Efficient Spatial-Temporal Information Fusion for LiDAR-Based 3D Moving Object Segmentation
Github: https://github.com/haomo-ai/motionseg3d
Paper: https://arxiv.org/abs/2207.02201v1
Dataset: https://paperswithcode.com/dataset/lidar-mos
@ArtificialIntelligencedl
Github: https://github.com/haomo-ai/motionseg3d
Paper: https://arxiv.org/abs/2207.02201v1
Dataset: https://paperswithcode.com/dataset/lidar-mos
@ArtificialIntelligencedl
π5
β¨ Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification
Tip-Adapter is a training-free adaption method for CLIP to conduct few-shot classification.
Github: https://github.com/gaopengcuhk/tip-adapter
Paper: https://arxiv.org/abs/2207.09519v1
Dataset: https://paperswithcode.com/dataset/oxford-102-flower
Tip-Adapter is a training-free adaption method for CLIP to conduct few-shot classification.
Github: https://github.com/gaopengcuhk/tip-adapter
Paper: https://arxiv.org/abs/2207.09519v1
Dataset: https://paperswithcode.com/dataset/oxford-102-flower
π1π₯1
Using Activation Functions in Neural Networks
https://machinelearningmastery.com/using-activation-functions-in-neural-networks/
@ArtificialIntelligencedl
https://machinelearningmastery.com/using-activation-functions-in-neural-networks/
@ArtificialIntelligencedl
π6
FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling
Github: https://github.com/timothyhtimothy/fast-vqa
Paper: https://arxiv.org/abs/2207.02595v1
Dataset: https://paperswithcode.com/dataset/kinetics
@ArtificialIntelligencedl
Github: https://github.com/timothyhtimothy/fast-vqa
Paper: https://arxiv.org/abs/2207.02595v1
Dataset: https://paperswithcode.com/dataset/kinetics
@ArtificialIntelligencedl
π8
Pre-training helps Bayesian optimization too
Github: https://github.com/google-research/hyperbo
Paper: https://arxiv.org/abs/2207.03084v1
Tensorflow Probability : https://www.tensorflow.org/probability
@ArtificialIntelligencedl
Github: https://github.com/google-research/hyperbo
Paper: https://arxiv.org/abs/2207.03084v1
Tensorflow Probability : https://www.tensorflow.org/probability
@ArtificialIntelligencedl
π9π₯1π₯°1
π Domain Adaptive Video Segmentation via Temporal Pseudo Supervision
Github: https://github.com/xing0047/tps
Paper: https://arxiv.org/abs/2207.02372v1
Dataset : https://paperswithcode.com/dataset/cityscapesprobability
@ArtificialIntelligencedl
Github: https://github.com/xing0047/tps
Paper: https://arxiv.org/abs/2207.02372v1
Dataset : https://paperswithcode.com/dataset/cityscapesprobability
@ArtificialIntelligencedl
π9
SFNet: Faster, Accurate, and Domain Agnostic Semantic Segmentation via Semantic Flow
Github: https://github.com/lxtGH/SFSegNets
Paper: https://arxiv.org/abs/2207.04415v1
Dataset : https://paperswithcode.com/dataset/idd
@ArtificialIntelligencedl
Github: https://github.com/lxtGH/SFSegNets
Paper: https://arxiv.org/abs/2207.04415v1
Dataset : https://paperswithcode.com/dataset/idd
@ArtificialIntelligencedl
π6
βοΈ Fast-Vid2Vid: Spatial-Temporal Compression for Video-to-Video Synthesis
Github: https://github.com/fast-vid2vid/fast-vid2vid
Paper: https://arxiv.org/abs/2207.05049v1
Project: https://fast-vid2vid.github.io/
Tasks : https://paperswithcode.com/task/video-to-video-synthesis
@ArtificialIntelligencedl
Github: https://github.com/fast-vid2vid/fast-vid2vid
Paper: https://arxiv.org/abs/2207.05049v1
Project: https://fast-vid2vid.github.io/
Tasks : https://paperswithcode.com/task/video-to-video-synthesis
@ArtificialIntelligencedl
π8
Masked Autoencoders that Listen
Github: https://github.com/facebookresearch/audiomae
Paper: https://arxiv.org/abs/2207.06405v1
Dataset : https://paperswithcode.com/dataset/audioset
@ArtificialIntelligencedl
Github: https://github.com/facebookresearch/audiomae
Paper: https://arxiv.org/abs/2207.06405v1
Dataset : https://paperswithcode.com/dataset/audioset
@ArtificialIntelligencedl
GitHub
GitHub - facebookresearch/AudioMAE: This repo hosts the code and models of "Masked Autoencoders that Listen".
This repo hosts the code and models of "Masked Autoencoders that Listen". - facebookresearch/AudioMAE
π7
Distance Learner: Incorporating Manifold Prior to Model Training
Github: https://github.com/microsoft/distance-learner
Paper: https://arxiv.org/abs/2207.06888v1
Project: https://fast-vid2vid.github.io/
@ArtificialIntelligencedl
Github: https://github.com/microsoft/distance-learner
Paper: https://arxiv.org/abs/2207.06888v1
Project: https://fast-vid2vid.github.io/
@ArtificialIntelligencedl
π8
ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning
Github: https://github.com/openperceptionx/st-p3
Paper: https://arxiv.org/abs/2207.07601v1
Dataset: https://paperswithcode.com/dataset/carla
@ArtificialIntelligencedl
Github: https://github.com/openperceptionx/st-p3
Paper: https://arxiv.org/abs/2207.07601v1
Dataset: https://paperswithcode.com/dataset/carla
@ArtificialIntelligencedl
π8
Class-incremental Novel Class Discovery
Github: https://github.com/oatmealliu/class-incd
Paper: https://arxiv.org/abs/2207.08605v1
Dataset: https://paperswithcode.com/dataset/tiny-imagenet
@ArtificialIntelligencedl
Github: https://github.com/oatmealliu/class-incd
Paper: https://arxiv.org/abs/2207.08605v1
Dataset: https://paperswithcode.com/dataset/tiny-imagenet
@ArtificialIntelligencedl
β€7
HiFormer: Hierarchical Multi-scale Representations Using Transformers for Medical Image Segmentation
Github: https://github.com/amirhossein-kz/hiformer
Paper: https://arxiv.org/abs/2207.08518v1
Tasks: https://paperswithcode.com/task/medical-image-segmentation
@ArtificialIntelligencedl
Github: https://github.com/amirhossein-kz/hiformer
Paper: https://arxiv.org/abs/2207.08518v1
Tasks: https://paperswithcode.com/task/medical-image-segmentation
@ArtificialIntelligencedl
β€8π2
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