Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation
This provides a unified framework for computer vision tasks, benefiting researchers and practitioners by simplifying multi-task learning, though it is incremental as it builds on existing DINO methods.
Mask DINO tackles the problem of unifying object detection and segmentation by extending DINO with a mask prediction branch, achieving state-of-the-art results including 54.5 AP on COCO instance segmentation, 59.4 PQ on COCO panoptic segmentation, and 60.8 mIoU on ADE20K semantic segmentation.
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}.