DiffusionDet: Diffusion Model for Object Detection
Preprint
Abstract
We propose DiffusionDet, a new framework that formulates object detection as a denoising diffusion process from noisy boxes to object boxes. During the training stage, object boxes diffuse from ground-truth boxes to random distribution, and the model learns to reverse this noising process. In inference, the model refines a set of randomly generated boxes to the output results in a progressive way. Our work possesses an appealing property of flexibility, which enables the dynamic number of boxes and iterative evaluation. The extensive experiments on the standard benchmarks show that DiffusionDet achieves favorable performance compared to previous well-established detectors. For example, DiffusionDet achieves 5.3 AP and 4.8 AP gains when evaluated with more boxes and iteration steps, under a zero-shot transfer setting from COCO to CrowdHuman. Our code is available at https://github.com/ShoufaChen/DiffusionDet.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- MotionDiffuse: Text-Driven Human Motion Generation With Diffusion ModelIEEE Transactions on Pattern Analysis and Machine Intelligence, 2024
- A Generalist Framework for Panoptic Segmentation of Images and Videos2023
- Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment2023
- Frido: Feature Pyramid Diffusion for Complex Scene Image SynthesisProceedings of the AAAI Conference on Artificial Intelligence, 2023
- DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation2023
- DETRs with Hybrid Matching2023
- Diffsound: Discrete Diffusion Model for Text-to-Sound GenerationIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2023
- In Defense of Online Models for Video Instance Segmentation2022
- Cascade R-CNN: High Quality Object Detection and Instance SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2019
- Tracking-Learning-DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011