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
Random-Afg - Afghanistan Random Old Idz Cloner Tools

AFGHANISTAN RANDOM OLD IDZ CLONER TOOLS Install $ apt update $ apt upgrade $ apt

MAHADI HASAN AFRIDI 5 Jan 26, 2022
Code for paper ECCV 2020 paper: Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop.

Who Left the Dogs Out? Evaluation and demo code for our ECCV 2020 paper: Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization

Benjamin Biggs 29 Dec 28, 2022
PyJokes - Joking around with Python library pyjokes

Hi, it's Muhaimin again 👋 This is something unorthodox but cool. Don't forget t

Muhaimin A. Salay Kanton 1 Feb 02, 2022
A python code to convert Keras pre-trained weights to Pytorch version

Weights_Keras_2_Pytorch 最近想在Pytorch项目里使用一下谷歌的NIMA,但是发现没有预训练好的pytorch权重,于是整理了一下将Keras预训练权重转为Pytorch的代码,目前是支持Keras的Conv2D, Dense, DepthwiseConv2D, Batch

Liu Hengyu 2 Dec 16, 2021
ESL: Event-based Structured Light

ESL: Event-based Structured Light Video (click on the image) This is the code for the 2021 3DV paper ESL: Event-based Structured Light by Manasi Mugli

Robotics and Perception Group 29 Oct 24, 2022
NeoDTI: Neural integration of neighbor information from a heterogeneous network for discovering new drug-target interactions

NeoDTI NeoDTI: Neural integration of neighbor information from a heterogeneous network for discovering new drug-target interactions (Bioinformatics).

62 Nov 26, 2022
Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"

Easy-To-Hard The official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks". Gett

Avi Schwarzschild 52 Sep 08, 2022
Differentiable Annealed Importance Sampling (DAIS)

Differentiable Annealed Importance Sampling (DAIS) This repository contains the code to reproduce the DAIS results from the paper Differentiable Annea

Guodong Zhang 6 Dec 26, 2021
All public open-source implementations of convnets benchmarks

convnet-benchmarks Easy benchmarking of all public open-source implementations of convnets. A summary is provided in the section below. Machine: 6-cor

Soumith Chintala 2.7k Dec 30, 2022
This is the official pytorch implementation for our ICCV 2021 paper "TRAR: Routing the Attention Spans in Transformers for Visual Question Answering" on VQA Task

🌈 ERASOR (RA-L'21 with ICRA Option) Official page of "ERASOR: Egocentric Ratio of Pseudo Occupancy-based Dynamic Object Removal for Static 3D Point C

Hyungtae Lim 225 Dec 29, 2022
Self-labelling via simultaneous clustering and representation learning. (ICLR 2020)

Self-labelling via simultaneous clustering and representation learning 🆗 🆗 🎉 NEW models (20th August 2020): Added standard SeLa pretrained torchvis

Yuki M. Asano 469 Jan 02, 2023
Text-to-Music Retrieval using Pre-defined/Data-driven Emotion Embeddings

Text2Music Emotion Embedding Text-to-Music Retrieval using Pre-defined/Data-driven Emotion Embeddings Reference Emotion Embedding Spaces for Matching

Minz Won 50 Dec 05, 2022
Official code repository for the work: "The Implicit Values of A Good Hand Shake: Handheld Multi-Frame Neural Depth Refinement"

Handheld Multi-Frame Neural Depth Refinement This is the official code repository for the work: The Implicit Values of A Good Hand Shake: Handheld Mul

55 Dec 14, 2022
Kaggle Ultrasound Nerve Segmentation competition [Keras]

Ultrasound nerve segmentation using Keras (1.0.7) Kaggle Ultrasound Nerve Segmentation competition [Keras] #Install (Ubuntu {14,16}, GPU) cuDNN requir

179 Dec 28, 2022
The NEOSSat is a dual-mission microsatellite designed to detect potentially hazardous Earth-orbit-crossing asteroids and track objects that reside in deep space

The NEOSSat is a dual-mission microsatellite designed to detect potentially hazardous Earth-orbit-crossing asteroids and track objects that reside in deep space

John Salib 2 Jan 30, 2022
PyTorch implementation of 'Gen-LaneNet: a generalized and scalable approach for 3D lane detection'

(pytorch) Gen-LaneNet: a generalized and scalable approach for 3D lane detection Introduction This is a pytorch implementation of Gen-LaneNet, which p

Yuliang Guo 233 Jan 06, 2023
Scalable machine learning based time series forecasting

mlforecast Scalable machine learning based time series forecasting. Install PyPI pip install mlforecast Optional dependencies If you want more functio

Nixtla 145 Dec 24, 2022
Code for Massive-scale Decoding for Text Generation using Lattices

Massive-scale Decoding for Text Generation using Lattices Jiacheng Xu, Greg Durrett TL;DR: a new search algorithm to construct lattices encoding many

Jiacheng Xu 37 Dec 18, 2022
Official PyTorch implementation of the paper "Deep Constrained Least Squares for Blind Image Super-Resolution", CVPR 2022.

Deep Constrained Least Squares for Blind Image Super-Resolution [Paper] This is the official implementation of 'Deep Constrained Least Squares for Bli

MEGVII Research 141 Dec 30, 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