DeepAI AI Chat
Log In Sign Up

Learning Spatial Fusion for Single-Shot Object Detection

by   Songtao Liu, et al.
Beihang University

Pyramidal feature representation is the common practice to address the challenge of scale variation in object detection. However, the inconsistency across different feature scales is a primary limitation for the single-shot detectors based on feature pyramid. In this work, we propose a novel and data driven strategy for pyramidal feature fusion, referred to as adaptively spatial feature fusion (ASFF). It learns the way to spatially filter conflictive information to suppress the inconsistency, thus improving the scale-invariance of features, and introduces nearly free inference overhead. With the ASFF strategy and a solid baseline of YOLOv3, we achieve the best speed-accuracy trade-off on the MS COCO dataset, reporting 38.1 FPS and 43.9


page 3

page 6

page 7


FSSD: Feature Fusion Single Shot Multibox Detector

SSD (Single Shot Multibox Detetor) is one of the best object detection a...

AFPN: Asymptotic Feature Pyramid Network for Object Detection

Multi-scale features are of great importance in encoding objects with sc...

Towards Better Object Detection in Scale Variation with Adaptive Feature Selection

It is a common practice to exploit pyramidal feature representation to t...

Learning Object Detectors from Scratch with Gated Recurrent Feature Pyramids

In this paper, we propose gated recurrent feature pyramid for the proble...

Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detection

Conventional deep learning based methods for object detection require a ...

Single-Shot Bidirectional Pyramid Networks for High-Quality Object Detection

Recent years have witnessed many exciting achievements for object detect...

CF-YOLO: Cross Fusion YOLO for Object Detection in Adverse Weather with a High-quality Real Snow Dataset

Snow is one of the toughest adverse weather conditions for object detect...

Code Repositories


yolov3 with mobilenet v2 and ASFF

view repo