Black-box Explanation of Object Detectors via Saliency Maps

• URL: http://arxiv.org/abs/2006.03204v2
• Date: Thu, 10 Jun 2021 22:36:13 GMT
• Title: Black-box Explanation of Object Detectors via Saliency Maps
• Authors: Vitali Petsiuk and Rajiv Jain and Varun Manjunatha and Vlad I. Morariu and Ashutosh Mehra and Vicente Ordonez and Kate Saenko
• Abstract summary: We propose D-RISE, a method for generating visual explanations for the predictions of object detectors. We show that D-RISE can be easily applied to different object detectors including one-stage detectors such as YOLOv3 and two-stage detectors such as Faster-RCNN.
• Score: 66.745167677293
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose D-RISE, a method for generating visual explanations for the predictions of object detectors. Utilizing the proposed similarity metric that accounts for both localization and categorization aspects of object detection allows our method to produce saliency maps that show image areas that most affect the prediction. D-RISE can be considered "black-box" in the software testing sense, as it only needs access to the inputs and outputs of an object detector. Compared to gradient-based methods, D-RISE is more general and agnostic to the particular type of object detector being tested, and does not need knowledge of the inner workings of the model. We show that D-RISE can be easily applied to different object detectors including one-stage detectors such as YOLOv3 and two-stage detectors such as Faster-RCNN. We present a detailed analysis of the generated visual explanations to highlight the utilization of context and possible biases learned by object detectors.

Related papers

• Exploring Robust Features for Few-Shot Object Detection in Satellite Imagery [17.156864650143678]
  We develop a few-shot object detector based on a traditional two-stage architecture. A large-scale pre-trained model is used to build class-reference embeddings or prototypes. We perform evaluations on two remote sensing datasets containing challenging and rare objects.
  arXiv  Detail & Related papers  (2024-03-08T15:20:27Z)
• Linear Object Detection in Document Images using Multiple Object Tracking [58.720142291102135]
  Linear objects convey substantial information about document structure. Many approaches can recover some vector representation, but only one closed-source technique introduced in 1994. We propose a framework for accurate instance segmentation of linear objects in document images using Multiple Object Tracking.
  arXiv  Detail & Related papers  (2023-05-26T14:22:03Z)
• ODAM: Gradient-based instance-specific visual explanations for object detection [51.476702316759635]
  gradient-weighted Object Detector Activation Maps (ODAM) ODAM produces heat maps that show the influence of regions on the detector's decision for each predicted attribute. We propose Odam-NMS, which considers the information of the model's explanation for each prediction to distinguish duplicate detected objects.
  arXiv  Detail & Related papers  (2023-04-13T09:20:26Z)
• Open-Vocabulary Point-Cloud Object Detection without 3D Annotation [62.18197846270103]
  The goal of open-vocabulary 3D point-cloud detection is to identify novel objects based on arbitrary textual descriptions. We develop a point-cloud detector that can learn a general representation for localizing various objects. We also propose a novel de-biased triplet cross-modal contrastive learning to connect the modalities of image, point-cloud and text.
  arXiv  Detail & Related papers  (2023-04-03T08:22:02Z)
• DExT: Detector Explanation Toolkit [5.735035463793008]
  State-of-the-art object detectors are treated as black boxes due to their highly non-linear internal computations. We propose an open-source Detector Explanation Toolkit (DExT) which implements a holistic explanation for all detector decisions.
  arXiv  Detail & Related papers  (2022-12-21T23:28:53Z)
• Ensembling object detectors for image and video data analysis [98.26061123111647]
  We propose a method for ensembling the outputs of multiple object detectors for improving detection performance and precision of bounding boxes on image data. We extend it to video data by proposing a two-stage tracking-based scheme for detection refinement.
  arXiv  Detail & Related papers  (2021-02-09T12:38:16Z)
• 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.