Effective Fusion Factor in FPN for Tiny Object Detection

• URL: http://arxiv.org/abs/2011.02298v2
• Date: Mon, 9 Nov 2020 09:40:08 GMT
• Title: Effective Fusion Factor in FPN for Tiny Object Detection
• Authors: Yuqi Gong, Xuehui Yu, Yao Ding, Xiaoke Peng, Jian Zhao, Zhenjun Han
• Abstract summary: We argue that the top-down connections between adjacent layers in FPN bring two-side influences for tiny object detection. We propose a novel concept, fusion factor, to control information that deep layers deliver to shallow layers. We show that when configuring FPN with a proper fusion factor, the network is able to achieve significant performance gains.
• Score: 12.241778953479226
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: FPN-based detectors have made significant progress in general object detection, e.g., MS COCO and PASCAL VOC. However, these detectors fail in certain application scenarios, e.g., tiny object detection. In this paper, we argue that the top-down connections between adjacent layers in FPN bring two-side influences for tiny object detection, not only positive. We propose a novel concept, fusion factor, to control information that deep layers deliver to shallow layers, for adapting FPN to tiny object detection. After series of experiments and analysis, we explore how to estimate an effective value of fusion factor for a particular dataset by a statistical method. The estimation is dependent on the number of objects distributed in each layer. Comprehensive experiments are conducted on tiny object detection datasets, e.g., TinyPerson and Tiny CityPersons. Our results show that when configuring FPN with a proper fusion factor, the network is able to achieve significant performance gains over the baseline on tiny object detection datasets. Codes and models will be released.

Related papers

• Renormalized Connection for Scale-preferred Object Detection in Satellite Imagery [51.83786195178233]
  We design a Knowledge Discovery Network (KDN) to implement the renormalization group theory in terms of efficient feature extraction. Renormalized connection (RC) on the KDN enables synergistic focusing'' of multi-scale features. RCs extend the multi-level feature's divide-and-conquer'' mechanism of the FPN-based detectors to a wide range of scale-preferred tasks.
  arXiv  Detail & Related papers  (2024-09-09T13:56:22Z)
• Visible and Clear: Finding Tiny Objects in Difference Map [50.54061010335082]
  We introduce a self-reconstruction mechanism in the detection model, and discover the strong correlation between it and the tiny objects. Specifically, we impose a reconstruction head in-between the neck of a detector, constructing a difference map of the reconstructed image and the input, which shows high sensitivity to tiny objects. We further develop a Difference Map Guided Feature Enhancement (DGFE) module to make the tiny feature representation more clear.
  arXiv  Detail & Related papers  (2024-05-18T12:22:26Z)
• Better Sampling, towards Better End-to-end Small Object Detection [7.7473020808686694]
  Small object detection remains unsatisfactory due to limited characteristics and high density and mutual overlap. We propose methods enhancing sampling within an end-to-end framework. Our model demonstrates a significant enhancement, achieving a 2.9% increase in average precision (AP) over the state-of-the-art (SOTA) on the VisDrone dataset.
  arXiv  Detail & Related papers  (2024-05-17T04:37:44Z)
• Innovative Horizons in Aerial Imagery: LSKNet Meets DiffusionDet for Advanced Object Detection [55.2480439325792]
  We present an in-depth evaluation of an object detection model that integrates the LSKNet backbone with the DiffusionDet head. The proposed model achieves a mean average precision (MAP) of approximately 45.7%, which is a significant improvement. This advancement underscores the effectiveness of the proposed modifications and sets a new benchmark in aerial image analysis.
  arXiv  Detail & Related papers  (2023-11-21T19:49:13Z)
• You Should Look at All Objects [28.862053913000384]
  This paper revisits FPN in the detection framework and reveals the nature of the success of FPN from the perspective of optimization. The degraded performance of large-scale objects is due to the arising of improper back-propagation paths after integrating FPN. Two feasible strategies are proposed to enable each level of the backbone to look at all objects in the FPN-based detection frameworks.
  arXiv  Detail & Related papers  (2022-07-16T09:59:34Z)
• SSPNet: Scale Selection Pyramid Network for Tiny Person Detection from UAV Images [10.439155825343517]
  We propose a Scale Selection Pyramid network (SSPNet) for tiny person detection. SSPNet consists of three components: Context Attention Module (CAM), Scale Enhancement Module (SEM), and Scale Selection Module (SSM) Our method outperforms other state-of-the-art (SOTA) detectors.
  arXiv  Detail & Related papers  (2021-07-04T05:46:41Z)
• Detecting Human-Object Interaction via Fabricated Compositional Learning [106.37536031160282]
  Human-Object Interaction (HOI) detection is a fundamental task for high-level scene understanding. Human has extremely powerful compositional perception ability to cognize rare or unseen HOI samples. We propose Fabricated Compositional Learning (FCL) to address the problem of open long-tailed HOI detection.
  arXiv  Detail & Related papers  (2021-03-15T08:52:56Z)
• DecAug: Augmenting HOI Detection via Decomposition [54.65572599920679]
  Current algorithms suffer from insufficient training samples and category imbalance within datasets. We propose an efficient and effective data augmentation method called DecAug for HOI detection. Experiments show that our method brings up to 3.3 mAP and 1.6 mAP improvements on V-COCO and HICODET dataset.
  arXiv  Detail & Related papers  (2020-10-02T13:59:05Z)
• A Systematic Evaluation of Object Detection Networks for Scientific Plots [17.882932963813985]
  We train and compare the accuracy of various SOTA object detection networks on the PlotQA dataset. At the standard IOU setting of 0.5, most networks perform well with mAP scores greater than 80% in detecting the relatively simple objects in plots. However, the performance drops drastically when evaluated at a stricter IOU of 0.9 with the best model giving a mAP of 35.70%.
  arXiv  Detail & Related papers  (2020-07-05T05:30:53Z)
• Extended Feature Pyramid Network for Small Object Detection [20.029591259254847]
  We propose extended feature pyramid network (EFPN) with an extra high-resolution pyramid level specialized for small object detection. Specifically, we design a novel module, named feature texture transfer (FTT), which is used to super-resolve features and extract credible regional details simultaneously. In our experiments, the proposed EFPN is efficient on both computation and memory, and yields state-of-the-art results.
  arXiv  Detail & Related papers  (2020-03-16T04:27:54Z)
• Cross-layer Feature Pyramid Network for Salient Object Detection [102.20031050972429]
  We propose a novel Cross-layer Feature Pyramid Network to improve the progressive fusion in salient object detection. The distributed features per layer own both semantics and salient details from all other layers simultaneously, and suffer reduced loss of important information.
  arXiv  Detail & Related papers  (2020-02-25T14:06:27Z)

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.