Implementation of ICCV21 paper: PnP-DETR: Towards Efficient Visual Analysis with Transformers

Related tags

Deep Learningpnp-detr
Overview

Implementation of ICCV 2021 paper: PnP-DETR: Towards Efficient Visual Analysis with Transformers arxiv

This repository is based on detr

Recently, DETR pioneered the solution of vision tasks with transformers, it directly translates the image feature map into the object detection result. Though effective, translating the full feature map can be costly due to redundant computation on some area like the background. In this work, we encapsulate the idea of reducing spatial redundancy into a novel poll and pool (PnP) sampling module, with which we build an end-to-end PnP-DETR architecture that adaptively allocates its computation spatially to be more efficient. Concretely, the PnP module abstracts the image feature map into fine foreground object feature vectors and a small number of coarse background contextual feature vectors. The transformer models information interaction within the fine-coarse feature space and translates the features into the detection result. Moreover, the PnP-augmented model can instantly achieve various desired trade-offs between performance and computation with a single model by varying the sampled feature length, without requiring to train multiple models as existing methods. Thus it offers greater flexibility for deployment in diverse scenarios with varying computation constraint. We further validate the generalizability of the PnP module on panoptic segmentation and the recent transformer-based image recognition model ViT and show consistent efficiency gain. We believe our method makes a step for efficient visual analysis with transformers, wherein spatial redundancy is commonly observed.

PnP-DETR

Usage

First, clone the repository locally:

git clone https://github.com/twangnh/pnp-detr

Then, install PyTorch 1.5+ and torchvision 0.6+:

conda install -c pytorch pytorch torchvision

Install pycocotools (for evaluation on COCO) and scipy (for training):

conda install cython scipy
pip install -U 'git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI'

That's it, should be good to train and evaluate detection models.

(optional) to work with panoptic install panopticapi:

pip install git+https://github.com/cocodataset/panopticapi.git

Data preparation

Download and extract COCO 2017 train and val images with annotations from http://cocodataset.org. We expect the directory structure to be the following:

path/to/coco/
  annotations/  # annotation json files
  train2017/    # train images
  val2017/      # val images

Training

To train baseline DETR on a single node with 8 gpus for 300 epochs run:

python -m torch.distributed.launch --nproc_per_node=8 --use_env main.py --coco_path /path/to/coco 

Following DETR, We train PnP-DETR with AdamW setting learning rate in the transformer to 1e-4 and 1e-5 in the backbone. Horizontal flips, scales an crops are used for augmentation. Images are rescaled to have min size 800 and max size 1333. The transformer is trained with dropout of 0.1, and the whole model is trained with grad clip of 0.1.

Evaluation

To evaluate DETR R50 on COCO val5k with a single GPU run:

python main.py --batch_size 2 --no_aux_loss --eval --resume xxx --coco_path /path/to/coco

Multinode training

Distributed training is available via Slurm and submitit:

pip install submitit

Train baseline DETR-6-6 model on 4 nodes for 300 epochs:

python run_with_submitit.py --timeout 3000 --coco_path /path/to/coco

License

DETR is released under the Apache 2.0 license. Please see the LICENSE file for more information.

Owner
twang
make things work
twang
Applying CLIP to Point Cloud Recognition.

PointCLIP: Point Cloud Understanding by CLIP This repository is an official implementation of the paper 'PointCLIP: Point Cloud Understanding by CLIP'

Renrui Zhang 175 Dec 24, 2022
Toward Realistic Single-View 3D Object Reconstruction with Unsupervised Learning from Multiple Images (ICCV 2021)

Table of Content Introduction Getting Started Datasets Installation Experiments Training & Testing Pretrained models Texture fine-tuning Demo Toward R

VinAI Research 42 Dec 05, 2022
Generalized Data Weighting via Class-level Gradient Manipulation

Generalized Data Weighting via Class-level Gradient Manipulation This repository is the official implementation of Generalized Data Weighting via Clas

18 Nov 12, 2022
Code To Tune or Not To Tune? Zero-shot Models for Legal Case Entailment.

COLIEE 2021 - task 2: Legal Case Entailment This repository contains the code to reproduce NeuralMind's submissions to COLIEE 2021 presented in the pa

NeuralMind 13 Dec 16, 2022
Implementation of ECCV20 paper: the devil is in classification: a simple framework for long-tail object detection and instance segmentation

Implementation of our ECCV 2020 paper The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation This repo contains code o

twang 98 Sep 17, 2022
Light-weight network, depth estimation, knowledge distillation, real-time depth estimation, auxiliary data.

light-weight-depth-estimation Boosting Light-Weight Depth Estimation Via Knowledge Distillation, https://arxiv.org/abs/2105.06143 Junjie Hu, Chenyou F

Junjie Hu 13 Dec 10, 2022
Encode and decode text application

Text Encoder and Decoder Encode and decode text in many ways using this application! Encode in: ASCII85 Base85 Base64 Base32 Base16 Url MD5 Hash SHA-1

Alice 1 Feb 12, 2022
Prototype python implementation of the ome-ngff table spec

Prototype python implementation of the ome-ngff table spec

Kevin Yamauchi 8 Nov 20, 2022
A Python Library for Graph Outlier Detection (Anomaly Detection)

PyGOD is a Python library for graph outlier detection (anomaly detection). This exciting yet challenging field has many key applications, e.g., detect

PyGOD Team 757 Jan 04, 2023
SpiroMask: Measuring Lung Function Using Consumer-Grade Masks

SpiroMask: Measuring Lung Function Using Consumer-Grade Masks Anonymised repository for paper submitted for peer review at ACM HEALTH (October 2021).

0 May 10, 2022
Reference implementation for Deep Unsupervised Learning using Nonequilibrium Thermodynamics

Diffusion Probabilistic Models This repository provides a reference implementation of the method described in the paper: Deep Unsupervised Learning us

Jascha Sohl-Dickstein 238 Jan 02, 2023
Like a cowsay but without cows!

Foxsay This is a simple program that generates pictures of a cute fox with a message. It is like a cowsay but without cows! Fox girls are better! Usag

Anastasia Kim 28 Feb 20, 2022
Open source annotation tool for machine learning practitioners.

doccano doccano is an open source text annotation tool for humans. It provides annotation features for text classification, sequence labeling and sequ

7.1k Jan 01, 2023
Curating a dataset for bioimage transfer learning

CytoImageNet A large-scale pretraining dataset for bioimage transfer learning. Motivation In past few decades, the increase in speed of data collectio

Stanley Z. Hua 9 Jun 20, 2022
City-seeds - A random generator of cultural characteristics intended to spark ideas and help draw threads

City Seeds This is a random generator of cultural characteristics intended to sp

Aydin O'Leary 2 Mar 12, 2022
Tensorflow implementation and notebooks for Implicit Maximum Likelihood Estimation

tf-imle Tensorflow 2 and PyTorch implementation and Jupyter notebooks for Implicit Maximum Likelihood Estimation (I-MLE) proposed in the NeurIPS 2021

NEC Laboratories Europe 69 Dec 13, 2022
Python script that takes an Impulse response .wav and a input .wav to demonstrate audio convolution.

convolver Python script that takes an Impulse response .wav and a input .wav to demonstrate audio convolution. Created by Sean Higley

Sean Higley 1 Feb 23, 2022
Repository for "Space-Time Correspondence as a Contrastive Random Walk" (NeurIPS 2020)

Space-Time Correspondence as a Contrastive Random Walk This is the repository for Space-Time Correspondence as a Contrastive Random Walk, published at

A. Jabri 239 Dec 27, 2022
A hybrid SOTA solution of LiDAR panoptic segmentation with C++ implementations of point cloud clustering algorithms. ICCV21, Workshop on Traditional Computer Vision in the Age of Deep Learning

ICCVW21-TradiCV-Survey-of-LiDAR-Cluster Motivation In contrast to popular end-to-end deep learning LiDAR panoptic segmentation solutions, we propose a

YimingZhao 103 Nov 22, 2022
Code for the paper: Adversarial Training Against Location-Optimized Adversarial Patches. ECCV-W 2020.

Adversarial Training Against Location-Optimized Adversarial Patches arXiv | Paper | Code | Video | Slides Code for the paper: Sukrut Rao, David Stutz,

Sukrut Rao 32 Dec 13, 2022