🦉 OWL-ViT: Open-World Object Detection with Vision Transformers

OWL-ViT is an open-vocabulary object detector.

Github: https://github.com/google-research/scenic/tree/main/scenic/projects/owl_vit

Paper: https://arxiv.org/abs/2205.06230

Colab: https://colab.research.google.com/github/google-research/scenic/blob/main/scenic/projects/owl_vit/notebooks/OWL_ViT_minimal_example.ipynb

Dataset: https://paperswithcode.com/dataset/objects365

@ai_machinelearning_big_data

AdaVAE: Exploring Adaptive GPT-2s in Variational Auto-Encoders for Language Modeling

First VAE framework empowered with adaptive GPT-2s (AdaVAE).

Github: https://github.com/ImKeTT/adavae

Paper: https://arxiv.org/abs/2205.05862v1

Task: https://paperswithcode.com/task/representation-learning

Efficient and performance-portable vector software

CPUs provide SIMD/vector instructions that apply the same operation to multiple data items. This can reduce energy usage e.g. fivefold because fewer instructions are executed. We also often see 5-10x speedups.

Code: https://github.com/google/highway

Paper: https://arxiv.org/abs/2205.05982v1

Testing: https://github.com/google/highway/blob/master/g3doc/release_testing_process.md

@ai_machinelearning_big_data

[RK-Net]Joint Representation Learning and Keypoint Detection for Cross-view Geo-localization

Github: https://github.com/AggMan96/RK-Net

Paper: https://zhunzhong.site/paper/RK_Net.pdf

Dataset: https://paperswithcode.com/dataset/university-1652

@ai_machinelearning_big_data

Group R-CNN for Point-based Weakly Semi-supervised Object Detection

Instance-aware representation learning which consists of instance-aware feature enhancement and instance-aware parameter generation to overcome this issue.

Code: https://github.com/jshilong/grouprcnn

Installation: https://mmdetection.readthedocs.io/en/v2.18.1/get_started.html#installation

Paper: https://arxiv.org/abs/2205.05920v1

Task: https://paperswithcode.com/task/object-detection

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

@ai_machinelearning_big_data

Towards Unified Keyframe Propagation Models

A two-stream approach, where high-frequency features interact locally and low-frequency features interact globally.

Github: https://github.com/runwayml/guided-inpainting

Paper: https://arxiv.org/abs/2205.09731v1

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

@ai_machinelearning_big_data

👀 Sockeye

Sockeye is an open-source sequence-to-sequence framework for Neural Machine Translation built on PyTorch.

Code: https://github.com/awslabs/sockeye

Tutorial: https://github.com/awslabs/sockeye/blob/main/docs/tutorials/wmt_large.md

Paper: https://arxiv.org/abs/2205.06618v1

@ai_machinelearning_big_data

🖇 A graph-transformer for whole slide image classification

Graph-Transformer (GT) that fuses a graph-based representation of an WSI and a vision transformer for processing pathology images.

Github: https://github.com/vkola-lab/tmi2022

Paper: https://arxiv.org/abs/2205.09671v1

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

☑️ TorchSSL

A Pytorch-based toolbox for semi-supervised learning.

Code: https://github.com/torchssl/torchssl

Paper: https://arxiv.org/abs/2205.07246v1

Logs and weights: https://onedrive.live.com/?authkey=%21AJ%2DwKMa%2DENcbk1s&id=AF426F3217F6565A%213488&cid=AF426F3217F6565A

@ai_machinelearning_big_data

RankGen - Improving Text Generation with Large Ranking Models

RankGen is a 1.2 billion encoder model which maps prefixes and generations from any language model (in continutation to the prefix) to a shared vector space.

Github: https://github.com/martiansideofthemoon/rankgen

Paper: https://arxiv.org/abs/2205.09726

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

@ai_machinelearning_big_data

🧍‍♂ AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars

Github: https://github.com/hongfz16/avatarclip

Colab demo: https://colab.research.google.com/drive/1dfaecX7xF3nP6fyXc8XBljV5QY1lc1TR?usp=sharing

Paper: https://arxiv.org/abs/2205.08535v1

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

Instructions: https://github.com/hongfz16/AvatarCLIP/blob/main/Avatar2FBX/README.md

@ai_machinelearning_big_data

☠️ PYSKL: Towards Good Practices for Skeleton Action Recognition

Skeleton-based action recognition

Github: https://github.com/kennymckormick/pyskl

Paper: https://arxiv.org/abs/2205.09443v1

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

@ai_machinelearning_big_data

📝 Automated Crossword Solving

Pretrained models, precomputed FAISS embeddings, and a crossword clue-answer dataset.

Github: https://github.com/albertkx/berkeley-crossword-solver

Paper: https://arxiv.org/abs/2205.09665v1

Dataset: https://www.xwordinfo.com/JSON/

@ai_machinelearning_big_data

🦄 Imagen unprecedented photorealism × deep level of language understanding From Google

Home: https://gweb-research-imagen.appspot.com/

Paper: https://gweb-research-imagen.appspot.com/paper.pdf

@ai_machinelearning_big_data

⚙️ Time-series Transformer Generative Adversarial Networks

Github: https://github.com/jsyoon0823/TimeGAN

Paper: https://arxiv.org/abs/2205.11164v1

Stock data: https://finance.yahoo.com/quote/GOOG/history

Energy data: http://archive.ics.uci.edu/ml/datasets/Appliances+energy+prediction


@ai_machinelearning_big_data

💻 BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework

Github: https://github.com/adlab-autodrive/bevfusion

Paper: https://arxiv.org/abs/2205.13790v1

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

📍 Perturbation Augmentation for Fairer NLP

Responsible NLP projects from Meta AI.

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

Paper: https://arxiv.org/abs/2205.12586v1

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

@ai_machinelearning_big_data

🟢 Green Hierarchical Vision Transformer for Masked Image Modeling

Github: https://github.com/layneh/greenmim

Paper: https://arxiv.org/abs/2205.13515v1

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

@ai_machinelearning_big_data

🔥 210 Machine Learning Projects (with Source Code) That You Can Build Today

Projects lists