Explaining YOLO: Leveraging Grad-CAM to Explain Object Detections

• URL: http://arxiv.org/abs/2211.12108v1
• Date: Tue, 22 Nov 2022 09:19:13 GMT
• Title: Explaining YOLO: Leveraging Grad-CAM to Explain Object Detections
• Authors: Armin Kirchknopf, Djordje Slijepcevic, Ilkay Wunderlich, Michael Breiter, Johannes Traxler, Matthias Zeppelzauer
• Abstract summary: We show how to integrate Grad-CAM into the model architecture and analyze the results. We show how to compute attribution-based explanations for individual detections and find that the normalization of the results has a great impact on their interpretation.
• Score: 2.0496125856846605
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We investigate the problem of explainability for visual object detectors. Specifically, we demonstrate on the example of the YOLO object detector how to integrate Grad-CAM into the model architecture and analyze the results. We show how to compute attribution-based explanations for individual detections and find that the normalization of the results has a great impact on their interpretation.

Related papers

• Measuring the Impact of Scene Level Objects on Object Detection: Towards Quantitative Explanations of Detection Decisions [1.6385815610837167]
  This paper presents a new black box explainability method for additional verification of object detection models. By comparing the accuracies of a model on test data with and without certain scene level objects, the contributions of these objects to the model's performance becomes clearer.
  arXiv  Detail & Related papers  (2024-01-19T16:21:55Z)
• Weakly-supervised Contrastive Learning for Unsupervised Object Discovery [52.696041556640516]
  Unsupervised object discovery is promising due to its ability to discover objects in a generic manner. We design a semantic-guided self-supervised learning model to extract high-level semantic features from images. We introduce Principal Component Analysis (PCA) to localize object regions.
  arXiv  Detail & Related papers  (2023-07-07T04:03:48Z)
• 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)
• 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)
• Real Time Object Detection System with YOLO and CNN Models: A Review [7.767212366020168]
  This survey is all about YOLO and convolution neural networks (CNN)in the direction of real time object detection. YOLO does generalized object representation more effectively without precision losses than other object detection models. CNN architecture models have the ability to eliminate highlights and identify objects in any given image.
  arXiv  Detail & Related papers  (2022-07-23T11:00:11Z)
• Instance-Aware Observer Network for Out-of-Distribution Object Segmentation [94.73449180972239]
  We extend the approach of ObsNet by harnessing an instance-wise mask prediction. We show that our proposed method accurately disentangles in-distribution objects from Out-Of-Distribution objects on three datasets.
  arXiv  Detail & Related papers  (2022-07-18T17:38:40Z)
• Contrastive Object Detection Using Knowledge Graph Embeddings [72.17159795485915]
  We compare the error statistics of the class embeddings learned from a one-hot approach with semantically structured embeddings from natural language processing or knowledge graphs. We propose a knowledge-embedded design for keypoint-based and transformer-based object detection architectures.
  arXiv  Detail & Related papers  (2021-12-21T17:10:21Z)
• Black-box Explanation of Object Detectors via Saliency Maps [66.745167677293]
  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.
  arXiv  Detail & Related papers  (2020-06-05T02:13:35Z)
• Explain and Improve: LRP-Inference Fine-Tuning for Image Captioning Models [82.3793660091354]
  This paper analyzes the predictions of image captioning models with attention mechanisms beyond visualizing the attention itself. We develop variants of layer-wise relevance propagation (LRP) and gradient-based explanation methods, tailored to image captioning models with attention mechanisms.
  arXiv  Detail & Related papers  (2020-01-04T05:15:11Z)

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.