This media is not supported in your browser
VIEW IN TELEGRAM
Parameter Prediction for Unseen Deep Architectures
improved GHNs trained on our DeepNets-1M allow to predict parameters for diverse networks, even if they are very different from those used to train GHNs (e.g. ResNet-50)
Github: https://github.com/facebookresearch/ppuda
Paper: https://arxiv.org/abs/2207.10049v1
Tasks: https://paperswithcode.com/dataset/deepnets-1m
@ArtificialIntelligencedl
improved GHNs trained on our DeepNets-1M allow to predict parameters for diverse networks, even if they are very different from those used to train GHNs (e.g. ResNet-50)
Github: https://github.com/facebookresearch/ppuda
Paper: https://arxiv.org/abs/2207.10049v1
Tasks: https://paperswithcode.com/dataset/deepnets-1m
@ArtificialIntelligencedl
π3
π― Object-Compositional Neural Implicit Surfaces
Github: https://github.com/qianyiwu/objsdf
Paper: https://arxiv.org/abs/2207.09686v1
Project: https://qianyiwu.github.io/objectsdf/
Dataset: https://paperswithcode.com/dataset/scannet
@ArtificialIntelligencedl
Github: https://github.com/qianyiwu/objsdf
Paper: https://arxiv.org/abs/2207.09686v1
Project: https://qianyiwu.github.io/objectsdf/
Dataset: https://paperswithcode.com/dataset/scannet
@ArtificialIntelligencedl
π6
π Sobolev Training for Implicit Neural Representations with Approximated Image Derivatives
a training paradigm for INRs whose target output is image pixels, to encode image derivatives in addition to image values in the neural network.
Github: https://github.com/megvii-research/Sobolev_INRs
Paper: https://arxiv.org/abs/2207.10395v1
Dataset: https://drive.google.com/drive/folders/128yBriW1IG_3NJ5Rp7APSTZsJqdJdfc1
@ArtificialIntelligencedl
a training paradigm for INRs whose target output is image pixels, to encode image derivatives in addition to image values in the neural network.
Github: https://github.com/megvii-research/Sobolev_INRs
Paper: https://arxiv.org/abs/2207.10395v1
Dataset: https://drive.google.com/drive/folders/128yBriW1IG_3NJ5Rp7APSTZsJqdJdfc1
@ArtificialIntelligencedl
π2
Forwarded from Machinelearning
π§Ώ Generative Multiplane Images: Making a 2D GAN 3D-Aware
What is really needed to make an existing 2D GAN 3D-aware? To answer this question, we modify a classical GAN, i.e., StyleGANv2, as little as possible. We find that only two modifications are absolutely necessary: 1) a multiplane image style generator branch which produces a set of alpha maps conditioned on their depth; 2) a pose-conditioned discriminator.
Github: https://github.com/apple/ml-gmpi
Paper: https://arxiv.org/abs/2207.10642v1
Dataset: https://paperswithcode.com/dataset/metfaces
Project: https://xiaoming-zhao.github.io/projects/gmpi/
Pretrained checkpoints: https://drive.google.com/drive/folders/1MEIjen0XOIW-kxEMfBUONnKYrkRATSR_
@ai_machinelearning_big_data
What is really needed to make an existing 2D GAN 3D-aware? To answer this question, we modify a classical GAN, i.e., StyleGANv2, as little as possible. We find that only two modifications are absolutely necessary: 1) a multiplane image style generator branch which produces a set of alpha maps conditioned on their depth; 2) a pose-conditioned discriminator.
Github: https://github.com/apple/ml-gmpi
Paper: https://arxiv.org/abs/2207.10642v1
Dataset: https://paperswithcode.com/dataset/metfaces
Project: https://xiaoming-zhao.github.io/projects/gmpi/
Pretrained checkpoints: https://drive.google.com/drive/folders/1MEIjen0XOIW-kxEMfBUONnKYrkRATSR_
@ai_machinelearning_big_data
π4β€1
Grounding Visual Representations with Texts for Domain Generalization
Github: https://github.com/mswzeus/gvrt
Paper: https://arxiv.org/abs/2207.10285v1
Dataset: https://paperswithcode.com/dataset/pacs
@ArtificialIntelligencedl
Github: https://github.com/mswzeus/gvrt
Paper: https://arxiv.org/abs/2207.10285v1
Dataset: https://paperswithcode.com/dataset/pacs
@ArtificialIntelligencedl
π4
AutoAlignV2: Deformable Feature Aggregation for Dynamic Multi-Modal 3D Object Detection
Github: https://github.com/zehuichen123/autoalignv2
Paper: https://arxiv.org/abs/2207.10316v1
Dataset: https://paperswithcode.com/dataset/nuscenes
@ArtificialIntelligencedl
Github: https://github.com/zehuichen123/autoalignv2
Paper: https://arxiv.org/abs/2207.10316v1
Dataset: https://paperswithcode.com/dataset/nuscenes
@ArtificialIntelligencedl
π8
This media is not supported in your browser
VIEW IN TELEGRAM
π±ββοΈ Multiface: A Dataset for Neural Face Rendering
Github: https://github.com/facebookresearch/multiface
Paper: https://arxiv.org/abs/2207.11243v1
Dataset: https://paperswithcode.com/dataset/facewarehouse
@ArtificialIntelligencedl
Github: https://github.com/facebookresearch/multiface
Paper: https://arxiv.org/abs/2207.11243v1
Dataset: https://paperswithcode.com/dataset/facewarehouse
@ArtificialIntelligencedl
π12β€1
β
C3-SL: Circular Convolution-Based Batch-Wise Compression for Communication-Efficient Split Learning
Circular convolution-based batch-wise compression for SL (C3-SL) to compress multiple features into one single feature.
Github: https://github.com/WesleyHsieh0806/C3-SL
Paper: https://arxiv.org/abs/2207.12397v1
Dataset: https://github.com/WesleyHsieh0806/C3-SL#books-prepare-dataset
Pretrained Dataset: https://github.com/WesleyHsieh0806/C3-SL/blob/master/Pretrained_Dataset.md
@ArtificialIntelligencedl
Circular convolution-based batch-wise compression for SL (C3-SL) to compress multiple features into one single feature.
Github: https://github.com/WesleyHsieh0806/C3-SL
Paper: https://arxiv.org/abs/2207.12397v1
Dataset: https://github.com/WesleyHsieh0806/C3-SL#books-prepare-dataset
Pretrained Dataset: https://github.com/WesleyHsieh0806/C3-SL/blob/master/Pretrained_Dataset.md
@ArtificialIntelligencedl
π2
π Compositional Human-Scene Interaction Synthesis with Semantic Control (COINS)
Github: https://github.com/zkf1997/coins
Paper: https://arxiv.org/abs/2207.12824v1
Project: https://zkf1997.github.io/COINS/index.html
@ArtificialIntelligencedl
Github: https://github.com/zkf1997/coins
Paper: https://arxiv.org/abs/2207.12824v1
Project: https://zkf1997.github.io/COINS/index.html
@ArtificialIntelligencedl
β€8
CENet: Toward Concise and Efficient LiDAR Semantic Segmentation for Autonomous Driving
Github: https://github.com/huixiancheng/cenet
Paper: https://arxiv.org/abs/2207.12691v1
Project: https://paperswithcode.com/dataset/semantickitti
@ArtificialIntelligencedl
Github: https://github.com/huixiancheng/cenet
Paper: https://arxiv.org/abs/2207.12691v1
Project: https://paperswithcode.com/dataset/semantickitti
@ArtificialIntelligencedl
π5π€1
Identifying Hard Noise in Long-Tailed Sample Distribution
Github: https://github.com/yxymessi/h2e-framework
Paper: https://arxiv.org/abs/2207.13378v1
Dataset: https://paperswithcode.com/dataset/food-101
@ArtificialIntelligencedl
Github: https://github.com/yxymessi/h2e-framework
Paper: https://arxiv.org/abs/2207.13378v1
Dataset: https://paperswithcode.com/dataset/food-101
@ArtificialIntelligencedl
π₯6
Visual Recognition by Request
Github: https://github.com/chufengt/Visual-Recognition-by-Request
Paper: https://arxiv.org/coming_soon
Dataset: https://paperswithcode.com/dataset/cityscapes-panoptic-parts
@ArtificialIntelligencedl
Github: https://github.com/chufengt/Visual-Recognition-by-Request
Paper: https://arxiv.org/coming_soon
Dataset: https://paperswithcode.com/dataset/cityscapes-panoptic-parts
@ArtificialIntelligencedl
GitHub
GitHub - chufengt/ViRReq: Code for the paper "Visual Recognition by Request".
Code for the paper "Visual Recognition by Request". - GitHub - chufengt/ViRReq: Code for the paper "Visual Recognition by Request".
π7
π§ββ Body-Part Map for Interactiveness
body-part saliency maps to mine informative cues from not only the targeted person, but also other persons in the image.
Github: https://github.com/enlighten0707/body-part-map-for-interactiveness
Paper: https://arxiv.org/abs/2207.14192v1
Dataset: https://paperswithcode.com/dataset/hico-det
@ArtificialIntelligencedl
body-part saliency maps to mine informative cues from not only the targeted person, but also other persons in the image.
Github: https://github.com/enlighten0707/body-part-map-for-interactiveness
Paper: https://arxiv.org/abs/2207.14192v1
Dataset: https://paperswithcode.com/dataset/hico-det
@ArtificialIntelligencedl
π7π₯2
π§ββ Body-Part Map for Interactiveness
new lighting estimation and editing framework to generate high-dynamic-range (HDR) indoor panorama lighting
Github: https://github.com/wanggcong/stylelight
Paper: https://arxiv.org/abs/2207.14811v1
Video: https://www.youtube.com/watch?v=sHeWK1MSPg4
Model: https://drive.google.com/file/d/1vHfwrtgk0EjZlS14Ye5lASJ0R4IWl_4w/view?usp=sharing
Project: https://style-light.github.io/
Dataset: https://indoor.hdrdb.com/
@ArtificialIntelligencedl
new lighting estimation and editing framework to generate high-dynamic-range (HDR) indoor panorama lighting
Github: https://github.com/wanggcong/stylelight
Paper: https://arxiv.org/abs/2207.14811v1
Video: https://www.youtube.com/watch?v=sHeWK1MSPg4
Model: https://drive.google.com/file/d/1vHfwrtgk0EjZlS14Ye5lASJ0R4IWl_4w/view?usp=sharing
Project: https://style-light.github.io/
Dataset: https://indoor.hdrdb.com/
@ArtificialIntelligencedl
π6π₯2
π Learning to Grasp on the Moon from 3D Octree Observations with Deep Reinforcement Learning
Github: https://github.com/andrejorsula/drl_grasping
Paper: https://arxiv.org/abs/2208.00818v1
@ArtificialIntelligencedl
Github: https://github.com/andrejorsula/drl_grasping
Paper: https://arxiv.org/abs/2208.00818v1
@ArtificialIntelligencedl
π₯7
π¦Ύ PyABSA - Open Framework for Aspect-based Sentiment Analysis
Github: https://github.com/yangheng95/pyabsa
Paper: https://arxiv.org/abs/2208.01368v1
Dataset: https://paperswithcode.com/dataset/sst
Colab: https://github.com/yangheng95/PyABSA/blob/release/readme/tutorial_readme.md
@ArtificialIntelligencedl
Github: https://github.com/yangheng95/pyabsa
Paper: https://arxiv.org/abs/2208.01368v1
Dataset: https://paperswithcode.com/dataset/sst
Colab: https://github.com/yangheng95/PyABSA/blob/release/readme/tutorial_readme.md
@ArtificialIntelligencedl
π6
π Negative Frames Matter in Egocentric Visual Query 2D Localization
Github: https://github.com/facebookresearch/vq2d_cvpr
Paper: https://arxiv.org/abs/2208.01949v1
VQ2D baseline: https://github.com/EGO4D/episodic-memory/tree/main/VQ2D
@ArtificialIntelligencedl
Github: https://github.com/facebookresearch/vq2d_cvpr
Paper: https://arxiv.org/abs/2208.01949v1
VQ2D baseline: https://github.com/EGO4D/episodic-memory/tree/main/VQ2D
@ArtificialIntelligencedl
π7
This media is not supported in your browser
VIEW IN TELEGRAM
Prompt Tuning for Generative Multimodal Pretrained Models
Github: https://github.com/ofa-sys/ofa
Paper: https://arxiv.org/abs/2208.02532v1
Dataset: https://paperswithcode.com/dataset/snli-ve
Demo: https://huggingface.co/spaces/OFA-Sys/OFA-Generic_Interface
@ArtificialIntelligencedl
Github: https://github.com/ofa-sys/ofa
Paper: https://arxiv.org/abs/2208.02532v1
Dataset: https://paperswithcode.com/dataset/snli-ve
Demo: https://huggingface.co/spaces/OFA-Sys/OFA-Generic_Interface
@ArtificialIntelligencedl
π₯7
Constructing Balance from Imbalance for Long-tailed Image Recognition
Github: https://github.com/silicx/dlsa
Paper: https://arxiv.org/abs/2208.02567v1
Dataset: https://paperswithcode.com/dataset/places
@ArtificialIntelligencedl
Github: https://github.com/silicx/dlsa
Paper: https://arxiv.org/abs/2208.02567v1
Dataset: https://paperswithcode.com/dataset/places
@ArtificialIntelligencedl
π7
β Learning Prior Feature and Attention Enhanced Image Inpainting
Github: https://github.com/ewrfcas/MAE-FAR
Paper: https://arxiv.org/abs/2208.01837v1
Dataset: https://paperswithcode.com/dataset/places
@ArtificialIntelligencedl
Github: https://github.com/ewrfcas/MAE-FAR
Paper: https://arxiv.org/abs/2208.01837v1
Dataset: https://paperswithcode.com/dataset/places
@ArtificialIntelligencedl
π10