp: A Python library for active inference in discrete state spaces

Github: https://github.com/infer-actively/pymdp

Paper: https://arxiv.org/abs/2201.03904v1

Docs: https://pymdp-rtd.readthedocs.io/

Tasks: https://paperswithcode.com/task/bayesian-inference

👉 @bigdata_1

Uniformer: Unified Transformer for Efficient Spatiotemporal Representation Learning

Github: https://github.com/sense-x/uniformer

Paper: https://arxiv.org/abs/2201.04676v1

Tasks: https://paperswithcode.com/dataset/kinetics-600

👉 @bigdata_1

Introducing StylEx: A New Approach for Visual Explanation of Classifiers

Github: https://explaining-in-style.github.io/

Code: https://github.com/google/explaining-in-style

Article: https://ai.googleblog.com/2022/01/introducing-stylex-new-approach-for.html

Video: https://explaining-in-style.github.io/#video

👉 @bigdata_1

Omnivore: A Single Model for Many Visual Modalities

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

Code: https://github.com/facebookresearch/omnivore/blob/main/inference_tutorial.ipynb

Paper: https://arxiv.org/abs/2201.08377

Dataset: https://paperswithcode.com/dataset/epic-kitchens-100

👉 @bigdata_1

The first high-performance self-supervised algorithm that works for speech, vision, and text

Github: https://github.com/pytorch/fairseq/tree/main/examples/data2vec

Paper: https://ai.facebook.com/research/data2vec-a-general-framework-for-self-supervised-learning-in-speech-vision-and-language

Meta AI: https://ai.facebook.com/blog/the-first-high-performance-self-supervised-algorithm-that-works-for-speech-vision-and-text/

👉 @bigdata_1

ConvMixer, an extremely simple model that is similar in spirit to the ViT and the even-more-basic MLP-Mixer

Github: https://github.com/locuslab/convmixer

Paper: https://arxiv.org/pdf/2201.09792v1.pdf

👉 @bigdata_1

Pearl: Parallel Evolutionary and Reinforcement Learning Library

Github: https://github.com/locuslab/convmixer

Paper: https://arxiv.org/pdf/2201.09568v1.pdf

👉 @bigdata_1

When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism

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

Paper: https://arxiv.org/abs/2201.10801v1

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

👉 @bigdata_1