Explaining Object Detectors via Collective Contribution of Pixels

• URL: http://arxiv.org/abs/2412.00666v1
• Date: Sun, 01 Dec 2024 04:04:32 GMT
• Title: Explaining Object Detectors via Collective Contribution of Pixels
• Authors: Toshinori Yamauchi, Hiroshi Kera, Kazuhiko Kawamoto,
• Abstract summary: We propose a method for object detectors that considers the collective contribution of multiple pixels. Our approach leverages game-theoretic concepts, specifically Shapley values and interactions, to provide explanations.
• Score: 5.2980803808373516
• License:
• Abstract: Visual explanations for object detectors are crucial for enhancing their reliability. Since object detectors identify and localize instances by assessing multiple features collectively, generating explanations that capture these collective contributions is critical. However, existing methods focus solely on individual pixel contributions, ignoring the collective contribution of multiple pixels. To address this, we proposed a method for object detectors that considers the collective contribution of multiple pixels. Our approach leverages game-theoretic concepts, specifically Shapley values and interactions, to provide explanations. These explanations cover both bounding box generation and class determination, considering both individual and collective pixel contributions. Extensive quantitative and qualitative experiments demonstrate that the proposed method more accurately identifies important regions in detection results compared to current state-of-the-art methods. The code will be publicly available soon.

Related papers

• Classification Committee for Active Deep Object Detection [24.74839931613233]
  We propose a classification committee for active deep object detection method. The committee selects the most informative images according to their uncertainty values. We show that our method outperforms the state-of-the-art active learning methods.
  arXiv  Detail & Related papers  (2023-08-16T16:31:36Z)
• 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)
• BoxMask: Revisiting Bounding Box Supervision for Video Object Detection [11.255962936937744]
  We propose BoxMask, which learns discriminative representations by incorporating class-aware pixel-level information. The proposed module can be effortlessly integrated into any region-based detector to boost detection.
  arXiv  Detail & Related papers  (2022-10-12T08:25:27Z)
• LEAD: Self-Supervised Landmark Estimation by Aligning Distributions of Feature Similarity [49.84167231111667]
  Existing works in self-supervised landmark detection are based on learning dense (pixel-level) feature representations from an image. We introduce an approach to enhance the learning of dense equivariant representations in a self-supervised fashion. We show that having such a prior in the feature extractor helps in landmark detection, even under drastically limited number of annotations.
  arXiv  Detail & Related papers  (2022-04-06T17:48:18Z)
• Disentangle Saliency Detection into Cascaded Detail Modeling and Body Filling [68.73040261040539]
  We propose to decompose the saliency detection task into two cascaded sub-tasks, emphi.e., detail modeling and body filling. Specifically, the detail modeling focuses on capturing the object edges by supervision of explicitly decomposed detail label. The body filling learns the body part which will be filled into the detail map to generate more accurate saliency map.
  arXiv  Detail & Related papers  (2022-02-08T19:33:02Z)
• 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)
• Unsupervised Part Discovery from Contrastive Reconstruction [90.88501867321573]
  The goal of self-supervised visual representation learning is to learn strong, transferable image representations. We propose an unsupervised approach to object part discovery and segmentation. Our method yields semantic parts consistent across fine-grained but visually distinct categories.
  arXiv  Detail & Related papers  (2021-11-11T17:59:42Z)
• Multi-view Contrastive Coding of Remote Sensing Images at Pixel-level [5.64497799927668]
  A pixel-wise contrastive approach based on an unlabeled multi-view setting is proposed to overcome this limitation. A pseudo-Siamese ResUnet is trained to learn a representation that aims to align features from the shifted positive pairs. Results demonstrate both improvements in efficiency and accuracy over the state-of-the-art multi-view contrastive methods.
  arXiv  Detail & Related papers  (2021-05-18T13:28:46Z)
• 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)
• 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)
• Object condensation: one-stage grid-free multi-object reconstruction in physics detectors, graph and image data [0.0]
  A new object condensation method is proposed for detector signals. The method is based on non-image-like data structures, such as graphs and point clouds. It is applied to a simple object classification problem in images and used to reconstruct multiple particles from detector signals.
  arXiv  Detail & Related papers  (2020-02-10T09:04:02Z)

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.