arXiv:1812.01217
Set Cross Entropy: Likelihood-based Permutation Invariant Loss Function for Probability Distributions
원문 초록
We propose a permutation-invariant loss function designed for the neural networks reconstructing a set of elements without considering the order within its vector representation. Unlike popular approaches for encoding and decoding a set, our work does not rely on a carefully engineered network topology nor by any additional sequential algorithm. The proposed method, Set Cross Entropy, has a natural information-theoretic interpretation and is related to the metrics defined for sets. We evaluate the proposed approach in two object reconstruction tasks and a rule learning task.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
CaLiV: LiDAR-to-Vehicle Calibration of Arbitrary Sensor Setups via Object Reconstruction
HoGS: Unified Near and Far Object Reconstruction via Homogeneous Gaussian Splatting
DQO-MAP: Dual Quadrics Multi-Object mapping with Gaussian Splatting
Convex Hull-based Algebraic Constraint for Visual Quadric SLAM
Inter3D: A Benchmark and Strong Baseline for Human-Interactive 3D Object Reconstruction
View Transformation Robustness for Multi-View 3D Object Reconstruction with Reconstruction Error-Guided View Selection
토론
이 논문과 연결된 포럼 글이 아직 없습니다.