paper-with-me

Papers

ODMTCNet: An Interpretable Multi-view Deep Neural Network Architecture for Image Feature Representation

2021-10-28 · Lei Gao, Zheng Guo, Ling Guan

This work proposes an interpretable multi-view deep neural network architecture, namely optimal discriminant multi-view tensor convolutional network (ODMTCNet), by integrating statistical machine learning (SML) principles with the deep neural network (DNN) architecture.

📄 PDF Abstract BibTeX arXiv:2110.14830

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine Learning

Similar Papers 제목 키워드 기반

Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representation

2020-04-05 · CVPR 2020 6 · Edoardo Remelli, Shangchen Han, Sina Honari, Pascal Fua 외

We present a lightweight solution to recover 3D pose from multi-view images captured with spatially calibrated cameras. Building upon recent advances in interpretable representation learning, we exploit 3D geometry to fu…

3D geometry3D Human Pose Estimation3D Pose EstimationGPU+2

Graphical Design of Interpretable Architectures

2026-08-19 · Pietro Barbiero arxiv

Designing, implementing, and comparing interpretable architectures requires a formal language to represent them. The most common representations fall short in one of two ways. Symbolic equations give no global view of an…

Multiview Manifold Evidential Fusion for PolSAR Image Classification

2025-10-13 · Junfei Shi, Haojia Zhang, Haiyan Jin, Junhuai Li 외 arxiv

Polarimetric Synthetic Aperture Radar (PolSAR) covariance matrices and their extracted multi-features - such as scattering angle, entropy, texture, and boundary descriptors - provide complementary and physically interpre…

Image ClassificationMetric Learning

Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering

2020-10-18 · ICLR 2021 1 · Yuxuan Zhang, Wenzheng Chen, Huan Ling, Jun Gao 외

Differentiable rendering has paved the way to training neural networks to perform "inverse graphics" tasks such as predicting 3D geometry from monocular photographs. To train high performing models, most of the current a…

3D geometryNeural Rendering

RAPID: A Reproducible Multi-Agent Pipeline for Interpretable Disaster Damage Assessment from Satellite and Street-View Imagery

2026-06-20 · Yifan Yang, Wenjing Gong, Kaili Zhang, Lei Zou 외 arxiv

Due to the increasing frequency and intensity of extreme climate events, there is a clear demand for intelligent, scalable, and autonomous approaches to disaster damage assessment. Existing methods, largely based on supe…

severity predictionImage Restoration