Layer-wise Customized Weak Segmentation Block and AIoU Loss for Accurate Object Detection

• URL: http://arxiv.org/abs/2108.11021v1
• Date: Wed, 25 Aug 2021 02:42:28 GMT
• Title: Layer-wise Customized Weak Segmentation Block and AIoU Loss for Accurate Object Detection
• Authors: Keyang Wang, Lei Zhang, Wenli Song, Qinghai Lang, Lingyun Qin
• Abstract summary: We propose a scale-customized weak segmentation (SCWS) block at the pixel level for scale customized object feature learning in each layer. By integrating the SCWS blocks into the single-shot detector, a scale-aware object detector (SCOD) is constructed to detect objects of different sizes naturally and accurately.
• Score: 7.3179451998143605
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The anchor-based detectors handle the problem of scale variation by building the feature pyramid and directly setting different scales of anchors on each cell in different layers. However, it is difficult for box-wise anchors to guide the adaptive learning of scale-specific features in each layer because there is no one-to-one correspondence between box-wise anchors and pixel-level features. In order to alleviate the problem, in this paper, we propose a scale-customized weak segmentation (SCWS) block at the pixel level for scale customized object feature learning in each layer. By integrating the SCWS blocks into the single-shot detector, a scale-aware object detector (SCOD) is constructed to detect objects of different sizes naturally and accurately. Furthermore, the standard location loss neglects the fact that the hard and easy samples may be seriously imbalanced. A forthcoming problem is that it is unable to get more accurate bounding boxes due to the imbalance. To address this problem, an adaptive IoU (AIoU) loss via a simple yet effective squeeze operation is specified in our SCOD. Extensive experiments on PASCAL VOC and MS COCO demonstrate the superiority of our SCOD.

Related papers

• SCLNet: A Scale-Robust Complementary Learning Network for Object Detection in UAV Images [0.0]
  This paper introduces a scale-robust complementary learning network (SCLNet) to address the scale challenges. One implementation is based on our proposed scale-complementary decoder and scale-complementary loss function. Another implementation is based on our proposed contrastive complement network and contrastive complement loss function.
  arXiv  Detail & Related papers  (2024-09-11T05:39:25Z)
• 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)
• Infrared Small Target Detection with Scale and Location Sensitivity [19.89762494490961]
  In this paper, we focus on boosting detection performance with a more effective loss but a simpler model structure. Specifically, we first propose a novel Scale and Location Sensitive (SLS) loss to handle the limitations of existing losses. By applying SLS loss to each scale of the predictions, our MSHNet outperforms existing state-of-the-art methods by a large margin.
  arXiv  Detail & Related papers  (2024-03-28T12:28:58Z)
• Global Context Aggregation Network for Lightweight Saliency Detection of Surface Defects [70.48554424894728]
  We develop a Global Context Aggregation Network (GCANet) for lightweight saliency detection of surface defects on the encoder-decoder structure. First, we introduce a novel transformer encoder on the top layer of the lightweight backbone, which captures global context information through a novel Depth-wise Self-Attention (DSA) module. The experimental results on three public defect datasets demonstrate that the proposed network achieves a better trade-off between accuracy and running efficiency compared with other 17 state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-09-22T06:19:11Z)
• STEERER: Resolving Scale Variations for Counting and Localization via Selective Inheritance Learning [74.2343877907438]
  Scale variation is a deep-rooted problem in object counting, which has not been effectively addressed by existing scale-aware algorithms. We propose a novel method termed STEERER that addresses the issue of scale variations in object counting. STEERER selects the most suitable scale for patch objects to boost feature extraction and only inherits discriminative features from lower to higher resolution progressively.
  arXiv  Detail & Related papers  (2023-08-21T05:09:07Z)
• SIOD: Single Instance Annotated Per Category Per Image for Object Detection [67.64774488115299]
  We propose the Single Instance annotated Object Detection (SIOD), requiring only one instance annotation for each existing category in an image. Degraded from inter-task (WSOD) or inter-image (SSOD) discrepancies to the intra-image discrepancy, SIOD provides more reliable and rich prior knowledge for mining the rest of unlabeled instances. Under the SIOD setting, we propose a simple yet effective framework, termed Dual-Mining (DMiner), which consists of a Similarity-based Pseudo Label Generating module (SPLG) and a Pixel-level Group Contrastive Learning module (PGCL)
  arXiv  Detail & Related papers  (2022-03-29T08:49:51Z)
• The KFIoU Loss for Rotated Object Detection [115.334070064346]
  In this paper, we argue that one effective alternative is to devise an approximate loss who can achieve trend-level alignment with SkewIoU loss. Specifically, we model the objects as Gaussian distribution and adopt Kalman filter to inherently mimic the mechanism of SkewIoU. The resulting new loss called KFIoU is easier to implement and works better compared with exact SkewIoU.
  arXiv  Detail & Related papers  (2022-01-29T10:54:57Z)
• Toward Minimal Misalignment at Minimal Cost in One-Stage and Anchor-Free Object Detection [6.486325109549893]
  classification and regression branches have different sensibility to the features from the same scale level and the same spatial location. We propose a point-based prediction method, which is based on the assumption that the high classification confidence point has the high regression quality, leads to the misalignment problem. We aim to resolve the phenomenon at minimal cost: a minor adjustment of the head network and a new label assignment method replacing the rigid one.
  arXiv  Detail & Related papers  (2021-12-16T14:22:13Z)
• 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)
• Single-Shot Two-Pronged Detector with Rectified IoU Loss [10.616828072065093]
  We introduce a novel two-pronged transductive idea to explore the relationship among different layers in both backward and forward directions. Under the guidance of the two-pronged idea, we propose a Two-Pronged Network (TPNet) to achieve bidirectional transfer between high-level features and low-level features.
  arXiv  Detail & Related papers  (2020-08-08T12:36:55Z)
• Multi-scale Interactive Network for Salient Object Detection [91.43066633305662]
  We propose the aggregate interaction modules to integrate the features from adjacent levels. To obtain more efficient multi-scale features, the self-interaction modules are embedded in each decoder unit. Experimental results on five benchmark datasets demonstrate that the proposed method without any post-processing performs favorably against 23 state-of-the-art approaches.
  arXiv  Detail & Related papers  (2020-07-17T15:41:37Z)

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.