SOLQ: Segmenting Objects by Learning Queries
arXiv:2106.02351
Abstract
In this paper, we propose an end-to-end framework for instance segmentation. Based on the recently introduced DETR [1], our method, termed SOLQ, segments objects by learning unified queries. In SOLQ, each query represents one object and has multiple representations: class, location and mask. The object queries learned perform classification, box regression and mask encoding simultaneously in an unified vector form. During training phase, the mask vectors encoded are supervised by the compression coding of raw spatial masks. In inference time, mask vectors produced can be directly transformed to spatial masks by the inverse process of compression coding. Experimental results show that SOLQ can achieve state-of-the-art performance, surpassing most of existing approaches. Moreover, the joint learning of unified query representation can greatly improve the detection performance of DETR. We hope our SOLQ can serve as a strong baseline for the Transformer-based instance segmentation. Code is available at https://github.com/megvii-research/SOLQ.
arXiv commentAccepted by NeurlPS 2021. Code is available at https://github.com/megvii-research/SOLQ
References in corpus (9)
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Deformable DETR: Deformable Transformers for End-to-End Object Detection
- FCOS: Fully Convolutional One-Stage Object Detection
- Semantic Instance Segmentation with a Discriminative Loss Function
- Pre-Trained Image Processing Transformer
- ISTR: End-to-End Instance Segmentation with Transformers
- TensorMask: A Foundation for Dense Object Segmentation
- DCT-Mask: Discrete Cosine Transform Mask Representation for Instance Segmentation