Addressing Visual Search in Open and Closed Set Settings

• URL: http://arxiv.org/abs/2012.06509v2
• Date: Wed, 14 Apr 2021 21:43:19 GMT
• Title: Addressing Visual Search in Open and Closed Set Settings
• Authors: Nathan Drenkow, Philippe Burlina, Neil Fendley, Onyekachi Odoemene, Jared Markowitz
• Abstract summary: We present a method for predicting pixel-level objectness from a low resolution gist image. We then use to select regions for performing object detection locally at high resolution. Second, we propose a novel strategy for open-set visual search that seeks to find all instances of a target class which may be previously unseen.
• Score: 8.928169373673777
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Searching for small objects in large images is a task that is both challenging for current deep learning systems and important in numerous real-world applications, such as remote sensing and medical imaging. Thorough scanning of very large images is computationally expensive, particularly at resolutions sufficient to capture small objects. The smaller an object of interest, the more likely it is to be obscured by clutter or otherwise deemed insignificant. We examine these issues in the context of two complementary problems: closed-set object detection and open-set target search. First, we present a method for predicting pixel-level objectness from a low resolution gist image, which we then use to select regions for performing object detection locally at high resolution. This approach has the benefit of not being fixed to a predetermined grid, thereby requiring fewer costly high-resolution glimpses than existing methods. Second, we propose a novel strategy for open-set visual search that seeks to find all instances of a target class which may be previously unseen and is defined by a single image. We interpret both detection problems through a probabilistic, Bayesian lens, whereby the objectness maps produced by our method serve as priors in a maximum-a-posteriori approach to the detection step. We evaluate the end-to-end performance of both the combination of our patch selection strategy with this target search approach and the combination of our patch selection strategy with standard object detection methods. Both elements of our approach are seen to significantly outperform baseline strategies.

Related papers

• A Coarse to Fine Framework for Object Detection in High Resolution Image [8.316322664637537]
  Current approaches of object detection seldom consider detecting tiny object or the large scale variance problem in high resolution images. We introduce a simple yet efficient approach that improves accuracy of object detection especially for small objects and large scale variance scene. Our approach can make good use of the sparsity of the objects and the information in high-resolution image, thereby making the detection more efficient.
  arXiv  Detail & Related papers  (2023-03-02T13:04:33Z)
• Focus-and-Detect: A Small Object Detection Framework for Aerial Images [1.911678487931003]
  We propose a two-stage object detection framework called "Focus-and-Detect" The first stage generates clusters of objects constituting the focused regions. The second stage, which is also an object detector network, predicts objects within the focal regions. Results indicate that the proposed two-stage framework achieves an AP score of 42.06 on VisDrone validation dataset.
  arXiv  Detail & Related papers  (2022-03-24T10:43:56Z)
• Hybrid Optimized Deep Convolution Neural Network based Learning Model for Object Detection [0.0]
  Object identification is one of the most fundamental and difficult issues in computer vision. In recent years, deep learning-based object detection techniques have grabbed the public's interest. In this study, a unique deep learning classification technique is used to create an autonomous object detecting system. The suggested framework has a detection accuracy of 0.9864, which is greater than current techniques.
  arXiv  Detail & Related papers  (2022-03-02T04:39:37Z)
• You Better Look Twice: a new perspective for designing accurate detectors with reduced computations [56.34005280792013]
  BLT-net is a new low-computation two-stage object detection architecture. It reduces computations by separating objects from background using a very lite first-stage. Resulting image proposals are then processed in the second-stage by a highly accurate model.
  arXiv  Detail & Related papers  (2021-07-21T12:39:51Z)
• A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection [56.82077636126353]
  We take advantage of object-centric images to improve object detection in scene-centric images. We present a simple yet surprisingly effective framework to do so. Our approach can improve the object detection (and instance segmentation) accuracy of rare objects by 50% (and 33%) relatively.
  arXiv  Detail & Related papers  (2021-02-17T17:27:21Z)
• 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)
• POMP: Pomcp-based Online Motion Planning for active visual search in indoor environments [89.43830036483901]
  We focus on the problem of learning an optimal policy for Active Visual Search (AVS) of objects in known indoor environments with an online setup. Our POMP method uses as input the current pose of an agent and a RGB-D frame. We validate our method on the publicly available AVD benchmark, achieving an average success rate of 0.76 with an average path length of 17.1.
  arXiv  Detail & Related papers  (2020-09-17T08:23:50Z)
• Tasks Integrated Networks: Joint Detection and Retrieval for Image Search [99.49021025124405]
  In many real-world searching scenarios (e.g., video surveillance), the objects are seldom accurately detected or annotated. We first introduce an end-to-end Integrated Net (I-Net), which has three merits. We further propose an improved I-Net, called DC-I-Net, which makes two new contributions.
  arXiv  Detail & Related papers  (2020-09-03T03:57:50Z)
• Rethinking of the Image Salient Object Detection: Object-level Semantic Saliency Re-ranking First, Pixel-wise Saliency Refinement Latter [62.26677215668959]
  We propose a lightweight, weakly supervised deep network to coarsely locate semantically salient regions. We then fuse multiple off-the-shelf deep models on these semantically salient regions as the pixel-wise saliency refinement. Our method is simple yet effective, which is the first attempt to consider the salient object detection mainly as an object-level semantic re-ranking problem.
  arXiv  Detail & Related papers  (2020-08-10T07:12:43Z)
• Toward unsupervised, multi-object discovery in large-scale image collections [26.39475298878971]
  This paper builds on the optimization approach of Vo et al. We propose a novel saliency-based region proposal algorithm. We exploit the inherent hierarchical structure of proposals as an effective regularizer.
  arXiv  Detail & Related papers  (2020-07-06T11:43:47Z)
• Localizing Grouped Instances for Efficient Detection in Low-Resource Scenarios [27.920304852537534]
  We propose a novel flexible detection scheme that efficiently adapts to variable object sizes and densities. We rely on a sequence of detection stages, each of which has the ability to predict groups of objects as well as individuals. We report experimental results on two aerial image datasets, and show that the proposed method is as accurate yet computationally more efficient than standard single-shot detectors.
  arXiv  Detail & Related papers  (2020-04-27T07:56:53Z)

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.