You Should Look at All Objects

• URL: http://arxiv.org/abs/2207.07889v1
• Date: Sat, 16 Jul 2022 09:59:34 GMT
• Title: You Should Look at All Objects
• Authors: Zhenchao Jin, Dongdong Yu, Luchuan Song, Zehuan Yuan, Lequan Yu
• Abstract summary: 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.
• Score: 28.862053913000384
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Feature pyramid network (FPN) is one of the key components for object detectors. However, there is a long-standing puzzle for researchers that the detection performance of large-scale objects are usually suppressed after introducing FPN. To this end, this paper first revisits FPN in the detection framework and reveals the nature of the success of FPN from the perspective of optimization. Then, we point out that the degraded performance of large-scale objects is due to the arising of improper back-propagation paths after integrating FPN. It makes each level of the backbone network only has the ability to look at the objects within a certain scale range. Based on these analysis, two feasible strategies are proposed to enable each level of the backbone to look at all objects in the FPN-based detection frameworks. Specifically, one is to introduce auxiliary objective functions to make each backbone level directly receive the back-propagation signals of various-scale objects during training. The other is to construct the feature pyramid in a more reasonable way to avoid the irrational back-propagation paths. Extensive experiments on the COCO benchmark validate the soundness of our analysis and the effectiveness of our methods. Without bells and whistles, we demonstrate that our method achieves solid improvements (more than 2%) on various detection frameworks: one-stage, two-stage, anchor-based, anchor-free and transformer-based detectors.

Related papers

• Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning [52.06176253457522]
  We propose a two-stage framework tailored for small object detection based on the Coarse-to-fine pipeline and Feature Imitation learning. CFINet achieves state-of-the-art performance on the large-scale small object detection benchmarks, SODA-D and SODA-A.
  arXiv  Detail & Related papers  (2023-08-18T13:13:09Z)
• AFPN: Asymptotic Feature Pyramid Network for Object Detection [16.86715579071991]
  This paper proposes an feature pyramid network (AFPN) to support direct interaction at non-adjacent levels. AFPN is initiated by fusing two adjacent low-level features and achieves higher-level features into the fusion process. We incorporate the proposed AFPN into both two-stage and one-stage object detection frameworks and evaluate with the MS-COCO 2017 validation and test datasets.
  arXiv  Detail & Related papers  (2023-06-28T07:58:49Z)
• A Tri-Layer Plugin to Improve Occluded Detection [100.99802831241583]
  We propose a simple '' module for the detection head of two-stage object detectors to improve the recall of partially occluded objects. The module predicts a tri-layer of segmentation masks for the target object, the occluder and the occludee, and by doing so is able to better predict the mask of the target object. We also establish a COCO evaluation dataset to measure the recall performance of partially occluded and separated objects.
  arXiv  Detail & Related papers  (2022-10-18T17:59:51Z)
• SFPN: Synthetic FPN for Object Detection [6.117917355232904]
  This paper proposes a new SFPN (Synthetic Fusion Pyramid Network) arichtecture to enhance the accuracy of light-weight CNN backones. Experiments prove the SFPN architecture outperforms either the large backbone VGG16, ResNet50 or light-weight backbones such as MobilenetV2 based on AP score.
  arXiv  Detail & Related papers  (2022-03-04T17:19:50Z)
• Plug-and-Play Few-shot Object Detection with Meta Strategy and Explicit Localization Inference [78.41932738265345]
  This paper proposes a plug detector that can accurately detect the objects of novel categories without fine-tuning process. We introduce two explicit inferences into the localization process to reduce its dependence on annotated data. It shows a significant lead in both efficiency, precision, and recall under varied evaluation protocols.
  arXiv  Detail & Related papers  (2021-10-26T03:09:57Z)
• Multi-patch Feature Pyramid Network for Weakly Supervised Object Detection in Optical Remote Sensing Images [39.25541709228373]
  We propose a new architecture for object detection with a multiple patch feature pyramid network (MPFP-Net) MPFP-Net is different from the current models that during training only pursue the most discriminative patches. We introduce an effective method to regularize the residual values and make the fusion transition layers strictly norm-preserving.
  arXiv  Detail & Related papers  (2021-08-18T09:25:39Z)
• Double-Dot Network for Antipodal Grasp Detection [20.21384585441404]
  This paper proposes a new deep learning approach to antipodal grasp detection, named Double-Dot Network (DD-Net) It follows the recent anchor-free object detection framework, which does not depend on empirically pre-set anchors. An effective CNN architecture is introduced to localize such fingertips, and with the help of auxiliary centers for refinement, it accurately and robustly infers grasp candidates.
  arXiv  Detail & Related papers  (2021-08-03T14:21:17Z)
• Slender Object Detection: Diagnoses and Improvements [74.40792217534]
  In this paper, we are concerned with the detection of a particular type of objects with extreme aspect ratios, namely textbfslender objects. For a classical object detection method, a drastic drop of $18.9%$ mAP on COCO is observed, if solely evaluated on slender objects.
  arXiv  Detail & Related papers  (2020-11-17T09:39:42Z)
• One-Shot Object Detection without Fine-Tuning [62.39210447209698]
  We introduce a two-stage model consisting of a first stage Matching-FCOS network and a second stage Structure-Aware Relation Module. We also propose novel training strategies that effectively improve detection performance. Our method exceeds the state-of-the-art one-shot performance consistently on multiple datasets.
  arXiv  Detail & Related papers  (2020-05-08T01:59:23Z)
• 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.