• Corpus ID: 215238659

Feature Pyramid Grids

@article{Chen2020FeaturePG,
  title={Feature Pyramid Grids},
  author={Kai Chen and Yuhang Cao and Chen Change Loy and Dahua Lin and Christoph Feichtenhofer},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.03580}
}
Feature pyramid networks have been widely adopted in the object detection literature to improve feature representations for better handling of variations in scale. In this paper, we present Feature Pyramid Grids (FPG), a deep multi-pathway feature pyramid, that represents the feature scale-space as a regular grid of parallel bottom-up pathways which are fused by multi-directional lateral connections. FPG can improve single-pathway feature pyramid networks by significantly increasing its… 
Fine-Grained Dynamic Head for Object Detection
TLDR
A fine-grained dynamic head is proposed to conditionally select a pixel-level combination of FPN features from different scales for each instance, which further releases the ability of multi-scale feature representation.
Dense Feature Pyramid Grids Network for Single Image Deraining
TLDR
A novel densely connected network with Dense Feature Pyramid Grids Modules, called DFPGN, to solve the rain removal task by combining five operations from different layers with various pathways and scales as the input of the current layer to improve the deraining ability of the network.
Feature Fusion Methods in Deep-Learning Generic Object Detection: A Survey
TLDR
This survey infers that feature fusion methods have acquired some good results especially in recent five years, but further improvements or potential research directions still widely exist.
Learning to Aggregate Multi-Scale Context for Instance Segmentation in Remote Sensing Images
TLDR
A novel context aggregation network (CATNet) is proposed to improve the feature extraction process of instance segmentation in remote sensing images, and outperforms state-of-the-arts under similar computational costs.
CATNet: Context AggregaTion Network for Instance Segmentation in Remote Sensing Images
TLDR
A novel context aggregation network (CATNet) is proposed to improve the feature extraction process of instance segmentation in remote sensing images and demonstrates that the proposed approach outperforms state-of-the-arts with similar computational costs.
A Holistically-Guided Decoder for Deep Representation Learning with Applications to Semantic Segmentation and Object Detection
TLDR
This paper proposes one novel holistically-guided decoder which is introduced to obtain the high-resolution semantic-rich feature maps via the multi-scale features from the encoder, and implements the EfficientFCN architecture for semantic segmentation and HGD-FPN for object detection and instance segmentation.
SDTP: Semantic-aware Decoupled Transformer Pyramid for Dense Image Prediction
TLDR
A novel Semantic-aware Decoupled Transformer Pyramid (SDTP) for dense image prediction, consisting of Intra-level Semantic Promotion (ISP), Crosslevel Decoupling Interaction (CDI) and Attention Refinement Function (ARF) and the proposed components are all plug-and-play, which can be embedded in other methods.
DSIC: Dynamic Sample-Individualized Connector for Multi-Scale Object Detection
TLDR
A Dynamic Sample-Individualized Connector for multi-scale object detection, which dynamically adjusts network connections to fit different samples, and demonstrates that the proposed method outperforms the state-of-the- arts.
Excavating RoI Attention for Underwater Object Detection
TLDR
This paper chooses the external attention module, a modified self-attention with reduced parameters, and proposes a double head structure and Positional Encoding module that can achieve promising performance in object detection.
RiWNet: A moving object instance segmentation Network being Robust in adverse Weather conditions
TLDR
The experiment proves how RiWFPN improves the network’s resilience to adverse weather effects compared to other FPN structures, and RiWNet shows better performance especially under adverse weather conditions.
...
...

References

SHOWING 1-10 OF 41 REFERENCES
Feature Pyramid Networks for Object Detection
TLDR
This paper exploits the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost and achieves state-of-the-art single-model results on the COCO detection benchmark without bells and whistles.
M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network
TLDR
A powerful end-to-end one-stage object detector called M2Det is designed and train by integrating it into the architecture of SSD, and achieve better detection performance than state-of-the-art one- stage detectors.
NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection
TLDR
The adopted Neural Architecture Search is adopted and a new feature pyramid architecture in a novel scalable search space covering all cross-scale connections is discovered, named NAS-FPN, which achieves better accuracy and latency tradeoff compared to state-of-the-art object detection models.
Very Deep Convolutional Networks for Large-Scale Image Recognition
TLDR
This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection
TLDR
A unified deep neural network, denoted the multi-scale CNN (MS-CNN), is proposed for fast multi- scale object detection, which is learned end-to-end, by optimizing a multi-task loss.
Path Aggregation Network for Instance Segmentation
TLDR
Path Aggregation Network (PANet) is proposed aiming at boosting information flow in proposal-based instance segmentation framework by enhancing the entire feature hierarchy with accurate localization signals in lower layers by bottom-up path augmentation.
Efficient Neural Architecture Transformation Searchin Channel-Level for Object Detection
TLDR
This paper proposes a novel neural architecture search strategy in channel-level instead of path-level and devise a search space specially targeting at object detection, which could be discovered to adapt a network designed for image classification to task of object detection.
Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
TLDR
This paper presents a network level search space that includes many popular designs, and develops a formulation that allows efficient gradient-based architecture search and demonstrates the effectiveness of the proposed method on the challenging Cityscapes, PASCAL VOC 2012, and ADE20K datasets.
SSD: Single Shot MultiBox Detector
TLDR
The approach, named SSD, discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature map location, which makes SSD easy to train and straightforward to integrate into systems that require a detection component.
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TLDR
This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.
...
...