DeepAI AI Chat
Log In Sign Up

FQDet: Fast-converging Query-based Detector

10/05/2022
by   Cédric Picron, et al.
0

Recently, two-stage Deformable DETR introduced the query-based two-stage head, a new type of two-stage head different from the region-based two-stage heads of classical detectors as Faster R-CNN. In query-based two-stage heads, the second stage selects one feature per detection, called the query, as opposed to pooling a rectangular grid of features as in region-based detectors. In this work, we further improve the query-based head from Deformable DETR, significantly speeding up the convergence while increasing its performance. This is achieved by incorporating classical techniques such as anchor generation within the query-based paradigm. By combining the best of both the classical and the query-based worlds, our FQDet head peaks at 45.4 AP on the 2017 COCO validation set when using a ResNet-50+TPN backbone, only after training for 12 epochs using the 1x schedule. We outperform other high-performing two-stage heads such as e.g. Cascade R-CNN, while using the same backbone and while often being computationally cheaper. Additionally, when using the large ResNeXt-101-DCN+TPN backbone and multi-scale testing, our FQDet head achieves 52.9 AP on the 2017 COCO test-dev set after only 12 epochs of training. Code will be released.

READ FULL TEXT
11/20/2017

Light-Head R-CNN: In Defense of Two-Stage Object Detector

In this paper, we first investigate why typical two-stage methods are no...
04/11/2023

StageInteractor: Query-based Object Detector with Cross-stage Interaction

Previous object detectors make predictions based on dense grid points or...
12/15/2022

Enhanced Training of Query-Based Object Detection via Selective Query Recollection

This paper investigates a phenomenon where query-based object detectors ...
03/30/2022

AdaMixer: A Fast-Converging Query-Based Object Detector

Traditional object detectors employ the dense paradigm of scanning over ...
01/28/2021

Augmenting Proposals by the Detector Itself

Lacking enough high quality proposals for RoI box head has impeded two-s...
01/04/2020

Pixel-Semantic Revise of Position Learning A One-Stage Object Detector with A Shared Encoder-Decoder

We analyze that different methods based channel or position attention me...
07/16/2022

You Should Look at All Objects

Feature pyramid network (FPN) is one of the key components for object de...