VarifocalNet: An IoU-aware Dense Object Detector

• URL: http://arxiv.org/abs/2008.13367v2
• Date: Thu, 4 Mar 2021 15:32:38 GMT
• Title: VarifocalNet: An IoU-aware Dense Object Detector
• Authors: Haoyang Zhang, Ying Wang, Feras Dayoub and Niko S\"underhauf
• Abstract summary: We learn an Iou-aware Classification Score (IACS) as a joint representation of object presence confidence and localization accuracy. We show that dense object detectors can achieve a more accurate ranking of candidate detections based on the IACS. We build an IoU-aware dense object detector based on the FCOS+ATSS architecture, that we call VarifocalNet or VFNet for short.
• Score: 11.580759212782812
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accurately ranking the vast number of candidate detections is crucial for dense object detectors to achieve high performance. Prior work uses the classification score or a combination of classification and predicted localization scores to rank candidates. However, neither option results in a reliable ranking, thus degrading detection performance. In this paper, we propose to learn an Iou-aware Classification Score (IACS) as a joint representation of object presence confidence and localization accuracy. We show that dense object detectors can achieve a more accurate ranking of candidate detections based on the IACS. We design a new loss function, named Varifocal Loss, to train a dense object detector to predict the IACS, and propose a new star-shaped bounding box feature representation for IACS prediction and bounding box refinement. Combining these two new components and a bounding box refinement branch, we build an IoU-aware dense object detector based on the FCOS+ATSS architecture, that we call VarifocalNet or VFNet for short. Extensive experiments on MS COCO show that our VFNet consistently surpasses the strong baseline by $\sim$2.0 AP with different backbones. Our best model VFNet-X-1200 with Res2Net-101-DCN achieves a single-model single-scale AP of 55.1 on COCO test-dev, which is state-of-the-art among various object detectors.Code is available at https://github.com/hyz-xmaster/VarifocalNet .

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)
• Cascade-DETR: Delving into High-Quality Universal Object Detection [99.62131881419143]
  We introduce Cascade-DETR for high-quality universal object detection. We propose the Cascade Attention layer, which explicitly integrates object-centric information into the detection decoder. Lastly, we introduce a universal object detection benchmark, UDB10, that contains 10 datasets from diverse domains.
  arXiv  Detail & Related papers  (2023-07-20T17:11:20Z)
• Anchor Retouching via Model Interaction for Robust Object Detection in Aerial Images [15.404024559652534]
  We present an effective Dynamic Enhancement Anchor (DEA) network to construct a novel training sample generator. Our method achieves state-of-the-art performance in accuracy with moderate inference speed and computational overhead for training.
  arXiv  Detail & Related papers  (2021-12-13T14:37:20Z)
• Disentangle Your Dense Object Detector [82.22771433419727]
  Deep learning-based dense object detectors have achieved great success in the past few years and have been applied to numerous multimedia applications such as video understanding. However, the current training pipeline for dense detectors is compromised to lots of conjunctions that may not hold. We propose Disentangled Dense Object Detector (DDOD), in which simple and effective disentanglement mechanisms are designed and integrated into the current state-of-the-art detectors.
  arXiv  Detail & Related papers  (2021-07-07T00:52:16Z)
• Modulating Localization and Classification for Harmonized Object Detection [40.82723262074911]
  We propose a mutual learning framework to modulate the two tasks. In particular, the two tasks are forced to learn from each other with a novel mutual labeling strategy. We achieve a significant performance gain over the baseline detectors on the COCO dataset.
  arXiv  Detail & Related papers  (2021-03-16T10:36:02Z)
• Corner Proposal Network for Anchor-free, Two-stage Object Detection [174.59360147041673]
  The goal of object detection is to determine the class and location of objects in an image. This paper proposes a novel anchor-free, two-stage framework which first extracts a number of object proposals. We demonstrate that these two stages are effective solutions for improving recall and precision.
  arXiv  Detail & Related papers  (2020-07-27T19:04:57Z)
• FCOS: A simple and strong anchor-free object detector [111.87691210818194]
  We propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion. Almost all state-of-the-art object detectors such as RetinaNet, SSD, YOLOv3, and Faster R-CNN rely on pre-defined anchor boxes. In contrast, our proposed detector FCOS is anchor box free, as well as proposal free.
  arXiv  Detail & Related papers  (2020-06-14T01:03:39Z)
• Scope Head for Accurate Localization in Object Detection [135.9979405835606]
  We propose a novel detector coined as ScopeNet, which models anchors of each location as a mutually dependent relationship. With our concise and effective design, the proposed ScopeNet achieves state-of-the-art results on COCO.
  arXiv  Detail & Related papers  (2020-05-11T04:00:09Z)
• Seeing without Looking: Contextual Rescoring of Object Detections for AP Maximization [4.346179456029563]
  We propose to incorporate context in object detection by post-processing the output of an arbitrary detector. Rescoring is done by conditioning on contextual information from the entire set of detections. We show that AP can be improved by simply reassigning the detection confidence values.
  arXiv  Detail & Related papers  (2019-12-27T18:56:29Z)

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.