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
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

Self-Supervised Vision Transformers with DINO PyTorch implementation and pretrained models for DINO. For details, see Emerging Properties in Self-Supe

Facebook Research 4.2k Jan 03, 2023
Implementation of the HMAX model of vision in PyTorch

PyTorch implementation of HMAX PyTorch implementation of the HMAX model that closely follows that of the MATLAB implementation of The Laboratory for C

Marijn van Vliet 52 Oct 13, 2022
Code for the paper "Combining Textual Features for the Detection of Hateful and Offensive Language"

The repository provides the source code for the paper "Combining Textual Features for the Detection of Hateful and Offensive Language" submitted to HA

Sherzod Hakimov 3 Aug 04, 2022
Web-interface + rest API for classification and regression (https://jeff1evesque.github.io/machine-learning.docs)

Machine Learning This project provides a web-interface, as well as a programmatic-api for various machine learning algorithms. Supported algorithms: S

Jeff Levesque 252 Dec 11, 2022
PyTorch implementation of the Deep SLDA method from our CVPRW-2020 paper "Lifelong Machine Learning with Deep Streaming Linear Discriminant Analysis"

Lifelong Machine Learning with Deep Streaming Linear Discriminant Analysis This is a PyTorch implementation of the Deep Streaming Linear Discriminant

Tyler Hayes 41 Dec 25, 2022
[ICLR 2022] DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR

DAB-DETR This is the official pytorch implementation of our ICLR 2022 paper DAB-DETR. Authors: Shilong Liu, Feng Li, Hao Zhang, Xiao Yang, Xianbiao Qi

336 Dec 25, 2022
High performance distributed framework for training deep learning recommendation models based on PyTorch.

High performance distributed framework for training deep learning recommendation models based on PyTorch.

340 Dec 30, 2022
Sound and Cost-effective Fuzzing of Stripped Binaries by Incremental and Stochastic Rewriting

StochFuzz: A New Solution for Binary-only Fuzzing StochFuzz is a (probabilistically) sound and cost-effective fuzzing technique for stripped binaries.

Zhuo Zhang 164 Dec 05, 2022
Pytorch reimplementation of the Mixer (MLP-Mixer: An all-MLP Architecture for Vision)

MLP-Mixer Pytorch reimplementation of Google's repository for the MLP-Mixer (Not yet updated on the master branch) that was released with the paper ML

Eunkwang Jeon 18 Dec 08, 2022
Basit bir burç modülü.

Bu modulu burclar hakkinda gundelik bir sekilde bilgi alin diye yaptim ve sizler icin kullanima sunuyorum. Modulun kullanimi asiri basit: Ornek Kullan

Special 17 Jun 08, 2022
A JAX-based research framework for writing differentiable numerical simulators with arbitrary discretizations

jaxdf - JAX-based Discretization Framework Overview | Example | Installation | Documentation ⚠️ This library is still in development. Breaking changes

UCL Biomedical Ultrasound Group 65 Dec 23, 2022
Official repository of "DeepMIH: Deep Invertible Network for Multiple Image Hiding", TPAMI 2022.

DeepMIH: Deep Invertible Network for Multiple Image Hiding (TPAMI 2022) This repo is the official code for DeepMIH: Deep Invertible Network for Multip

Junpeng Jing 67 Nov 22, 2022
Face recognition system using MTCNN, FACENET, SVM and FAST API to track participants of Big Brother Brasil in real time.

BBB Face Recognizer Face recognition system using MTCNN, FACENET, SVM and FAST API to track participants of Big Brother Brasil in real time. Instalati

Rafael Azevedo 232 Dec 24, 2022
Code for the paper "Improved Techniques for Training GANs"

Status: Archive (code is provided as-is, no updates expected) improved-gan code for the paper "Improved Techniques for Training GANs" MNIST, SVHN, CIF

OpenAI 2.2k Jan 01, 2023
Codebase for the paper titled "Continual learning with local module selection"

This repository contains the codebase for the paper Continual Learning via Local Module Composition. Setting up the environemnt Create a new conda env

Oleksiy Ostapenko 20 Dec 10, 2022
Simple PyTorch implementations of Badnets on MNIST and CIFAR10.

Simple PyTorch implementations of Badnets on MNIST and CIFAR10.

Vera 75 Dec 13, 2022
Auto-updating data to assist in investment to NEPSE

Symbol Ratios Summary Sector LTP Undervalued Bonus % MEGA Strong Commercial Banks 368 5 10 JBBL Strong Development Banks 568 5 10 SIFC Strong Finance

Amit Chaudhary 16 Nov 01, 2022
The implementation code for "DAGAN: Deep De-Aliasing Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruction"

DAGAN This is the official implementation code for DAGAN: Deep De-Aliasing Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruct

TensorLayer Community 159 Nov 22, 2022
Code for "Hierarchical Skills for Efficient Exploration" HSD-3 Algorithm and Baselines

Hierarchical Skills for Efficient Exploration This is the source code release for the paper Hierarchical Skills for Efficient Exploration. It contains

Facebook Research 38 Dec 06, 2022
codes for Image Inpainting with External-internal Learning and Monochromic Bottleneck

Image Inpainting with External-internal Learning and Monochromic Bottleneck This repository is for the CVPR 2021 paper: 'Image Inpainting with Externa

97 Nov 29, 2022