Create accountLogin

Recent searches

No recent searches

Search options

Only available when logged in.
sigmoid.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
A social space for people researching, working with, or just interested in AI!

Administered by:

Server stats:

657
active users

sigmoid.social: AboutProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.7

Farid

✨ Diffusion meets Object Detection

📰 DiffusionDet: Diffusion Model for Object Detection

• It formulates object detection as a denoising diffusion process
from noisy boxes to object boxes

• At training, object boxes diffuse from ground-truth boxes to random distribution

• The model learns to reverse this noising process

• During inference, the model gradually refines a set of randomly generated boxes to refine the results

Paper - DiffusionDet: Diffusion Model for Object Detection
#NewPaper#PaperThread#StableDiffusion
Nov 20, 2022, 02:36 AM·Public·Web
24boosts·40favorites
Public
Farid

• DiffusionDet has better COCO metric scores compared to many classical object detection models

abs: arxiv.org/abs/2211.09788
pdf: arxiv.org/pdf/2211.09788.pdf

source code: github.com/ShoufaChen/Diffusio

arXiv.orgDiffusionDet: Diffusion Model for Object DetectionWe propose DiffusionDet, a new framework that formulates object detection as a denoising diffusion process from noisy boxes to object boxes. During 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. The extensive evaluations on the standard benchmarks, including MS-COCO and LVIS, show that DiffusionDet achieves favorable performance compared to previous well-established detectors. Our work brings two important findings in object detection. First, random boxes, although drastically different from pre-defined anchors or learned queries, are also effective object candidates. Second, object detection, one of the representative perception tasks, can be solved by a generative way. Our code is available at https://github.com/ShoufaChen/DiffusionDet.
Public
Lucas Beyer

@farid Very cool new object detection paradigm!

Though it takes a bit of a hit in terms of FPS, this will probably be improved in a few follow-up papers by the community.

Comes with great flexibility of using the model at evaluation time.

Public
Farid

@lb I agree with you, Lucas.

I look forward to seeing more papers on object detection/segmentation using diffusion.

Public
Oliver Batchelor

@farid This is really great, IMO applying this kind of iterative methods to new types of object detection, for example those described by graphs or curves will be super interesting.

ExploreLive feeds
About