Text2Poster: Laying out Stylized Texts on Retrieved Images
π₯ Github: https://github.com/chuhaojin/text2poster-icassp-22
β© Paper: https://arxiv.org/abs/2301.02363v1
ArtificialIntelligencedl
ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π7β€1π₯1
PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers
π₯ Github: https://github.com/yuxumin/PoinTr#pretrained-models
β© Paper: https://arxiv.org/abs/2108.08839
β‘οΈ Datasets: https://github.com/yuxumin/PoinTr/blob/master/DATASET.md
βοΈ Video: https://youtu.be/mSGphas0p8g
ArtificialIntelligencedl
ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π4β€1π₯1
DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention
π₯ Github: https://github.com/cecret3350/DEA-Net
β© Paper: https://arxiv.org/abs/2301.04805v1
β‘οΈ Datasets: https://paperswithcode.com/dataset/reside
ArtificialIntelligencedl
ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π4β€2π₯2
This media is not supported in your browser
VIEW IN TELEGRAM
Proximal Stochastic Polyak
π₯ Github: https://github.com/fabian-sp/ProxSPS
β© Paper: https://arxiv.org/abs/2301.04935v1
ArtificialIntelligencedl
ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π6β€1π₯1π€1
Tracr: Compiled Transformers as a Laboratory for Interpretability
π₯ Github: https://github.com/deepmind/tracr
β© Paper: https://arxiv.org/abs/2301.05062v1
ArtificialIntelligencedl
git clone https://github.com/deepmind/tracr
cd tracr
pip3 install .ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π7π₯2β€1π€1
This media is not supported in your browser
VIEW IN TELEGRAM
ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π6β€1π₯1
π Heterogeneous Multi-Robot Reinforcement Learning
π₯ Github: https://github.com/proroklab/vectorizedmultiagentsimulator
β© Paper: https://arxiv.org/abs/2207.03530
π₯ Colab: https://colab.research.google.com/github/proroklab/VectorizedMultiAgentSimulator/blob/main/notebooks/VMAS_Use_vmas_environment.ipynb
ArtificialIntelligencedl
pip install vmasArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π₯5π3β€1
Cross-Modal Adaptation with Multimodal Models
π₯ Github: https://github.com/linzhiqiu/cross_modal_adaptation
β© Paper: https://arxiv.org/abs/2301.06267v2
β‘οΈ Dataset: https://paperswithcode.com/dataset/esc-50
ArtificialIntelligencedl
conda create -n cross_modal python=3.9ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π4π₯2β€1
Using CycleGANs to Generate Realistic STEM Images for Machine Learning
π₯ Github: https://github.com/ClarkResearchGroup/stem-learning
β© Paper: https://arxiv.org/abs/2301.07743v1
ArtificialIntelligencedl
git clone https://github.com/ClarkResearchGroup/stem-learning.gitArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
β€5π2π₯°1
ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π₯5β€1π1
An Empirical Study of Metrics to Measure Representational Harms in Pre-Trained Language Models
π₯ Github: https://github.com/microsoft/SafeNLP
β© Paper: https://arxiv.org/abs/2301.09211v1
β‘οΈ Dataset: https://paperswithcode.com/dataset/https-github-com-microsoft-safenlp
ArtificialIntelligencedl
ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π7β€2π₯1
βοΈ Geometric GNN Dojo
π₯ Github: https://github.com/chaitjo/geometric-gnn-dojo
β© Paper: https://arxiv.org/abs/2301.09308v1
β‘οΈ Dataset: https://paperswithcode.com/dataset/cluster
ArtificialIntelligencedl
ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π₯5π2β€1
A Simple Adaptive Unfolding Network for Hyperspectral Image Reconstruction
π₯ Github: https://github.com/hustvl/saunet
β© Paper: https://arxiv.org/abs/2301.10208v1
ArtificialIntelligencedl
ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π5β€1π₯1
Distilling Cognitive Backdoor Patterns within an Image
π₯ Github: https://github.com/HanxunH/CognitiveDistillation
β© Paper: https://arxiv.org/abs/2301.10908v1
β‘οΈ Dataset: https://paperswithcode.com/dataset/celeba
ArtificialIntelligencedl
ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π₯5β€1π1
Koopman neural operator as a mesh-free solver of non-linear partial differential equations
π₯ Github: https://github.com/koopman-laboratory/koopmanlab
β© Paper: https://arxiv.org/abs/2301.10022v1
β‘οΈ Dataset: https://drive.google.com/drive/folders/1UnbQh2WWc6knEHbLn-ZaXrKUZhp7pjt-
ArtificialIntelligencedl
pip install koopmanlabArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π4β€2π₯1π€1π1
ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π₯7π4β€2
π Project: https://opennlplab.github.io/AVSBench/
ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π4π₯1π₯°1
Forwarded from Machinelearning
Over 3000 models, and over 100 datasets on the Hugging Face Hub.
ΠΠΎΠ»Π΅Π΅ 3000 ΠΌΠΎΠ΄Π΅Π»Π΅ΠΉ ΠΊΠΎΠΌΠΏΡΡΡΠ΅ΡΠ½ΠΎΠ³ΠΎ Π·ΡΠ΅Π½ΠΈΡ ΠΈ Π±ΠΎΠ»Π΅Π΅ 100 Π΄Π°ΡΠ°ΡΠ΅ΡΠΎΠ² Π½Π° Hugging Face Hub.
Supported vision tasks and Pipelines
Training your own vision models
Integration with timm
Diffusers
Support for third-party libraries
Datasets
HugsVision
Model documentation
Hugging Face notebooks
Hugging Face example scripts
Task pages
Timm
Generate 3D voxels from a predicted depth map of an input image
Open vocabulary semantic segmentation
Narrate videos by generating captions
Classify videos from YouTube
Zero-shot video classification
Visual question-answering
Use zero-shot image classification to find best captions for an image to generate similar images
π€ AutoTrain
AutoTrain
Image classification
Automatic model evaluation
π¦Ύ Zero-shot models
CLIP
OWL-ViT
CLIPSeg
GroupViT
X-CLIP
π Deployment
Deploying TensorFlow Vision Models in Hugging Face with TF Serving
Deploying ViT on Kubernetes with TF Serving
Deploying ViT on Vertex AI
Deploying ViT with TFX and Vertex AI
@ai_machinelearning_big_data
Please open Telegram to view this post
VIEW IN TELEGRAM
π7β€3π₯1
NP-Match: When Neural Processes meet Semi-Supervised Learning
π₯ Github: https://github.com/jianf-wang/np-match
β© Paper: https://arxiv.org/abs/2301.13569v1
β‘οΈ Dataset: https://paperswithcode.com/dataset/stl-10
ArtificialIntelligencedl
ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π4β€2π₯1
What Makes Good Examples for Visual In-Context Learning?
π₯ Github: https://github.com/zhangyuanhan-ai/visual_prompt_retrieval
β© Paper: https://arxiv.org/abs/2301.13670v2
β‘οΈ Dataset: https://paperswithcode.com/dataset/coco
ArtificialIntelligencedl
ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π4β€1π₯1