TL;DR
QueryInst introduces a novel query-based instance segmentation method that leverages intrinsic one-to-one correspondence in object queries, achieving state-of-the-art results with improved speed on multiple benchmarks.
Contribution
The paper proposes QueryInst, a new query-based instance segmentation framework that simplifies multi-stage mask head connections and enhances performance and efficiency.
Findings
Outperforms HTC on COCO with 48.1 box AP and 42.8 mask AP
Achieves best online VIS performance with good speed-accuracy trade-off
Runs 2.4 times faster than comparable methods
Abstract
Recently, query based object detection frameworks achieve comparable performance with previous state-of-the-art object detectors. However, how to fully leverage such frameworks to perform instance segmentation remains an open problem. In this paper, we present QueryInst (Instances as Queries), a query based instance segmentation method driven by parallel supervision on dynamic mask heads. The key insight of QueryInst is to leverage the intrinsic one-to-one correspondence in object queries across different stages, as well as one-to-one correspondence between mask RoI features and object queries in the same stage. This approach eliminates the explicit multi-stage mask head connection and the proposal distribution inconsistency issues inherent in non-query based multi-stage instance segmentation methods. We conduct extensive experiments on three challenging benchmarks, i.e., COCO,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsLinear Layer · Absolute Position Encodings · Position-Wise Feed-Forward Layer · Dense Connections · Vision Transformer · Sparse R-CNN · Region Proposal Network · Faster R-CNN · Cascade R-CNN · Cascade Mask R-CNN
