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
Code for our EMNLP 2021 paper “Heterogeneous Graph Neural Networks for Keyphrase Generation”

GATER This repository contains the code for our EMNLP 2021 paper “Heterogeneous Graph Neural Networks for Keyphrase Generation”. Our implementation is

Jiacheng Ye 12 Nov 24, 2022
Effective Use of Transformer Networks for Entity Tracking

Effective Use of Transformer Networks for Entity Tracking (EMNLP19) This is a PyTorch implementation of our EMNLP paper on the effectiveness of pre-tr

5 Nov 06, 2021
Code of the paper "Shaping Visual Representations with Attributes for Few-Shot Learning (ASL)".

Shaping Visual Representations with Attributes for Few-Shot Learning This code implements the Shaping Visual Representations with Attributes for Few-S

chx_nju 9 Sep 01, 2022
Image Recognition using Pytorch

PyTorch Project Template A simple and well designed structure is essential for any Deep Learning project, so after a lot practice and contributing in

Sarat Chinni 1 Nov 02, 2021
Implementation of Shape Generation and Completion Through Point-Voxel Diffusion

Shape Generation and Completion Through Point-Voxel Diffusion Project | Paper Implementation of Shape Generation and Completion Through Point-Voxel Di

Linqi Zhou 103 Dec 29, 2022
Finetuner allows one to tune the weights of any deep neural network for better embeddings on search tasks

Finetuner allows one to tune the weights of any deep neural network for better embeddings on search tasks

Jina AI 794 Dec 31, 2022
Narya API allows you track soccer player from camera inputs, and evaluate them with an Expected Discounted Goal (EDG) Agent

Narya The Narya API allows you track soccer player from camera inputs, and evaluate them with an Expected Discounted Goal (EDG) Agent. This repository

Paul Garnier 121 Dec 30, 2022
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

Build Type Linux MacOS Windows Build Status OpenPose has represented the first real-time multi-person system to jointly detect human body, hand, facia

25.7k Jan 09, 2023
Learning Dense Representations of Phrases at Scale (Lee et al., 2020)

DensePhrases DensePhrases provides answers to your natural language questions from the entire Wikipedia in real-time. While it efficiently searches th

Princeton Natural Language Processing 540 Dec 30, 2022
Overview of architecture and implementation of TEDS-Net, as described in MICCAI 2021: "TEDS-Net: Enforcing Diffeomorphisms in Spatial Transformers to Guarantee TopologyPreservation in Segmentations"

TEDS-Net Overview of architecture and implementation of TEDS-Net, as described in MICCAI 2021: "TEDS-Net: Enforcing Diffeomorphisms in Spatial Transfo

Madeleine K Wyburd 14 Jan 04, 2023
(CVPR 2022 Oral) Official implementation for "Surface Representation for Point Clouds"

RepSurf - Surface Representation for Point Clouds [CVPR 2022 Oral] By Haoxi Ran* , Jun Liu, Chengjie Wang ( * : corresponding contact) The pytorch off

Haoxi Ran 264 Dec 23, 2022
Official implementation for "QS-Attn: Query-Selected Attention for Contrastive Learning in I2I Translation" (CVPR 2022)

QS-Attn: Query-Selected Attention for Contrastive Learning in I2I Translation (CVPR2022) https://arxiv.org/abs/2203.08483 Unpaired image-to-image (I2I

Xueqi Hu 50 Dec 16, 2022
[IJCAI-2021] A benchmark of data-free knowledge distillation from paper "Contrastive Model Inversion for Data-Free Knowledge Distillation"

DataFree A benchmark of data-free knowledge distillation from paper "Contrastive Model Inversion for Data-Free Knowledge Distillation" Authors: Gongfa

ZJU-VIPA 47 Jan 09, 2023
Code for CVPR 2021 paper TransNAS-Bench-101: Improving Transferrability and Generalizability of Cross-Task Neural Architecture Search.

TransNAS-Bench-101 This repository contains the publishable code for CVPR 2021 paper TransNAS-Bench-101: Improving Transferrability and Generalizabili

Yawen Duan 17 Nov 20, 2022
This repository contains the code used to quantitatively evaluate counterfactual examples in the associated paper.

On Quantitative Evaluations of Counterfactuals Install To install required packages with conda, run the following command: conda env create -f requi

Frederik Hvilshøj 1 Jan 16, 2022
Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.

Machine Learning From Scratch About Python implementations of some of the fundamental Machine Learning models and algorithms from scratch. The purpose

Erik Linder-Norén 21.8k Jan 09, 2023
training script for space time memory network

Trainig Script for Space Time Memory Network This codebase implemented training code for Space Time Memory Network with some cyclic features. Requirem

Yuxi Li 100 Dec 20, 2022
Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm

Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetu

3 Dec 05, 2022
Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction

Welcome to Barlow Barlow is a tool for identifying the failure modes for a given neural network. To achieve this, Barlow first creates a group of imag

Sahil Singla 33 Dec 05, 2022
Official Chainer implementation of GP-GAN: Towards Realistic High-Resolution Image Blending (ACMMM 2019, oral)

GP-GAN: Towards Realistic High-Resolution Image Blending (ACMMM 2019, oral) [Project] [Paper] [Demo] [Related Work: A2RL (for Auto Image Cropping)] [C

Wu Huikai 402 Dec 27, 2022