关注并星标

从此不迷路

计算机视觉研究院

公众号ID ComputerVisionGzq

计算机视觉研究院专栏

作者：Edison_G

这个是”计算机视觉研究院“新推出的模块，后期我们会陆续为大家带来最新文章及技术的代码实现分享！

• 《Towards Layer-wise Image Vectorization》(CVPR 2022)

GitHub: github.com/ma-xu/LIVE

Installation

We suggest users to use the conda for creating new python environment.

Requirement: 5.010.0.

git clone git@github.com:ma-xu/LIVE.gitcd LIVEconda create -n live python=3.7conda activate liveconda install -y pytorch torchvision -c pytorchconda install -y numpy scikit-imageconda install -y -c anaconda cmakeconda install -y -c conda-forge ffmpegpip install svgwrite svgpathtools cssutils numba torch-tools scikit-fmm easydict visdompip install opencv-python==4.5.4.60 # please install this version to avoid segmentation fault.cd DiffVGgit submodule update --init --recursivepython setup.py installcd ..

Run Experiments

conda activate livecd LIVE# Please modify the paramters accordingly.python main.py --config  --experiment  --signature  --target  --log_dir # Here is an simple example:python main.py --config config/base.yaml --experiment experiment_5x1 --signature smile --target figures/smile.png --log_dir log/

• 《Multimodal Token Fusion for Vision Transformers》(CVPR 2022)

GitHub: github.com/yikaiw/TokenFusion

• 《PointAugmenting: Cross-Modal Augmentation for 3D Object Detection》(CVPR 2022)

GitHub: github.com/VISION-SJTU/PointAugmenting

• 《Fantastic questions and where to find them: FairytaleQA -- An authentic dataset for narrative comprehension.》(ACL 2022)

GitHub: github.com/uci-soe/FairytaleQAData

• 《LUNAR: Unifying Local Outlier Detection Methods via Graph Neural Networks》(AAAI 2022)

GitHub: github.com/agoodge/LUNAR

Firstly, extract data.zip

To replicate the results on the HRSS dataset with neighbour count k = 100 and "Mixed" negative sampling scheme

• Extract saved_models.zip

• Run:

python3 main.py --dataset HRSS --samples MIXED --k 100

To train a new model:

python3 main.py --dataset HRSS --samples MIXED --k 100 --train_new_model

• 《Pseudo-Label Transfer from Frame-Level to Note-Level in a Teacher-Student Framework for Singing Transcription from Polyphonic Music》(ICASSP 2022)

GitHub: github.com/keums/icassp2022-vocal-transcription

• 《Robust Disentangled Variational Speech Representation Learning for Zero-shot Voice Conversion》(ICASSP 2022)

GitHub: github.com/jlian2/Robust-Voice-Style-Transfer

Demo：https://jlian2.github.io/Robust-Voice-Style-Transfer/

• 《HandoverSim: A Simulation Framework and Benchmark for Human-to-Robot Object Handovers》(ICRA 2022)

GitHub: github.com/NVlabs/handover-sim

2022-06-03 16:13:46: Running evaluation for results/2022-02-28_08-57-34_yang-icra2021_s0_test2022-06-03 16:13:47: Evaluation results:| success rate | mean accum time (s) | failure (%) || (%) | exec | plan | total | hand contact | object drop | timeout ||:---------------:|:------:|:------:|:-------:|:---------------:|:---------------:|:--------------:|| 64.58 ( 93/144) | 4.864 | 0.036 | 4.900 | 17.36 ( 25/144) | 11.81 ( 17/144) | 6.25 ( 9/144) |2022-06-03 16:13:47: Printing scene ids2022-06-03 16:13:47: Success (93 scenes):--- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- 0 1 2 3 4 5 6 7 8 9 10 12 13 15 16 17 18 19 21 22 23 25 26 27 28 30 33 34 35 36 37 38 42 43 46 49 50 53 54 56 59 60 62 63 64 66 68 69 70 71 72 77 81 83 85 87 89 91 92 93 94 95 96 98 103 106 107 108 109 110 111 112 113 114 115 116 117 120 121 123125 126 127 128 130 131 132 133 137 138 139 141 143--- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- ---2022-06-03 16:13:47: Failure - hand contact (25 scenes):--- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- 11 14 20 29 39 40 41 44 45 47 51 55 57 58 65 67 74 80 82 88102 105 118 124 136--- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- ---2022-06-03 16:13:47: Failure - object drop (17 scenes):--- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- 24 31 32 52 61 78 79 84 86 97 101 104 119 122 134 140 142--- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- ---2022-06-03 16:13:47: Failure - timeout (9 scenes):--- --- --- --- --- --- --- --- --- 48 73 75 76 90 99 100 129 135--- --- --- --- --- --- --- --- ---2022-06-03 16:13:47: Evaluation complete.

• 《CDLM: Cross-Document Language Modeling》(EMNLP 2021)

GitHub: github.com/aviclu/CDLM

You can either pretrain by yourself or use the pretrained CDLM model weights and tokenizer files, which are available on HuggingFace.

Then, use：

from transformers import AutoTokenizer, AutoModel# load model and tokenizertokenizer = AutoTokenizer.from_pretrained('biu-nlp/cdlm')model = AutoModel.from_pretrained('biu-nlp/cdlm')

• 《Continual Learning for Task-Oriented Dialogue Systems》(EMNLP 2021)

GitHub: github.com/andreamad8/ToDCL

• 《Torsional Diffusion for Molecular Conformer Generation》(2022)

GitHub: github.com/gcorso/torsional-diffusion

• 《MMChat: Multi-Modal Chat Dataset on Social Media》(2022)

GitHub: github.com/silverriver/MMChat

• 《Can CNNs Be More Robust Than Transformers?》(2022)

GitHub: github.com/UCSC-VLAA/RobustCNN

• 《Revealing Single Frame Bias for Video-and-Language Learning》(2022)

GitHub: github.com/jayleicn/singularity

• 《Progressive Distillation for Fast Sampling of Diffusion Models》(2022)

GitHub: github.com/Hramchenko/diffusion_distiller

• 《Neural Basis Models for Interpretability》(2022)

GitHub: github.com/facebookresearch/nbm-spam

• 《Scalable Interpretability via Polynomials》(2022)

GitHub: github.com/facebookresearch/nbm-spam

• 《Infinite Recommendation Networks: A Data-Centric Approach》(2022)

GitHub: github.com/noveens/infinite_ae_cf

• 《The GatedTabTransformer. An enhanced deep learning architecture for tabular modeling》(2022)

GitHub: github.com/radi-cho/GatedTabTransformer

Usage：

import torchimport torch.nn as nnfrom gated_tab_transformer import GatedTabTransformer
model = GatedTabTransformer( categories = (10, 5, 6, 5, 8), # tuple containing the number of unique values within each category num_continuous = 10, # number of continuous values transformer_dim = 32, # dimension, paper set at 32 dim_out = 1, # binary prediction, but could be anything transformer_depth = 6, # depth, paper recommended 6 transformer_heads = 8, # heads, paper recommends 8 attn_dropout = 0.1, # post-attention dropout ff_dropout = 0.1, # feed forward dropout mlp_act = nn.LeakyReLU(0), # activation for final mlp, defaults to relu, but could be anything else (selu, etc.) mlp_depth=4, # mlp hidden layers depth mlp_dimension=32, # dimension of mlp layers gmlp_enabled=True # gmlp or standard mlp)
x_categ = torch.randint(0, 5, (1, 5)) # category values, from 0 - max number of categories, in the order as passed into the constructor abovex_cont = torch.randn(1, 10) # assume continuous values are already normalized inpidually
pred = model(x_categ, x_cont)print(pred)

• 《Distract Your Attention: Multi-head Cross Attention Network for Facial Expression Recognition》(2022)

GitHub: github.com/yaoing/DAN

• 《Towards Principled Disentanglement for Domain Generalization》(2021)

GitHub: github.com/hlzhang109/DDG

• 《SoundStream: An End-to-End Neural Audio Codec》(2021)

GitHub: github.com/wesbz/SoundStream

THE END

转载请联系本公众号获得授权

计算机视觉研究院学习群等你加入！

计算机视觉研究院主要涉及深度学习领域，主要致力于人脸检测、人脸识别，多目标检测、目标跟踪、图像分割等研究方向。研究院接下来会不断分享最新的论文算法新框架，我们这次改革不同点就是，我们要着重”研究“。之后我们会针对相应领域分享实践过程，让大家真正体会摆脱理论的真实场景，培养爱动手编程爱动脑思考的习惯！

计算机视觉研究院

公众号ID ComputerVisionGzq