FFAM: Feature Factorization Activation Map for Explanation of 3D Detectors

• URL: http://arxiv.org/abs/2405.12601v1
• Date: Tue, 21 May 2024 08:55:10 GMT
• Title: FFAM: Feature Factorization Activation Map for Explanation of 3D Detectors
• Authors: Shuai Liu, Boyang Li, Zhiyu Fang, Mingyue Cui, Kai Huang,
• Abstract summary: We propose a feature factorization activation map (FFAM) to generate high-quality visual explanations for 3D detectors. To achieve object-specific visual explanations, we refine the global visual explanation using the feature gradient of a target object. We qualitatively and quantitatively analyze FFAM with multiple detectors on several datasets.
• Score: 9.143384495617722
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LiDAR-based 3D object detection has made impressive progress recently, yet most existing models are black-box, lacking interpretability. Previous explanation approaches primarily focus on analyzing image-based models and are not readily applicable to LiDAR-based 3D detectors. In this paper, we propose a feature factorization activation map (FFAM) to generate high-quality visual explanations for 3D detectors. FFAM employs non-negative matrix factorization to generate concept activation maps and subsequently aggregates these maps to obtain a global visual explanation. To achieve object-specific visual explanations, we refine the global visual explanation using the feature gradient of a target object. Additionally, we introduce a voxel upsampling strategy to align the scale between the activation map and input point cloud. We qualitatively and quantitatively analyze FFAM with multiple detectors on several datasets. Experimental results validate the high-quality visual explanations produced by FFAM. The Code will be available at \url{https://github.com/Say2L/FFAM.git}.

Related papers

• VFMM3D: Releasing the Potential of Image by Vision Foundation Model for Monocular 3D Object Detection [80.62052650370416]
  monocular 3D object detection holds significant importance across various applications, including autonomous driving and robotics. In this paper, we present VFMM3D, an innovative framework that leverages the capabilities of Vision Foundation Models (VFMs) to accurately transform single-view images into LiDAR point cloud representations.
  arXiv  Detail & Related papers  (2024-04-15T03:12:12Z)
• OA-BEV: Bringing Object Awareness to Bird's-Eye-View Representation for Multi-Camera 3D Object Detection [78.38062015443195]
  OA-BEV is a network that can be plugged into the BEV-based 3D object detection framework. Our method achieves consistent improvements over the BEV-based baselines in terms of both average precision and nuScenes detection score.
  arXiv  Detail & Related papers  (2023-01-13T06:02:31Z)
• CMR3D: Contextualized Multi-Stage Refinement for 3D Object Detection [57.44434974289945]
  We propose Contextualized Multi-Stage Refinement for 3D Object Detection (CMR3D) framework. Our framework takes a 3D scene as input and strives to explicitly integrate useful contextual information of the scene. In addition to 3D object detection, we investigate the effectiveness of our framework for the problem of 3D object counting.
  arXiv  Detail & Related papers  (2022-09-13T05:26:09Z)
• Label-Guided Auxiliary Training Improves 3D Object Detector [32.96310946612949]
  We propose a Label-Guided auxiliary training method for 3D object detection (LG3D) Our proposed LG3D improves VoteNet by 2.5% and 3.1% mAP on the SUN RGB-D and ScanNetV2 datasets.
  arXiv  Detail & Related papers  (2022-07-24T14:22:21Z)
• Boosting 3D Object Detection via Object-Focused Image Fusion [33.616129400275156]
  We present DeMF, a method to fuse image information into point features. We evaluate our method on the challenging SUN RGB-D dataset.
  arXiv  Detail & Related papers  (2022-07-21T16:32:05Z)
• Boosting 3D Object Detection by Simulating Multimodality on Point Clouds [51.87740119160152]
  This paper presents a new approach to boost a single-modality (LiDAR) 3D object detector by teaching it to simulate features and responses that follow a multi-modality (LiDAR-image) detector. The approach needs LiDAR-image data only when training the single-modality detector, and once well-trained, it only needs LiDAR data at inference. Experimental results on the nuScenes dataset show that our approach outperforms all SOTA LiDAR-only 3D detectors.
  arXiv  Detail & Related papers  (2022-06-30T01:44:30Z)
• OccAM's Laser: Occlusion-based Attribution Maps for 3D Object Detectors on LiDAR Data [8.486063950768694]
  We propose a method to generate attribution maps for 3D object detection in LiDAR point clouds. These maps indicate the importance of each 3D point in predicting the specific objects. We show a detailed evaluation of the attribution maps and demonstrate that they are interpretable and highly informative.
  arXiv  Detail & Related papers  (2022-04-13T18:00:30Z)
• RBGNet: Ray-based Grouping for 3D Object Detection [104.98776095895641]
  We propose the RBGNet framework, a voting-based 3D detector for accurate 3D object detection from point clouds. We propose a ray-based feature grouping module, which aggregates the point-wise features on object surfaces using a group of determined rays. Our model achieves state-of-the-art 3D detection performance on ScanNet V2 and SUN RGB-D with remarkable performance gains.
  arXiv  Detail & Related papers  (2022-04-05T14:42:57Z)
• A Versatile Multi-View Framework for LiDAR-based 3D Object Detection with Guidance from Panoptic Segmentation [9.513467995188634]
  3D object detection using LiDAR data is an indispensable component for autonomous driving systems. We propose a novel multi-task framework that jointly performs 3D object detection and panoptic segmentation.
  arXiv  Detail & Related papers  (2022-03-04T04:57:05Z)
• SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detection [78.90102636266276]
  We propose a novel set abstraction method named Semantics-Augmented Set Abstraction (SASA) Based on the estimated point-wise foreground scores, we then propose a semantics-guided point sampling algorithm to help retain more important foreground points during down-sampling. In practice, SASA shows to be effective in identifying valuable points related to foreground objects and improving feature learning for point-based 3D detection.
  arXiv  Detail & Related papers  (2022-01-06T08:54:47Z)
• VIN: Voxel-based Implicit Network for Joint 3D Object Detection and Segmentation for Lidars [12.343333815270402]
  A unified neural network structure is presented for joint 3D object detection and point cloud segmentation. We leverage rich supervision from both detection and segmentation labels rather than using just one of them.
  arXiv  Detail & Related papers  (2021-07-07T02:16:20Z)

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.