🔥 YOLOv6

YOLOv6-N hits 35.9% AP on COCO dataset with 1234 FPS on T4. YOLOv6-S strikes 43.5% AP with 495 FPS, and the quantized YOLOv6-S model achieves 43.3% AP at a accelerated speed of 869 FPS on T4.

git clone https://github.com/meituan/YOLOv6
cd YOLOv6
pip install -r requirements.txt

⚙️ Github
➡️ Paper
✔️ Colab
💻 Quantization Tutorial
📄 Dataset

@ai_machinelearning_big_data

💬 Text-Free Learning of a Natural Language Interface for Pretrained Face Generators

Fast text2StyleGAN, a natural language interface that adapts pre-trained GANs for text-guided human face synthesis.

pip install git+https://github.com/openai/CLIP.git

Github: https://github.com/duxiaodan/fast_text2stylegan

Paper: https://arxiv.org/abs/2209.03177v1

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

@ArtificialIntelligencedl

💬 AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog

git clone https://github.com/Tomiinek/Aargh.git
cd Aargh
pip install -e .

Github: https://github.com/tomiinek/aargh

Paper: https://arxiv.org/abs/2209.03632v1

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

@ArtificialIntelligencedl

🔭 AiRLoc: Aerial View Goal Localization with Reinforcement Learning

conda create -n airloc
conda activate airloc
pip install -r requirements.txt

Github: https://github.com/aleksispi/airloc

Paper: https://arxiv.org/abs/2209.03694v1

@ArtificialIntelligencedl

MassMIND: Massachusetts Maritime INfrared Dataset 1

Github: https://github.com/uml-marine-robotics/massmind

Paper: https://arxiv.org/abs/2209.04097v1

Dataset: https://drive.google.com/file/d/1T572f0oqy5JmuTvVEwkSUeXLWOSHl4hL/view

@ArtificialIntelligencedl

💫 F-COREF: Fast, Accurate and Easy to Use Coreference Resolution

a python package for fast, accurate, and easy-to-use English coreference resolution.

pip install fastcoref

Github: https://github.com/shon-otmazgin/fastcoref

Paper: https://arxiv.org/abs/2209.04280v2

Dataset: https://paperswithcode.com/dataset/multi-news

@ArtificialIntelligencedl

🦾 StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation

Github: https://github.com/adymaharana/storydalle

Paper: https://arxiv.org/abs/2209.06192

Model: https://github.com/adymaharana/storydalle/blob/main/MODEL_CARD.MD

Demo: https://github.com/adymaharana/storydalle/blob/main/DEMO.MD

Dataset: https://paperswithcode.com/dataset/multi-news

@ArtificialIntelligencedl

🚀 Entity Tagging: Extracting Entities in Text Without Mention Supervision

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

Paper: https://arxiv.org/abs/2209.06148v1

Model: https://github.com/adymaharana/storydalle/blob/main/MODEL_CARD.MD

Dataset: http://manikvarma.org/downloads/XC/XMLRepository.html

@ArtificialIntelligencedl

🛠 CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment

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

Paper: https://arxiv.org/abs/2209.06430v1

Dataset: https://paperswithcode.com/dataset/flickr30k

@ArtificialIntelligencedl

📲 Self-distilled Feature Aggregation for Self-supervised Monocular Depth Estimation

Github: https://github.com/ZM-Zhou/SMDE-Pytorch

Paper: https://arxiv.org/abs/2209.07088v1

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

@ArtificialIntelligencedl

🛠 Can We Solve 3D Vision Tasks Starting from A 2D Vision Transformer?

⚙️Github: https://github.com/VITA-Group/Simple3D-Former

📄Paper: https://arxiv.org/abs/2209.07026v1

📎Dataset: https://paperswithcode.com/dataset/modelnet

@ArtificialIntelligencedl

🖊 Causes of Catastrophic Forgetting in Class-Incremental Semantic Segmentation

Framework for Analysis of Class-Incremental Learning with 12 state-of-the-art methods and 3 baselines.

git clone https://github.com/mmasana/FACIL.git
cd FACIL

⚙️Github: https://github.com/mmasana/FACIL

📄Paper: https://arxiv.org/abs/2209.08010v1

📎Dataset: https://github.com/mmasana/FACIL/blob/master/src/datasets#datasets

@ArtificialIntelligencedl

🔌 HiPart: Hierarchical divisive clustering toolbox

It is a package with similar execution principles as the scikit-learn package. It also provides two types of static visualizations for all the algorithms executed in the package, with the addition of linkage generation for the divisive hierarchical clustering structure.

pip install HiPart

⚙️Github: https://github.com/panagiotisanagnostou/hipart

📄Paper: https://arxiv.org/abs/2209.08680v1

📎Dataset: https://paperswithcode.com/dataset/usps

@ArtificialIntelligencedl

A Framework for Benchmarking Clustering Algorithms

⚙️Github: https://github.com/gagolews/clustering-benchmarks

📄Paper: https://arxiv.org/abs/2209.09493v1

📎Results: https://github.com/gagolews/clustering-results-v1

@ArtificialIntelligencedl

🎼 A Framework for Benchmarking Clustering Algorithms

BEVStereo is a new multi-view 3D object detector using temporal stereo to enhance depth estimation.

⚙️Github: https://github.com/megvii-basedetection/bevstereo

📄Paper: https://arxiv.org/abs/2209.10248v1

🗒Dataset: https://paperswithcode.com/dataset/nuscenes

@ArtificialIntelligencedl

🗣 Robust Speech Recognition via Large-Scale Weak Supervision

Whisper is a general-purpose speech recognition model by Open AI.

pip install git+https://github.com/openai/whisper.git

⚙️ Github
💡 Colab
💻 Model
🗒 Paper
🦾 Dataset
✴️ HABR

@ai_machinelearning_big_data

🦾 Identity-Aware Hand Mesh Estimation and Personalization from RGB Images

A novel personalization pipeline to calibrate the intrinsic shape parameters using only a few unlabeled RGB images of the subject.

conda create -n IdHandMesh python=3.8
conda activate IdHandMesh

⚙️Github: https://github.com/deyingk/personalizedhandmeshestimation

📄Paper: https://arxiv.org/abs/2209.10840v1

🗒Dataset: https://paperswithcode.com/dataset/dexycb

@ArtificialIntelligencedl

MnTTS: An Open-Source Mongolian Text-to-Speech Synthesis Dataset and Accompanied Baseline

# Clone the repo
git clone https://github.com/walker-hyf/MnTTS.git
cd $PROJECT_ROOT_DIR

⚙️Github: https://github.com/walker-hyf/mntts

📄Paper: https://arxiv.org/abs/2209.10848v1

🗒Dataset: https://paperswithcode.com/dataset/ljspeech

@ArtificialIntelligencedl

🔸 Poisson Flow Generative Models

A new Poisson flow generative model (PFGM) that maps a uniform distribution on a high-dimensional hemisphere into any data distribution.

⚙️Github: https://github.com/newbeeer/poisson_flow

📄Paper: https://arxiv.org/abs/2209.11178v1

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

@ArtificialIntelligencedl

🚀 On Efficient Reinforcement Learning for Full-length Game of StarCraft II

In this work, we investigate a set of RL techniques for the full-length game of StarCraft II

⚙️Github: https://github.com/liuruoze/mini-AlphaStar

📄Paper: https://arxiv.org/abs/2209.11553v1

🗒HierNet-SC2: https://github.com/liuruoze/hiernet-sc2

@ArtificialIntelligencedl

🦾 EasyRec: An easy-to-use, extendable and efficient framework for building industrial recommendation systems


EasyRec implements state of the art deep learning models used in common recommendation tasks: candidate generation(matching), scoring(ranking), and multi-task learning.

⚙️Github: https://github.com/alibaba/easyrec

📄Paper: https://arxiv.org/abs/2209.12766v1

🗒Dataset: https://paperswithcode.com/dataset/criteo

@ArtificialIntelligencedl