Artificial Intelligence
βοΈ PeRFception - Perception using Radiance Fields Github: https://github.com/POSTECH-CVLab/PeRFception Project: https://postech-cvlab.github.io/PeRFception Supplementary Materials: https://openreview.net/attachment?id=MzaPEKHv-0J&name=supplementary_materialβ¦
π Unrestricted Black-box Adversarial Attack Using GAN with Limited Queries
Github: https://github.com/ndb796/latenthsja
Source Codes: https://github.com/ndb796/LatentHSJA/blob/main/attacks/HSJA_for_Facial_Identity_Recognition_Model.ipynb
Dataset: https://postechackr-my.sharepoint.com/:u:/g/personal/dongbinna_postech_ac_kr/ES-jbCNC6mNHhCyR4Nl1QpYBlxVOJ5YiVerhDpzmoS9ezA
@ArtificialIntelligencedl
Github: https://github.com/ndb796/latenthsja
Source Codes: https://github.com/ndb796/LatentHSJA/blob/main/attacks/HSJA_for_Facial_Identity_Recognition_Model.ipynb
Dataset: https://postechackr-my.sharepoint.com/:u:/g/personal/dongbinna_postech_ac_kr/ES-jbCNC6mNHhCyR4Nl1QpYBlxVOJ5YiVerhDpzmoS9ezA
@ArtificialIntelligencedl
π₯7π2
π Unbiased Multi-Modality Guidance for Image Inpainting
Github: https://github.com/yeates/MMT
Paper: https://arxiv.org/abs/2208.11844v1
Dataset: https://paperswithcode.com/dataset/cityscapes
Demo: https://github.com/yeates/MMT/blob/main
Pre-trained Models: https://drive.google.com/drive/folders/1x1_VOBDVFtYyVloW-BYNZIVobA67gxQ_?usp=sharing
@ArtificialIntelligencedl
Github: https://github.com/yeates/MMT
Paper: https://arxiv.org/abs/2208.11844v1
Dataset: https://paperswithcode.com/dataset/cityscapes
Demo: https://github.com/yeates/MMT/blob/main
Pre-trained Models: https://drive.google.com/drive/folders/1x1_VOBDVFtYyVloW-BYNZIVobA67gxQ_?usp=sharing
@ArtificialIntelligencedl
π7
π Refine and Represent: Region-to-Object Representation Learning
Github: https://github.com/kkallidromitis/r2o
Paper: https://arxiv.org/abs/2208.11821v1
Dataset: https://paperswithcode.com/dataset/cub-200-2011
@ArtificialIntelligencedl
Github: https://github.com/kkallidromitis/r2o
Paper: https://arxiv.org/abs/2208.11821v1
Dataset: https://paperswithcode.com/dataset/cub-200-2011
@ArtificialIntelligencedl
π9
π² Arbitrary Shape Text Detection via Segmentation with Probability Maps
an innovative and robust segmentation-based detection method via probability maps for accurately detecting text instances.
Github: https://github.com/gxym/textpms
Paper: https://arxiv.org/abs/2208.12419v1
Dataset: https://paperswithcode.com/dataset/msra-td500
@ArtificialIntelligencedl
an innovative and robust segmentation-based detection method via probability maps for accurately detecting text instances.
Github: https://github.com/gxym/textpms
Paper: https://arxiv.org/abs/2208.12419v1
Dataset: https://paperswithcode.com/dataset/msra-td500
@ArtificialIntelligencedl
π₯7π1
π Learning Affordance Grounding from Exocentric Images
Github: https://github.com/lhc1224/Cross-View-AG
Paper: https://arxiv.org/abs/2208.13196v1
Dataset: https://paperswithcode.com/dataset/3d-affordancenet
@ArtificialIntelligencedl
Github: https://github.com/lhc1224/Cross-View-AG
Paper: https://arxiv.org/abs/2208.13196v1
Dataset: https://paperswithcode.com/dataset/3d-affordancenet
@ArtificialIntelligencedl
π7
βοΈ Reweighting Strategy based on Synthetic Data Identification for Sentence Similarity
novel approach that first trains the classifier to measure the importance of each sentence
Github: https://github.com/ddehun/coling2022_reweighting_sts
Paper: https://arxiv.org/abs/2208.13376v2
Dataset: https://paperswithcode.com/dataset/mrpc
@ArtificialIntelligencedl
novel approach that first trains the classifier to measure the importance of each sentence
Github: https://github.com/ddehun/coling2022_reweighting_sts
Paper: https://arxiv.org/abs/2208.13376v2
Dataset: https://paperswithcode.com/dataset/mrpc
@ArtificialIntelligencedl
π₯7
π¨ Controllable 3D Generative Adversarial Face Model via Disentangling Shape and Appearance
Github: https://github.com/aashishrai3799/3DFaceCAM
Project: https://aashishrai3799.github.io/3DFaceCAM
Paper: https://arxiv.org/abs/2208.14263
Video: https://drive.google.com/file/d/1PqIN4Rzp4vapWs2pUegUEoMhg4lM2Smy/view?usp=sharing
Dataset: https://paperswithcode.com/dataset/facescape
@ArtificialIntelligencedl
Github: https://github.com/aashishrai3799/3DFaceCAM
Project: https://aashishrai3799.github.io/3DFaceCAM
Paper: https://arxiv.org/abs/2208.14263
Video: https://drive.google.com/file/d/1PqIN4Rzp4vapWs2pUegUEoMhg4lM2Smy/view?usp=sharing
Dataset: https://paperswithcode.com/dataset/facescape
@ArtificialIntelligencedl
π7
π AccoMontage2: A Complete Harmonization and Accompaniment Arrangement System
Github: https://github.com/billyblu2000/accomontage2
Paper: https://arxiv.org/abs/2209.00353v1
Dataset: https://drive.google.com/drive/folders/1z8oW16dZtdS06woHc7_rxserNJRrkc4s?usp=sharing
@ArtificialIntelligencedl
Github: https://github.com/billyblu2000/accomontage2
Paper: https://arxiv.org/abs/2209.00353v1
Dataset: https://drive.google.com/drive/folders/1z8oW16dZtdS06woHc7_rxserNJRrkc4s?usp=sharing
@ArtificialIntelligencedl
π9
π« AccoMontage2: A Complete Harmonization and Accompaniment Arrangement System
AccoMontage2, a system capable of doing full-length song harmonization and accompaniment arrangement based on a lead melod
Github: https://github.com/billyblu2000/accomontage2
Paper: https://arxiv.org/abs/2209.00353v1
Dataset: https://drive.google.com/drive/folders/1z8oW16dZtdS06woHc7_rxserNJRrkc4s?usp=sharing
@ArtificialIntelligencedl
AccoMontage2, a system capable of doing full-length song harmonization and accompaniment arrangement based on a lead melod
Github: https://github.com/billyblu2000/accomontage2
Paper: https://arxiv.org/abs/2209.00353v1
Dataset: https://drive.google.com/drive/folders/1z8oW16dZtdS06woHc7_rxserNJRrkc4s?usp=sharing
@ArtificialIntelligencedl
β€7π3
This media is not supported in your browser
VIEW IN TELEGRAM
π Real-time 3D Single Object Tracking with Transformer
Github: https://github.com/shanjiayao/ptt
Paper: https://arxiv.org/abs/2209.00860v1
Dataset: https://paperswithcode.com/dataset/kitti
Video: https://youtu.be/Cajj6iHFvrc
@ArtificialIntelligencedl
Github: https://github.com/shanjiayao/ptt
Paper: https://arxiv.org/abs/2209.00860v1
Dataset: https://paperswithcode.com/dataset/kitti
Video: https://youtu.be/Cajj6iHFvrc
@ArtificialIntelligencedl
π4
π Structural Bias for Aspect Sentiment Triplet Extraction
Github: https://github.com/genezc/structbias
Paper: https://arxiv.org/abs/2209.00820v1
@ArtificialIntelligencedl
Github: https://github.com/genezc/structbias
Paper: https://arxiv.org/abs/2209.00820v1
@ArtificialIntelligencedl
π4π₯1
β‘οΈ Continual Learning: Fast and Slow
Dual Networks a general continual learning framework comprising a fast learning system for supervised learning of pattern-separated representation.
Github: https://github.com/phquang/DualNet
Paper: https://arxiv.org/abs/2209.02370v1
Dataset: https://paperswithcode.com/dataset/svhn
@ArtificialIntelligencedl
Dual Networks a general continual learning framework comprising a fast learning system for supervised learning of pattern-separated representation.
Github: https://github.com/phquang/DualNet
Paper: https://arxiv.org/abs/2209.02370v1
Dataset: https://paperswithcode.com/dataset/svhn
@ArtificialIntelligencedl
π5
π§ Morphology-preserving Autoregressive 3D Generative Modelling of the Brain
Github: https://github.com/amigolab/synthanatomy
Paper: https://arxiv.org/abs/2209.03177v1
Project: https://amigos.ai/thisbraindoesnotexist/
@ArtificialIntelligencedl
Github: https://github.com/amigolab/synthanatomy
Paper: https://arxiv.org/abs/2209.03177v1
Project: https://amigos.ai/thisbraindoesnotexist/
@ArtificialIntelligencedl
π₯4
Forwarded from Machinelearning
π₯ 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
βοΈ Github
β‘οΈ Paper
βοΈ Colab
π» Quantization Tutorial
π Dataset
@ai_machinelearning_big_data
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
βοΈ Github
β‘οΈ Paper
βοΈ Colab
π» Quantization Tutorial
π Dataset
@ai_machinelearning_big_data
π₯6π€1
This media is not supported in your browser
VIEW IN TELEGRAM
π¬ 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
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
π6
π¬ 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
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
π5
π 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
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
π4π₯3
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
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
π6
π« F-COREF: Fast, Accurate and Easy to Use Coreference Resolution
a python package for fast, accurate, and easy-to-use English coreference resolution.
Github: https://github.com/shon-otmazgin/fastcoref
Paper: https://arxiv.org/abs/2209.04280v2
Dataset: https://paperswithcode.com/dataset/multi-news
@ArtificialIntelligencedl
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
π4
π¦Ύ 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
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
π8π₯1