Parallel Feature Pyramid Network for Object Detection

By Seung-Wook Kim, Hyong-Keun Kook, Jee-Young Sun, Mun-Cheon Kang, Sung-Jea Ko. 2018

286 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection (2019, background): “6 PFPNet-R512 [21] trainval35k VGG-16 35.”
EfficientDet: Scalable and Efficient Object Detection (2019, background): “Cross-scale connections are further studied in [13, 12, 34].”
Deep High-Resolution Representation Learning for Visual Recognition (2019, neutral): “PFPNet [70] VGG16 512 35.”
YOLOv4: Optimal Speed and Accuracy of Object Detection (2020, background): “Parallel Feature Pyramid Network for Object Detection [34] PFPNet-R VGG-16 320 33 (M) 31.”
Fast Convergence of DETR with Spatially Modulated Co-Attention (2021, background): “Feature Pyramid Network (FPN) [24] and its variants [20] proposed a bottom-up and top-down way to generate multi-scale features for achieving better performance for object detection.”
Learning Spatial Fusion for Single-Shot Object Detection (2019, background): “Kim et al. [13] show a parallel feature pyramid by adopting spatial pyramid pooling and widening the network.”
High-Resolution Representations for Labeling Pixels and Regions (2019, unknown): “PFPNet [46] VGG16 512 - 35.”
M3D-RPN: Monocular 3D Region Proposal Network for Object Detection (2019, background): “We observe that 2D object detection performs reasonably and continues to make rapid advances [5, 6, 11, 14, 19, 33].”
High-Level Semantic Feature Detection: A New Perspective for Pedestrian Detection (2019, background): “Note that more complicated feature fusion strategies like [23, 15, 17] can be explored to further improve the detection performance, but it is not in the scope of this work.”
CSPNet: A New Backbone that can Enhance Learning Capability of CNN (2019, unknown): “8 PFPNet (S) [12] VGG16 [31] 300×300 39 29.”
Towards Accurate One-Stage Object Detection With AP-Loss (2019, background): “Table 3 lists the benchmark results comparing to recent state-of-the-art onestage detectors such as SSD [18], YOLOv2 [23], DSSD [6], DSOD [28], DES [36], RetinaNet [15], RefineDet [35], PFPNet [10], RFBNet [17].”
Rethinking Coarse-to-Fine Approach in Single Image Deblurring (2021, methodology): “Although PFPNet was trained using the PASCAL VOC dataset [2] that contains 20 different classes, the blurry images in the GoPro dataset primarily contain only three classes among them, i.e., car, person, and potted plant.”
Imbalance Problems in Object Detection: A Review (2019, methodology): “Note that, unlike FPN [26], there is no lateral connection to the backbone network during the zoom-in phase, which is basically a sequence of deconvolutional layers (see red arrows for the zoom-in phase).”
A Survey of Deep Learning-Based Object Detection (2019, background): “[64] propose a parallel feature pyramid (FP) net-”
ScratchDet: Exploring to Train Single-Shot Object Detectors from Scratch (2018, unknown): “9 PFPNet-R320 (Kim et al. 2018) trainval35k VGG-16 31.”
P2T: Pyramid Pooling Transformer for Scene Understanding (2021, methodology): “After that, pyramid pooling has been widely applied to various vision tasks such as semantic segmentation [37], [54], [55], [56], [57] and object detection [36], [58], [59], [60].”