LAVT: Language-Aware Vision Transformer for Referring Image Segmentation

Overview

LAVT: Language-Aware Vision Transformer for Referring Image Segmentation

Where we are ?

12.27 目前和原论文仍有1%左右得差距,但已经力压很多SOTA了

ckpt__448_epoch_25.pth mIoU Overall IoU [email protected]
Refcoco val 70.743 71.671 82.26
Refcoco testA 73.679 74.772 -
Refcoco testB 67.582 67.339 -

12.29 45epoch的结果又上升了大约1%

ckpt__448_epoch_45.pth mIoU Overall IoU
Refcoco val 71.949 72.246
Refcoco testA 74.533 75.467
Refcoco testB 67.849 68.123

the pretrain model will be released soon

对原论文的复现

论文链接: https://arxiv.org/abs/2112.02244

官方实现: https://github.com/yz93/LAVT-RIS

Architecture

Features

  • 将不同模态feature的fusion提前到Image Encoder阶段

  • 思路上对这两篇论文有很多借鉴

    • Vision-Language Transformer and Query Generation for Referring Segmentation

    • Locate then Segment: A Strong Pipeline for Referring Image Segmentation

  • 采用了比较新的主干网络 Swin-Transformer

Usage

详细参数设置可以见args.py

for training

CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nproc_per_node 4 --master_port 12345 main.py --batch_size 2 --cfg_file configs/swin_base_patch4_window7_224.yaml --size 448

for evaluation

CUDA_VISIBLE_DEVICES=4,5,6,7 python -m torch.distributed.launch --nproc_per_node 4 --master_port 23458 main.py --size 448 --batch_size 1 --resume --eval --type val --eval_mode cat --pretrain ckpt_448_epoch_20.pth --cfg_file configs/swin_base_patch4_window7_224.yaml

*.pth 都放在./checkpoint

for resume from checkpoint

CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nproc_per_node 4 --master_port 12346 main.py --batch_size 2 --cfg_file configs/swin_base_patch4_window7_224.yaml --size 448 --resume --pretrain ckpt_448_epoch_10.pth

for dataset preparation

please get details from ./data/readme.md

Need to be finished

由于我在复现的时候,官方的code还没有出来,所以一些细节上的设置可能和官方code不同

  • Swin Transformer 我选择的是 swin_base_patch4_window12_384_22k.pth,具体代码可以参考官方代码 https://github.com/microsoft/Swin-Transformer/blob/main/get_started.md 原论文中的图像resize的尺寸是480*480,可是我目前基于官方的代码若想调到这个尺寸,总是会报错,查了一下觉得可能用object detection 的swin transformer的code比较好

    12.27 这个问题目前也已经得到了较好的解决,目前训练用的是 swin_base_patch4_window7_224_22k.pth, 输入图片的尺寸调整到448*448

    解决方案可以参考:

    https://github.com/microsoft/Swin-Transformer/issues/155

  • 原论文中使用的lr_scheduler是polynomial learning rate decay, 没有给出具体的参数手动设置了一下

    12.21 目前来看感觉自己设置的不是很好

    12.27 调整了一下设置,初始学习率的设置真的很重要,特别是根据batch_size 去scale你的 inital learning rate

  • 原论文中的batch_size=32,基于自己的实验我猜想应该是用了8块GPU,每一块的batch_size=4, 由于我第一次写DDP code,训练时发现,程序总是会在RANK0上给其余RANK开辟类似共享显存的东西,导致我无法做到原论文相同的配置,需要改进

  • 仔细观察Refcoco的数据集,会发现一个target会对应好几个sentence,training时我设计的是随机选一个句子,evaluate时感觉应该要把所有句子用上会更好,关于这一点我想了两种evaluate的方法

    目前eval 只能支持 batch_size=1

    • 将所有句子concatenate成为一个句子,送入BERT,Input 形式上就是(Image,cat(sent_1,sent_2,sent_3)) => model => pred

    实验发现这种eval_mode 下的mean IOU 会好不少, overall_IOU 也会好一点

    • 对同一张图片处理多次处理,然后将结果进行平均,Input 形式上就是 ((Image,sent_1),(Image,sent_2),(Image,sent_3)) => model => average(pred_1,pred_2,pred_3)

Visualization

详细见inference.ipynb

input sentences

  1. right girl
  2. closest girl on right

results

Failure cases study

AnalysisFailure.ipynb 提供了一个研究model不work的途径,主要是筛选了IoU < 0.5的case,并在这些case中着重查看了一下IoU < 0.10.4 < IoU < 0.5 的例子

目前我只看了一些有限的failure cases,做了如下总结

  • 模型对于similar,dense object在language guide下定位不精确
  • 模型对于language的理解不分主次
  • refcoco本身标记的一些问题
Owner
zichengsaber
CVer
zichengsaber
A PyTorch Implementation of PGL-SUM from "Combining Global and Local Attention with Positional Encoding for Video Summarization", Proc. IEEE ISM 2021

PGL-SUM: Combining Global and Local Attention with Positional Encoding for Video Summarization PyTorch Implementation of PGL-SUM From "PGL-SUM: Combin

Evlampios Apostolidis 35 Dec 22, 2022
Populating 3D Scenes by Learning Human-Scene Interaction https://posa.is.tue.mpg.de/

Populating 3D Scenes by Learning Human-Scene Interaction [Project Page] [Paper] License Software Copyright License for non-commercial scientific resea

Mohamed Hassan 81 Nov 08, 2022
The source code and dataset for the RecGURU paper (WSDM 2022)

RecGURU About The Project Source code and baselines for the RecGURU paper "RecGURU: Adversarial Learning of Generalized User Representations for Cross

Chenglin Li 17 Jan 07, 2023
YOLOv7 - Framework Beyond Detection

🔥🔥🔥🔥 YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥

JinTian 3k Jan 01, 2023
Avalanche RL: an End-to-End Library for Continual Reinforcement Learning

Avalanche RL: an End-to-End Library for Continual Reinforcement Learning Avalanche Website | Getting Started | Examples | Tutorial | API Doc | Paper |

ContinualAI 43 Dec 24, 2022
Implementation of " SESS: Self-Ensembling Semi-Supervised 3D Object Detection" (CVPR2020 Oral)

SESS: Self-Ensembling Semi-Supervised 3D Object Detection Created by Na Zhao from National University of Singapore Introduction This repository contai

125 Dec 23, 2022
Code for "Reconstructing 3D Human Pose by Watching Humans in the Mirror", CVPR 2021 oral

Reconstructing 3D Human Pose by Watching Humans in the Mirror Qi Fang*, Qing Shuai*, Junting Dong, Hujun Bao, Xiaowei Zhou CVPR 2021 Oral The videos a

ZJU3DV 178 Dec 13, 2022
Use AI to generate a optimized stock portfolio

Use AI, Modern Portfolio Theory, and Monte Carlo simulation's to generate a optimized stock portfolio that minimizes risk while maximizing returns. Ho

Greg James 30 Dec 22, 2022
U-Net Implementation: Convolutional Networks for Biomedical Image Segmentation" using the Carvana Image Masking Dataset in PyTorch

U-Net Implementation By Christopher Ley This is my interpretation and implementation of the famous paper "U-Net: Convolutional Networks for Biomedical

Christopher Ley 1 Jan 06, 2022
Implementation of our paper "Video Playback Rate Perception for Self-supervised Spatio-Temporal Representation Learning".

PRP Introduction This is the implementation of our paper "Video Playback Rate Perception for Self-supervised Spatio-Temporal Representation Learning".

yuanyao366 39 Dec 29, 2022
use tensorflow 2.0 to tell a dog and cat from a specified picture

dog_or_cat use tensorflow 2.0 to tell a dog and cat from a specified picture This is one of the classic experiments for the introduction of deep learn

你这个代码我看不懂 1 Oct 22, 2021
Решения, подсказки, тесты и утилиты для тренировки по алгоритмам от Яндекса.

Решения и подсказки к тренировке по алгоритмам от Яндекса Что есть внутри Решения с подсказками и комментариями; рекомендую сначала смотреть md файл п

Yankovsky Andrey 50 Dec 26, 2022
Autonomous Movement from Simultaneous Localization and Mapping

Autonomous Movement from Simultaneous Localization and Mapping About us Built by a group of Clarkson University students with the help from Professor

14 Nov 07, 2022
Robot Hacking Manual (RHM). From robotics to cybersecurity. Papers, notes and writeups from a journey into robot cybersecurity.

RHM: Robot Hacking Manual Download in PDF RHM v0.4 ┃ Read online The Robot Hacking Manual (RHM) is an introductory series about cybersecurity for robo

Víctor Mayoral Vilches 233 Dec 30, 2022
Official implementation of ACTION-Net: Multipath Excitation for Action Recognition (CVPR'21).

ACTION-Net Official implementation of ACTION-Net: Multipath Excitation for Action Recognition (CVPR'21). Getting Started EgoGesture data folder struct

V-Sense 171 Dec 26, 2022
Code for "Intra-hour Photovoltaic Generation Forecasting based on Multi-source Data and Deep Learning Methods."

pv_predict_unet-lstm Code for "Intra-hour Photovoltaic Generation Forecasting based on Multi-source Data and Deep Learning Methods." IEEE Transactions

FolkScientistInDL 8 Oct 08, 2022
PyArmadillo: an alternative approach to linear algebra in Python

PyArmadillo is a linear algebra library for the Python language, with an emphasis on ease of use.

Terry Zhuo 58 Oct 11, 2022
Space Invaders For Python

Space-Invaders Just download or clone the git repository. To run the Space Invader game you need to have pyhton installed in you system. If you dont h

Fei 5 Jul 27, 2022
Fit Fast, Explain Fast

FastExplain Fit Fast, Explain Fast Installing pip install fast-explain About FastExplain FastExplain provides an out-of-the-box tool for analysts to

8 Dec 15, 2022
DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

DeeBERT This is the code base for the paper DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference. Code in this repository is also available

Castorini 132 Nov 14, 2022