Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation

TL;DR

Mask DINO is a unified transformer-based framework that advances object detection and segmentation by integrating mask prediction into DINO, achieving state-of-the-art results across multiple segmentation tasks with high efficiency and scalability.

Contribution

It introduces Mask DINO, a novel extension of DINO that supports all image segmentation tasks within a unified architecture, improving performance and scalability.

Findings

Outperforms existing segmentation methods on COCO and ADE20K datasets.

Achieves 54.5 AP on COCO instance segmentation.

Establishes new best results for panoptic and semantic segmentation.

Abstract

In this paper we present Mask DINO, a unified object detection and segmentation framework. Mask DINO extends DINO (DETR with Improved Denoising Anchor Boxes) by adding a mask prediction branch which supports all image segmentation tasks (instance, panoptic, and semantic). It makes use of the query embeddings from DINO to dot-product a high-resolution pixel embedding map to predict a set of binary masks. Some key components in DINO are extended for segmentation through a shared architecture and training process. Mask DINO is simple, efficient, and scalable, and it can benefit from joint large-scale detection and segmentation datasets. Our experiments show that Mask DINO significantly outperforms all existing specialized segmentation methods, both on a ResNet-50 backbone and a pre-trained model with SwinL backbone. Notably, Mask DINO establishes the best results to date on instance segmentation (54.5 AP on COCO), panoptic segmentation (59.4 PQ on COCO), and semantic segmentation (60.8 mIoU on ADE20K) among models under one billion parameters. Code is available at \url{https://github.com/IDEACVR/MaskDINO}.