Abstract
Current top-performing object detectors depend on deep CNN backbones, such as ResNet-101 and Inception, benefiting from their powerful feature representations but suffering from high computational costs. Conversely, some lightweight model based detectors fulfil real time processing, while their accuracies are often criticized. In this paper, we explore an alternative to build a fast and accurate detector by strengthening lightweight features using a hand-crafted mechanism. Inspired by the structure of Receptive Fields (RFs) in human visual systems, we propose a novel RF Block (RFB) module, which takes the relationship between the size and eccentricity of RFs into account, to enhance the feature discriminability and robustness. We further assemble RFB to the top of SSD, constructing the RFB Net detector. To evaluate its effectiveness, experiments are conducted on two major benchmarks and the results show that RFB Net is able to reach the performance of advanced very deep detectors while keeping the real-time speed. Code is available at this https URL.
Keywords
Computer scienceDetectorRobustness (evolution)Block (permutation group theory)Object detectionArtificial intelligenceReceptive fieldFeature (linguistics)Code (set theory)Pattern recognition (psychology)Computer visionTelecommunications
Affiliated Institutions
Related Publications
M2Det: A Single-Shot Object Detector Based on Multi-Level Feature Pyramid Network
Feature pyramids are widely exploited by both the state-of-the-art one-stage object detectors (e.g., DSSD, RetinaNet, RefineDet) and the two-stage object detectors (e.g., Mask R...
CenterNet: Keypoint Triplets for Object Detection
In object detection, keypoint-based approaches often experience the drawback of a large number of incorrect object bounding boxes, arguably due to the lack of an additional asse...
Rank & Sort Loss for Object Detection and Instance Segmentation
We propose Rank & Sort (RS) Loss, a ranking-based loss function to train deep object detection and instance segmentation methods (i.e. visual detectors). RS Loss supervises the ...
Feature Pyramid Networks for Object Detection
Feature pyramids are a basic component in recognition systems for detecting objects at different scales. But pyramid representations have been avoided in recent object detectors...
FCOS: Fully Convolutional One-Stage Object Detection
We propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to semantic segmentation. Almost all stat...
Publication Info
- Year
- 2018
- Type
- book-chapter
- Pages
- 404-419
- Citations
- 1687
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
1687
OpenAlex
164
Influential
Cite This
Songtao Liu,
Di Huang,
Yunhong Wang
(2018).
Receptive Field Block Net for Accurate and Fast Object Detection.
Lecture notes in computer science
, 404-419.
https://doi.org/10.1007/978-3-030-01252-6_24
Identifiers
- DOI
- 10.1007/978-3-030-01252-6_24
- PMID
- 40686667
- PMCID
- PMC12274184
- arXiv
- 1711.07767