DeepAI AI Chat
Log In Sign Up

RCNet: Reverse Feature Pyramid and Cross-scale Shift Network for Object Detection

by   Zhuofan Zong, et al.
Beihang University

Feature pyramid networks (FPN) are widely exploited for multi-scale feature fusion in existing advanced object detection frameworks. Numerous previous works have developed various structures for bidirectional feature fusion, all of which are shown to improve the detection performance effectively. We observe that these complicated network structures require feature pyramids to be stacked in a fixed order, which introduces longer pipelines and reduces the inference speed. Moreover, semantics from non-adjacent levels are diluted in the feature pyramid since only features at adjacent pyramid levels are merged by the local fusion operation in a sequence manner. To address these issues, we propose a novel architecture named RCNet, which consists of Reverse Feature Pyramid (RevFP) and Cross-scale Shift Network (CSN). RevFP utilizes local bidirectional feature fusion to simplify the bidirectional pyramid inference pipeline. CSN directly propagates representations to both adjacent and non-adjacent levels to enable multi-scale features more correlative. Extensive experiments on the MS COCO dataset demonstrate RCNet can consistently bring significant improvements over both one-stage and two-stage detectors with subtle extra computational overhead. In particular, RetinaNet is boosted to 40.2 AP, which is 3.7 points higher than baseline, by replacing FPN with our proposed model. On COCO test-dev, RCNet can achieve very competitive performance with a single-model single-scale 50.5 AP. Codes will be made available.


page 3

page 8


Selective Multi-Scale Learning for Object Detection

Pyramidal networks are standard methods for multi-scale object detection...

RevBiFPN: The Fully Reversible Bidirectional Feature Pyramid Network

This work introduces the RevSilo, the first reversible module for bidire...

AugFPN: Improving Multi-scale Feature Learning for Object Detection

Current state-of-the-art detectors typically exploit feature pyramid to ...

Learning Spatial Fusion for Single-Shot Object Detection

Pyramidal feature representation is the common practice to address the c...

Dynamic Feature Pyramid Networks for Object Detection

This paper studies feature pyramid network (FPN), which is a widely used...

Dually Supervised Feature Pyramid for Object Detection and Segmentation

Feature pyramid architecture has been broadly adopted in object detectio...

Tea Chrysanthemum Detection under Unstructured Environments Using the TC-YOLO Model

Tea chrysanthemum detection at its flowering stage is one of the key com...