Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/bytedance/dq-det

Codes for ICML 2023 Learning Dynamic Query Combinations for Transformer-based Object Detection and Segmentation

https://github.com/bytedance/dq-det

Science Score: 26.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (8.5%) to scientific vocabulary

Keywords

research
Last synced: 7 months ago · JSON representation

Repository

Codes for ICML 2023 Learning Dynamic Query Combinations for Transformer-based Object Detection and Segmentation

Basic Info
  • Host: GitHub
  • Owner: bytedance
  • License: apache-2.0
  • Language: Python
  • Default Branch: master
  • Homepage:
  • Size: 13.7 MB
Statistics
  • Stars: 37
  • Watchers: 3
  • Forks: 3
  • Open Issues: 3
  • Releases: 0
Topics
research
Created over 2 years ago · Last pushed over 2 years ago
Metadata Files
Readme License

README.md

Learning Dynamic Query Combinations for Transformer-based Object Detection and Segmentation

This repository is an official implementation of the paper Learning Dynamic Query Combinations for Transformer-based Object Detection and Segmentation .

Introduction

<!--{width="800" style="display: block; margin: 0 auto" }-->

Abstract. Transformer-based detection and segmentation methods use a list of learned detection queries to retrieve information from the transformer network and learn to predict the location and category of one specific object from each query. We empirically find that random convex combinations of the learned queries are still good for the corresponding models. We then propose to learn a convex combination with dynamic coefficients based on the high-level semantics of the image. The generated dynamic queries, named modulated queries, better capture the prior of object locations and categories in the different images. Equipped with our modulated queries, a wide range of DETR-based models achieve consistent and superior performance across multiple tasks including object detection, instance segmentation, panoptic segmentation, and video instance segmentation.

License

This project is released under the Apache 2.0 license.

Usage

Please follow the instructions in each individual folder.

Owner

  • Name: Bytedance Inc.
  • Login: bytedance
  • Kind: organization
  • Location: Singapore

GitHub Events

Total
  • Issues event: 1
  • Watch event: 2
Last Year
  • Issues event: 1
  • Watch event: 2

Issues and Pull Requests

Last synced: 12 months ago

All Time
  • Total issues: 3
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 3
  • Total pull request authors: 0
  • Average comments per issue: 0.0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 1
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 1
  • Pull request authors: 0
  • Average comments per issue: 0.0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • cp3wan (1)
  • lizhiwen19900709 (1)
  • PolarishT (1)
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels

Dependencies

SMCA-DETR/Dockerfile docker
  • pytorch/pytorch 1.5-cuda10.1-cudnn7-runtime build
SMCA-DETR-DQ/Dockerfile docker
  • pytorch/pytorch 1.5-cuda10.1-cudnn7-runtime build
Cond-DETR/requirements.txt pypi
  • cython *
  • panopticapi *
  • scipy *
  • termcolor *
  • torch >=1.7.0
  • torchvision >=0.6.0
Cond-DETR-DQ/requirements.txt pypi
  • cython *
  • panopticapi *
  • scipy *
  • termcolor *
  • torch >=1.7.0
  • torchvision >=0.6.0
DAB-DETR/requirements.txt pypi
  • addict *
  • cython *
  • panopticapi *
  • scipy *
  • submitit *
  • termcolor *
  • timm *
  • torch >=1.5.0
  • torchvision >=0.6.0
  • yapf *
DAB-DETR-DQ/requirements.txt pypi
  • addict *
  • cython *
  • panopticapi *
  • scipy *
  • submitit *
  • termcolor *
  • timm *
  • torch >=1.5.0
  • torchvision >=0.6.0
  • yapf *
Deform-DETR/requirements.txt pypi
  • cython *
  • pycocotools *
  • scipy *
  • tqdm *
Deform-DETR-DQ/requirements.txt pypi
  • cython *
  • pycocotools *
  • scipy *
  • tqdm *
SMCA-DETR/Adaptive_Cluster_Transformer/setup.py pypi
  • torch *
SMCA-DETR/requirements.txt pypi
  • cython *
  • onnx *
  • onnxruntime *
  • panopticapi *
  • scipy *
  • submitit *
  • torch >=1.5.0
  • torchvision >=0.6.0
SMCA-DETR-DQ/Adaptive_Cluster_Transformer/setup.py pypi
  • torch *
SMCA-DETR-DQ/requirements.txt pypi
  • cython *
  • onnx *
  • onnxruntime *
  • panopticapi *
  • scipy *
  • submitit *
  • torch >=1.5.0
  • torchvision >=0.6.0
DAB-DETR/models/dab_deformable_detr/ops/setup.py pypi
DAB-DETR-DQ/models/dab_deformable_detr/ops/setup.py pypi
Deform-DETR/models/ops/setup.py pypi
Deform-DETR-DQ/models/ops/setup.py pypi
Mask2Former-DQ/mask2former/modeling/pixel_decoder/ops/setup.py pypi
Mask2Former-DQ/requirements.txt pypi
  • cython *
  • h5py *
  • numpy *
  • pillow *
  • scikit-image *
  • scipy *
  • shapely *
  • submitit *
  • timm *