Dynamic Feature Pyramid Networks for Object Detection

• URL: http://arxiv.org/abs/2012.00779v1
• Date: Tue, 1 Dec 2020 19:03:55 GMT
• Title: Dynamic Feature Pyramid Networks for Object Detection
• Authors: Mingjian Zhu, Kai Han, Changbin Yu, Yunhe Wang
• Abstract summary: We introduce an inception FPN in which each layer contains convolution filters with different kernel sizes to enlarge the receptive field. We propose a new dynamic FPN (DyFPN) which consists of multiple branches with different computational costs. Experiments conducted on benchmarks demonstrate that the proposed DyFPN significantly improves performance with the optimal allocation of computation resources.
• Score: 40.24111664691307
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper studies feature pyramid network (FPN), which is a widely used module for aggregating multi-scale feature information in the object detection system. The performance gain in most of the existing works is mainly contributed to the increase of computation burden, especially the floating number operations (FLOPs). In addition, the multi-scale information within each layer in FPN has not been well investigated. To this end, we first introduce an inception FPN in which each layer contains convolution filters with different kernel sizes to enlarge the receptive field and integrate more useful information. Moreover, we point out that not all objects need such a complicated calculation module and propose a new dynamic FPN (DyFPN). Each layer in the DyFPN consists of multiple branches with different computational costs. Specifically, the output features of DyFPN will be calculated by using the adaptively selected branch according to a learnable gating operation. Therefore, the proposed method can provide a more efficient dynamic inference for achieving a better trade-off between accuracy and detection performance. Extensive experiments conducted on benchmarks demonstrate that the proposed DyFPN significantly improves performance with the optimal allocation of computation resources. For instance, replacing the FPN with the inception FPN improves detection accuracy by 1.6 AP using the Faster R-CNN paradigm on COCO minival, and the DyFPN further reduces about 40% of its FLOPs while maintaining similar performance.

Related papers

• Algorithm-Hardware Co-Design of Distribution-Aware Logarithmic-Posit Encodings for Efficient DNN Inference [4.093167352780157]
  We introduce Logarithmic Posits (LP), an adaptive, hardware-friendly data type inspired by posits. We also develop a novel genetic-algorithm based framework, LP Quantization (LPQ), to find optimal layer-wise LP parameters.
  arXiv  Detail & Related papers  (2024-03-08T17:28:49Z)
• Receptive Field-based Segmentation for Distributed CNN Inference Acceleration in Collaborative Edge Computing [93.67044879636093]
  We study inference acceleration using distributed convolutional neural networks (CNNs) in collaborative edge computing network. We propose a novel collaborative edge computing using fused-layer parallelization to partition a CNN model into multiple blocks of convolutional layers.
  arXiv  Detail & Related papers  (2022-07-22T18:38:11Z)
• Transformer-based Context Condensation for Boosting Feature Pyramids in Object Detection [77.50110439560152]
  Current object detectors typically have a feature pyramid (FP) module for multi-level feature fusion (MFF) We propose a novel and efficient context modeling mechanism that can help existing FPs deliver better MFF results. In particular, we introduce a novel insight that comprehensive contexts can be decomposed and condensed into two types of representations for higher efficiency.
  arXiv  Detail & Related papers  (2022-07-14T01:45:03Z)
• A^2-FPN: Attention Aggregation based Feature Pyramid Network for Instance Segmentation [68.10621089649486]
  We propose Attention Aggregation based Feature Pyramid Network (A2-FPN) to improve multi-scale feature learning. A2-FPN achieves an improvement of 2.0% and 1.4% mask AP when integrated into the strong baselines such as Cascade Mask R-CNN and Hybrid Task Cascade.
  arXiv  Detail & Related papers  (2021-05-07T11:51:08Z)
• Implicit Feature Pyramid Network for Object Detection [22.530998243247154]
  We present an implicit feature pyramid network (i-FPN) for object detection. We propose to use an implicit function, recently introduced in deep equilibrium model (DEQ) to model the transformation of FPN. Experimental results on MS dataset show that i-FPN can significantly boost detection performance compared to baseline detectors.
  arXiv  Detail & Related papers  (2020-12-25T11:30:27Z)
• Fine-Grained Dynamic Head for Object Detection [68.70628757217939]
  We propose a fine-grained dynamic head to conditionally select a pixel-level combination of FPN features from different scales for each instance. Experiments demonstrate the effectiveness and efficiency of the proposed method on several state-of-the-art detection benchmarks.
  arXiv  Detail & Related papers  (2020-12-07T08:16:32Z)
• iffDetector: Inference-aware Feature Filtering for Object Detection [70.8678270164057]
  We introduce a generic Inference-aware Feature Filtering (IFF) module that can easily be combined with modern detectors. IFF performs closed-loop optimization by leveraging high-level semantics to enhance the convolutional features. IFF can be fused with CNN-based object detectors in a plug-and-play manner with negligible computational cost overhead.
  arXiv  Detail & Related papers  (2020-06-23T02:57:29Z)
• ResFPN: Residual Skip Connections in Multi-Resolution Feature Pyramid Networks for Accurate Dense Pixel Matching [10.303618438296981]
  Feature Pyramid Networks (FPN) have proven to be a suitable feature extractor for CNN-based dense matching tasks. We present ResFPN -- a multi-resolution feature pyramid network with multiple residual skip connections. In our ablation study, we demonstrate the effectiveness of our novel architecture with clearly higher accuracy than FPN.
  arXiv  Detail & Related papers  (2020-06-22T13:31:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.