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
official implemntation for "Contrastive Learning with Stronger Augmentations"

CLSA CLSA is a self-supervised learning methods which focused on the pattern learning from strong augmentations. Copyright (C) 2020 Xiao Wang, Guo-Jun

Lab for MAchine Perception and LEarning (MAPLE) 47 Nov 29, 2022
A python library for implementing a recommender system

python-recsys A python library for implementing a recommender system. Installation Dependencies python-recsys is build on top of Divisi2, with csc-pys

Oscar Celma 1.5k Dec 17, 2022
An integration of several popular automatic augmentation methods, including OHL (Online Hyper-Parameter Learning for Auto-Augmentation Strategy) and AWS (Improving Auto Augment via Augmentation Wise Weight Sharing) by Sensetime Research.

An integration of several popular automatic augmentation methods, including OHL (Online Hyper-Parameter Learning for Auto-Augmentation Strategy) and AWS (Improving Auto Augment via Augmentation Wise

45 Dec 08, 2022
A public available dataset for road boundary detection in aerial images

Topo-boundary This is the official github repo of paper Topo-boundary: A Benchmark Dataset on Topological Road-boundary Detection Using Aerial Images

Zhenhua Xu 79 Jan 04, 2023
Links to works on deep learning algorithms for physics problems, TUM-I15 and beyond

Links to works on deep learning algorithms for physics problems, TUM-I15 and beyond

Nils Thuerey 1.3k Jan 08, 2023
for taichi voxel-challange event

Taichi Voxel Challenge Figure: result of python3 example6.py. Please replace the image above (demo.jpg) with yours, so that other people can immediate

Liming Xu 20 Nov 26, 2022
A Python type explainer!

typesplainer A Python typehint explainer! Available as a cli, as a website, as a vscode extension, as a vim extension Usage First, install the package

Typesplainer 79 Dec 01, 2022
Subgraph Based Learning of Contextual Embedding

SLiCE Self-Supervised Learning of Contextual Embeddings for Link Prediction in Heterogeneous Networks Dataset details: We use four public benchmark da

Pacific Northwest National Laboratory 27 Dec 01, 2022
This program was designed to detect whether someone is wearing a facemask through a live video stream.

This program was designed to detect whether someone is wearing a facemask through a live video stream. A custom lightweight CNN trained with TensorFlow on a public dataset provided by Kaggle is used

0 Apr 02, 2022
Pytorch Lightning Implementation of SC-Depth Methods.

SC_Depth_pl: This is a pytorch lightning implementation of SC-Depth (V1, V2) for self-supervised learning of monocular depth from video. In the V1 (IJ

JiaWang Bian 216 Dec 30, 2022
FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes

FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes This repository contains the source code accompanying the paper: FlexConv: C

Robert-Jan Bruintjes 96 Dec 12, 2022
using STGCN to achieve egg classification task

EEG Classification   The task requires us to classify electroencephalography(EEG) into six categories, including human body, human face, animal body,

4 Jun 13, 2022
EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation (CVPR'21)

EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation (CVPR'21) Citation If y

addisonwang 18 Nov 11, 2022
A distributed deep learning framework that supports flexible parallelization strategies.

FlexFlow FlexFlow is a deep learning framework that accelerates distributed DNN training by automatically searching for efficient parallelization stra

528 Dec 25, 2022
This repository includes the official project for the paper: TransMix: Attend to Mix for Vision Transformers.

TransMix: Attend to Mix for Vision Transformers This repository includes the official project for the paper: TransMix: Attend to Mix for Vision Transf

Jie-Neng Chen 130 Jan 01, 2023
Space-event-trace - Tracing service for spaceteam events

space-event-trace Tracing service for TU Wien Spaceteam events. This service is

TU Wien Space Team 2 Jan 04, 2022
No Code AI/ML platform

NoCodeAIML No Code AI/ML platform - Community Edition Video credits: Uday Kiran Typical No Code AI/ML Platform will have features like drag and drop,

Bhagvan Kommadi 5 Jan 28, 2022
Robust, modular and efficient implementation of advanced Hamiltonian Monte Carlo algorithms

AdvancedHMC.jl AdvancedHMC.jl provides a robust, modular and efficient implementation of advanced HMC algorithms. An illustrative example for Advanced

The Turing Language 167 Jan 01, 2023
Converts geometry node attributes to built-in attributes

Attribute Converter Simplifies converting attributes created by geometry nodes to built-in attributes like UVs or vertex colors, as a single click ope

Ivan Notaros 12 Dec 22, 2022
implement of SwiftNet:Real-time Video Object Segmentation

SwiftNet The official PyTorch implementation of SwiftNet:Real-time Video Object Segmentation, which has been accepted by CVPR2021. Requirements Python

haochen wang 64 Dec 14, 2022