The enhancement of 3D object detection is pivotal for precise environmental
perception and improved task execution capabilities in autonomous driving.
LiDAR point clouds, offering accurate depth information, serve as a crucial
information for this purpose. Our study focuses on key challenges in 3D target
detection. To tackle the challenge of expanding the receptive field of a 3D
convolutional kernel, we introduce the Dynamic Feature Fusion Module (DFFM).
This module achieves adaptive expansion of the 3D convolutional kernel's
receptive field, balancing the expansion with acceptable computational loads.
This innovation reduces operations, expands the receptive field, and allows the
model to dynamically adjust to different object requirements. Simultaneously,
we identify redundant information in 3D features. Employing the Feature
Selection Module (FSM) quantitatively evaluates and eliminates non-important
features, achieving the separation of output box fitting and feature
extraction. This innovation enables the detector to focus on critical features,
resulting in model compression, reduced computational burden, and minimized
candidate frame interference. Extensive experiments confirm that both DFFM and
FSM not only enhance current benchmarks, particularly in small target
detection, but also accelerate network performance. Importantly, these modules
exhibit effective complementarity.

利用 3D 物体检测、LiDAR 点云、动态特征融合模块和特征选择模块以提高网络性能。

3D 目标检测中的大感受野策略与重要特征提取策略

Large receptive field strategy and important feature extraction strategy  in 3D object detection

Explainable AI offers insights into what factors drive a certain prediction
of a black-box AI system. One popular interpreting approach is through
counterfactual explanations, which go beyond why a system arrives at a certain
decision to further provide suggestions on what a user can do to alter the
original outcome. A counterfactual example must possess plenty of desiderata.
These constraints exist at trade-offs between one and another presenting
radical challenges to existing works. We here propose a stochastic
learning-based framework that effectively balances the counterfactual
trade-offs. The framework consists of a generation and a feature selection
module with complementary roles: the former aims to model the distribution of
valid counterfactuals whereas the latter serves to enforce additional
constraints in a way that allows for differentiable training and amortized
optimization. We demonstrate the effectiveness of our method in generating
actionable and plausible counterfactuals that are more diverse than the
existing methods and particularly more efficient than closest baselines.

通过提出一种基于随机学习的框架和特征选择模块来平衡反事实解释的权衡，本研究在生成可行的反事实解释方面展现了其有效性，并表明其比基线更加多样化和高效。