Dynamic Sparse R-CNN

by   Qinghang Hong, et al.

Sparse R-CNN is a recent strong object detection baseline by set prediction on sparse, learnable proposal boxes and proposal features. In this work, we propose to improve Sparse R-CNN with two dynamic designs. First, Sparse R-CNN adopts a one-to-one label assignment scheme, where the Hungarian algorithm is applied to match only one positive sample for each ground truth. Such one-to-one assignment may not be optimal for the matching between the learned proposal boxes and ground truths. To address this problem, we propose dynamic label assignment (DLA) based on the optimal transport algorithm to assign increasing positive samples in the iterative training stages of Sparse R-CNN. We constrain the matching to be gradually looser in the sequential stages as the later stage produces the refined proposals with improved precision. Second, the learned proposal boxes and features remain fixed for different images in the inference process of Sparse R-CNN. Motivated by dynamic convolution, we propose dynamic proposal generation (DPG) to assemble multiple proposal experts dynamically for providing better initial proposal boxes and features for the consecutive training stages. DPG thereby can derive sample-dependent proposal boxes and features for inference. Experiments demonstrate that our method, named Dynamic Sparse R-CNN, can boost the strong Sparse R-CNN baseline with different backbones for object detection. Particularly, Dynamic Sparse R-CNN reaches the state-of-the-art 47.2 surpassing Sparse R-CNN by 2.2


G-CNN: an Iterative Grid Based Object Detector

We introduce G-CNN, an object detection technique based on CNNs which wo...

SRCN3D: Sparse R-CNN 3D Surround-View Camera Object Detection and Tracking for Autonomous Driving

Detection And Tracking of Moving Objects (DATMO) is an essential compone...

IoU-Enhanced Attention for End-to-End Task Specific Object Detection

Without densely tiled anchor boxes or grid points in the image, sparse R...

Sparse R-CNN: End-to-End Object Detection with Learnable Proposals

We present Sparse R-CNN, a purely sparse method for object detection in ...

Unbalanced Optimal Transport: A Unified Framework for Object Detection

During training, supervised object detection tries to correctly match th...

Which to Match? Selecting Consistent GT-Proposal Assignment for Pedestrian Detection

Accurate pedestrian classification and localization have received consid...

Dense Hybrid Proposal Modulation for Lane Detection

In this paper, we present a dense hybrid proposal modulation (DHPM) meth...

Please sign up or login with your details

Forgot password? Click here to reset