Accelerating DETR Convergence via Semantic-Aligned Matching

Github: https://github.com/ZhangGongjie/SAM-DETR

Documentatuin: https://cocodataset.org/

Paper: https://arxiv.org/abs/2203.06883v1


@ArtificialIntelligencedl

Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy

Github: https://github.com/davidzhangyuanhan/bamboo

Project: https://opengvlab.shlab.org.cn/bamboo/home

Paper: https://arxiv.org/abs/2203.07845

@ArtificialIntelligencedl

Context-Aware Drift Detection

Github: https://github.com/SeldonIO/alibi-detect

Project: https://docs.seldon.io/projects/alibi-detect/en/latest/

Paper: https://arxiv.org/abs/2203.08644v1

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

@ArtificialIntelligencedl

➡️ One-Shot Adaptation of GAN in Just One CLIP

A novel single-shot GAN adaptation method through unified CLIP space manipulations.

Github: https://github.com/submission6378/oneshotclip

Paper: https://arxiv.org/abs/2203.09301v1

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

Adapted models: https://drive.google.com/drive/folders/1svLJjuuK-yCCJ7Xq9l4Dy4gSuzplK_7i?usp=sharing

@ArtificialIntelligencedl

🔹 TensoRF: Tensorial Radiance Fields

A novel approach to model and reconstruct radiance fields

Github: https://github.com/apchenstu/TensoRF

Paper: https://arxiv.org/abs/2203.09517v1

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

Project page: https://apchenstu.github.io/TensoRF/

https://news.1rj.ru/str/ArtificialIntelligencedl

💬 Under the Morphosyntactic Lens: A Multifaceted Evaluation of Gender Bias in Speech Translation


Github: https://github.com/mgaido91/FBK-fairseq-ST

Paper: https://arxiv.org/abs/2203.09866v1

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

Project page: https://apchenstu.github.io/TensoRF/

@ArtificialIntelligencedl

🔎 Полное собрание шпаргалок по машинному обучению, статистике, Python и R

Article

@ArtificialIntelligencedl

🪄 Generative Invariance Transfer

Github: https://github.com/allanyangzhou/generative-invariance-transfer

Paper: https://arxiv.org/abs/2203.09739v1

Dataset: https://paperswithcode.com/dataset/cifar-10

@ArtificialIntelligencedl

🚀 AOT (Associating Objects with Transformers for Video Object Segmentation) in PyTorch

Github: https://github.com/yoxu515/aot-benchmark

Paper: https://arxiv.org/pdf/2203.11442v1.pdf

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

Demo: https://github.com/yoxu515/aot-benchmark/blob/main/datasets/Demo

@ArtificialIntelligencedl

📑 PubTables-1M: Towards comprehensive table extraction from unstructured documents

Github: https://github.com/microsoft/table-transformer

Paper: https://arxiv.org/pdf/2110.00061.pdf

Dataset: https://msropendata.com/datasets/505fcbe3-1383-42b1-913a-f651b8b712d3

https://news.1rj.ru/str/ArtificialIntelligencedl

🦾 Global Tracking Transformers

Github: https://github.com/xingyizhou/GTR

Demo: https://github.com/facebookresearch/detectron2/blob/main/GETTING_STARTED.md

Paper: https://arxiv.org/abs/2203.13250v1

Dataset: https://paperswithcode.com/dataset/mot17

https://news.1rj.ru/str/ArtificialIntelligencedl

⚡️ EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation

Github: https://github.com/tjiiv-cprg/epro-pnp

Paper: https://arxiv.org/abs/2203.13254v1

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

@ArtificialIntelligencedl

🎨 Autoregressive Image Generation using Residual Quantization

Github: https://github.com/kakaobrain/rq-vae-transformer

Pytorch: https://github.com/lucidrains/vector-quantize-pytorch

Paper: https://arxiv.org/abs/2203.01941v2

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

@ArtificialIntelligencedl

◾️ pyABC: Efficient and robust easy-to-use approximate Bayesian computation

Github: https://github.com/icb-dcm/pyabc

Paper: https://arxiv.org/abs/2203.13043v1

@ArtificialIntelligencedl

🧍 Discovering Human-Object Interaction Concepts via Self-Compositional Learning

Github: https://github.com/zhihou7/HOI-CL

Paper: https://arxiv.org/abs/2203.14272v1

Dataset: https://paperswithcode.com/dataset/hico-det

@ArtificialIntelligencedl

Semantic Line Detection Using Mirror Attention and Comparative Ranking and Matching

A novel algorithm to detect semantic lines is proposed in this paper. We develop three networks: detection network with mirror attention (D-Net) and comparative ranking and matching networks (R-Net and M-Net)

Github: https://github.com/dongkwonjin/Semantic-Line-DRM

Code: https://github.com/dongkwonjin/Semantic-Line-SLNet

Paper: https://arxiv.org/abs/2203.15285v1

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

@ArtificialIntelligencedl

Semantic Line Detection Using Mirror Attention and Comparative Ranking and Matching

A novel approach where the two processes for activity classification and entity estimation are interactive and complementary.

Github: https://github.com/jhcho99/coformer

Architecture: https://github.com/jhcho99/gsrtr

Paper: https://arxiv.org/abs/2203.16518v1

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

@ArtificialIntelligencedl

📱 Best it channels in Telegram

https://news.1rj.ru/str/ai_machinelearning_big_data - best ml channel
https://news.1rj.ru/str/ArtificialIntelligencedl - ai
https://news.1rj.ru/str/pythonl - largest python channel
https://news.1rj.ru/str/pro_python_code - python ru

https://news.1rj.ru/str/datascienceiot - ds, ml free books
https://news.1rj.ru/str/programming_books_it
https://news.1rj.ru/str/pythonlbooks - python books

https://news.1rj.ru/str/javanoscriptv - javanoscript channel
https://news.1rj.ru/str/about_javanoscript - advanced js
https://news.1rj.ru/str/JavaScript_testit - js tests
https://news.1rj.ru/str/Golang_google - Go channel
https://news.1rj.ru/str/golangl. -golang chat
https://news.1rj.ru/str/golang_jobsgo -golang jobs

https://news.1rj.ru/str/neural - neural nets
https://news.1rj.ru/str/hashdev - web development
https://news.1rj.ru/str/htmlcssjavas - web
https://news.1rj.ru/str/hr_itwork - jobs

https://news.1rj.ru/str/linux_kal - kali linux
https://news.1rj.ru/str/machinee_learning - ml chat
https://news.1rj.ru/str/linuxkalii - linux chat

https://news.1rj.ru/str/machinelearning_ru - ml ru
https://news.1rj.ru/str/python_testit - python tests
https://news.1rj.ru/str/csharp_ci- c#
https://news.1rj.ru/str/Machinelearningtest - machine learning test
https://news.1rj.ru/str/tensorflowblog - tensorflow
https://news.1rj.ru/str/Django_pythonl django
https://news.1rj.ru/str/javatg - java
https://news.1rj.ru/str/golangtests - Golang quizzes
https://news.1rj.ru/str/sqlhub - sql

https://news.1rj.ru/str/jsspeak - js chat

https://news.1rj.ru/str/memes_prog - it memes

💥 T5X is a modular, composable, research-friendly framework for high-performance, configurable, self-service training, evaluation, and inference of sequence models.

Github: https://github.com/google-research/t5x

Paper: https://arxiv.org/abs/2203.17189v1

@ArtificialIntelligencedl

💻 TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing (CVPR 2022)

Recent advances like StyleGAN have promoted the growth of controllable facial editing.

Github: https://github.com/billyxyb/transeditor

Paper: https://arxiv.org/abs/2203.17266v1

@ArtificialIntelligencedl

🔍 Exploiting Explainable Metrics for Augmented SGD

A new explainability metrics that measure the redundant information in a network's layers and exploit this information to augment the Stochastic Gradient Descent

Project

Code: https://github.com/mahdihosseini/rmsgd

Paper: https://arxiv.org/pdf/2203.16723v1.pdf

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

@ArtificialIntelligencedl