What Are Expected Queries in End-to-End Object Detection?

by   Shilong Zhang, et al.

End-to-end object detection is rapidly progressed after the emergence of DETR. DETRs use a set of sparse queries that replace the dense candidate boxes in most traditional detectors. In comparison, the sparse queries cannot guarantee a high recall as dense priors. However, making queries dense is not trivial in current frameworks. It not only suffers from heavy computational cost but also difficult optimization. As both sparse and dense queries are imperfect, then what are expected queries in end-to-end object detection? This paper shows that the expected queries should be Dense Distinct Queries (DDQ). Concretely, we introduce dense priors back to the framework to generate dense queries. A duplicate query removal pre-process is applied to these queries so that they are distinguishable from each other. The dense distinct queries are then iteratively processed to obtain final sparse outputs. We show that DDQ is stronger, more robust, and converges faster. It obtains 44.5 AP on the MS COCO detection dataset with only 12 epochs. DDQ is also robust as it outperforms previous methods on both object detection and instance segmentation tasks on various datasets. DDQ blends advantages from traditional dense priors and recent end-to-end detectors. We hope it can serve as a new baseline and inspires researchers to revisit the complementarity between traditional methods and end-to-end detectors. The source code is publicly available at <https://github.com/jshilong/DDQ>.


Dense Distinct Query for End-to-End Object Detection

One-to-one label assignment in object detection has successfully obviate...

Efficient DETR: Improving End-to-End Object Detector with Dense Prior

The recently proposed end-to-end transformer detectors, such as DETR and...

DEYOv2: Rank Feature with Greedy Matching for End-to-End Object Detection

This paper presents a novel object detector called DEYOv2, an improved v...

Progressive End-to-End Object Detection in Crowded Scenes

In this paper, we propose a new query-based detection framework for crow...

CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos

Current dense retrievers are not robust to out-of-domain and outlier que...

QueryPose: Sparse Multi-Person Pose Regression via Spatial-Aware Part-Level Query

We propose a sparse end-to-end multi-person pose regression framework, t...

Benchmark for Generic Product Detection: A strong baseline for Dense Object Detection

Object detection in densely packed scenes is a new area where standard o...

Please sign up or login with your details

Forgot password? Click here to reset