R(Det)2: Randomized Decision Routing for Object Detection
Ya-Li Li, Shengjin Wang
Abstract
In the paradigm of object detection, the decision head is an important part, which affects detection performance significantly. Yet how to design a high-performance decision head remains to be an open issue. In this paper, we propose a novel approach to combine decision trees and deep neural networks in an end-to-end learning manner for object detection. First, we disentangle the decision choices and prediction values by plugging soft decision trees into neural networks. To facilitate effective learning, we propose randomized decision routing with node selective and associative losses, which can boost the feature representative learning and network decision simultaneously. Second, we develop the decision head for object detection with narrow branches to generate the routing probabilities and masks, for the purpose of obtaining divergent decisions from different nodes. We name this approach as the randomized decision routing for object detection, abbreviated as R(Det)2. Experiments on MS-COCO dataset demonstrate that R(Det)2 is effective to improve the detection performance. Equipped with existing detectors, it achieves 1.4 3.6\% AP improvement.
Create a lesson
Related papers
CiGS: Conduction in Gaussian Splats for Interior Temperature Field from Thermal Images
Liu Zhenyuan, Bharath Seshadri, Bailey Miller et al.
Visual Marking as a Native Reasoning Capability for Multimodal LLMs
Jiazhen Liu, Yanghao Wang, Chaolei Tan et al.
Self-supervised learning for zebrafish embryo phenotype evaluation: Systematic comparison of algorithms, label-efficient classification, and transfer learning
Thomas Lautenschlager, Gaëlle Hayot, Quentin Brassart et al.
EvoMem3D: Adaptive-Depth Temporal Representation Memory for Multi-Camera 3D Detection
Moshe Kimhi, Idan Kligvasser, Yotam Intrator et al.
Ocular Recognition: Interoperability, Multi-Resolution, and Spectrum Challenges
Fabian Stockhardt, Juan E. Tapia, Christoph Busch
AstroPIE-53: Towards Understanding Failure Modes of Human Pose Estimation in Space
Stephanie Käs, Marten Flaig, Lukas Woyke et al.