SaccadeNet: A Fast and Accurate Object Detector

• URL: http://arxiv.org/abs/2003.12125v1
• Date: Thu, 26 Mar 2020 19:47:17 GMT
• Title: SaccadeNet: A Fast and Accurate Object Detector
• Authors: Shiyi Lan, Zhou Ren, Yi Wu, Larry S. Davis, Gang Hua
• Abstract summary: We propose a fast and accurate object detector called textitSaccadeNet. It contains four main modules, the cenam, the coram, the atm, and the aggatt, which allows it to attend to different informative object keypoints. Among all the real-time object detectors, %that can run faster than 25 FPS, our SaccadeNet achieves the best detection performance.
• Score: 76.36741299193568
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Object detection is an essential step towards holistic scene understanding. Most existing object detection algorithms attend to certain object areas once and then predict the object locations. However, neuroscientists have revealed that humans do not look at the scene in fixed steadiness. Instead, human eyes move around, locating informative parts to understand the object location. This active perceiving movement process is called \textit{saccade}. %In this paper, Inspired by such mechanism, we propose a fast and accurate object detector called \textit{SaccadeNet}. It contains four main modules, the \cenam, the \coram, the \atm, and the \aggatt, which allows it to attend to different informative object keypoints, and predict object locations from coarse to fine. The \coram~is used only during training to extract more informative corner features which brings free-lunch performance boost. On the MS COCO dataset, we achieve the performance of 40.4\% mAP at 28 FPS and 30.5\% mAP at 118 FPS. Among all the real-time object detectors, %that can run faster than 25 FPS, our SaccadeNet achieves the best detection performance, which demonstrates the effectiveness of the proposed detection mechanism.

Related papers

• Toward Realistic Camouflaged Object Detection: Benchmarks and Method [11.279532701331647]
  Camouflaged object detection (COD) primarily relies on semantic or instance segmentation methods. We propose a camouflage-aware feature refinement (CAFR) strategy to detect camouflaged objects. CAFR fully utilizes a clear perception of the current object within the prior knowledge of large models to assist detectors in deeply understanding the distinctions between background and foreground.
  arXiv  Detail & Related papers  (2025-01-13T13:04:00Z)
• Leveraging Object Priors for Point Tracking [25.030407197192]
  Point tracking is a fundamental problem in computer vision with numerous applications in AR and robotics. We propose a novel objectness regularization approach that guides points to be aware of object priors. Our approach achieves state-of-the-art performance on three point tracking benchmarks.
  arXiv  Detail & Related papers  (2024-09-09T16:48:42Z)
• What You See Is What You Detect: Towards better Object Densification in 3D detection [2.3436632098950456]
  The widely-used full-shape completion approach actually leads to a higher error-upper bound especially for far away objects and small objects like pedestrians. We introduce a visible part completion method that requires only 11.3% of the prediction points that previous methods generate. To recover the dense representation, we propose a mesh-deformation-based method to augment the point set associated with visible foreground objects.
  arXiv  Detail & Related papers  (2023-10-27T01:46:37Z)
• SalienDet: A Saliency-based Feature Enhancement Algorithm for Object Detection for Autonomous Driving [160.57870373052577]
  We propose a saliency-based OD algorithm (SalienDet) to detect unknown objects. Our SalienDet utilizes a saliency-based algorithm to enhance image features for object proposal generation. We design a dataset relabeling approach to differentiate the unknown objects from all objects in training sample set to achieve Open-World Detection.
  arXiv  Detail & Related papers  (2023-05-11T16:19:44Z)
• DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and Tracking [67.34803048690428]
  We propose to model Dynamic Objects in RecurrenT (DORT) to tackle this problem. DORT extracts object-wise local volumes for motion estimation that also alleviates the heavy computational burden. It is flexible and practical that can be plugged into most camera-based 3D object detectors.
  arXiv  Detail & Related papers  (2023-03-29T12:33:55Z)
• Boundary-Guided Camouflaged Object Detection [20.937071658007255]
  We propose a novel boundary-guided network (BGNet) for camouflaged object detection. Our method explores valuable and extra object-related edge semantics to guide representation learning of COD. Our method promotes camouflaged object detection of accurate boundary localization.
  arXiv  Detail & Related papers  (2022-07-02T10:48:35Z)
• Object Manipulation via Visual Target Localization [64.05939029132394]
  Training agents to manipulate objects, poses many challenges. We propose an approach that explores the environment in search for target objects, computes their 3D coordinates once they are located, and then continues to estimate their 3D locations even when the objects are not visible. Our evaluations show a massive 3x improvement in success rate over a model that has access to the same sensory suite.
  arXiv  Detail & Related papers  (2022-03-15T17:59:01Z)
• A Fast Location Algorithm for Very Sparse Point Clouds Based on Object Detection [0.0]
  We propose an algorithm which can quickly locate the target object through image object detection in the circumstances of having very sparse feature points. We conduct the experiment in a manually designed scene by holding a smartphone and the results represent high positioning speed and accuracy of our method.
  arXiv  Detail & Related papers  (2021-10-21T05:17:48Z)
• Analysis of voxel-based 3D object detection methods efficiency for real-time embedded systems [93.73198973454944]
  Two popular voxel-based 3D object detection methods are studied in this paper. Our experiments show that these methods mostly fail to detect distant small objects due to the sparsity of the input point clouds at large distances. Our findings suggest that a considerable part of the computations of existing methods is focused on locations of the scene that do not contribute with successful detection.
  arXiv  Detail & Related papers  (2021-05-21T12:40:59Z)
• Location-Sensitive Visual Recognition with Cross-IOU Loss [177.86369890708457]
  This paper proposes a unified solution named location-sensitive network (LSNet) for object detection, instance segmentation, and pose estimation. Based on a deep neural network as the backbone, LSNet predicts an anchor point and a set of landmarks which together define the shape of the target object.
  arXiv  Detail & Related papers  (2021-04-11T02:17:14Z)
• 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)

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.