paper-with-me

홈 › Papers

Physics Inspired Optimization on Semantic Transfer Features: An Alternative Method for Room Layout Estimation

2017-07-03 · CVPR 2017 7 · Hao Zhao, Ming Lu, Anbang Yao, Yiwen Guo, Yurong Chen, Li Zhang

In this paper, we propose an alternative method to estimate room layouts of cluttered indoor scenes. This method enjoys the benefits of two novel techniques. The first one is semantic transfer (ST), which is: (1) a formulation to integrate the relationship between scene clutter and room layout into convolutional neural networks; (2) an architecture that can be end-to-end trained; (3) a practical strategy to initialize weights for very deep networks under unbalanced training data distribution. ST allows us to extract highly robust features under various circumstances, and in order to address the computation redundance hidden in these features we develop a principled and efficient inference scheme named physics inspired optimization (PIO). PIO's basic idea is to formulate some phenomena observed in ST features into mechanics concepts. Evaluations on public datasets LSUN and Hedau show that the proposed method is more accurate than state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:1707.00383

Code (0)

등록된 구현이 없습니다.

Tasks

Room Layout Estimation

Similar Papers 제목 키워드 기반

Physics-Inspired Deep Learning and Transferable Models for Bridge Scour Prediction

2024-07-01 · Negin Yousefpour, Bo wang

This paper introduces scour physics-inspired neural networks (SPINNs), a hybrid physics-data-driven framework for bridge scour prediction using deep learning. SPINNs integrate physics-based, empirical equations into deep…

Deep LearningDepth EstimationPrediction

Phase Consistent Ecological Domain Adaptation

2020-04-10 · CVPR 2020 6 · Yanchao Yang, Dong Lao, Ganesh Sundaramoorthi, Stefano Soatto

We introduce two criteria to regularize the optimization involved in learning a classifier in a domain where no annotated data are available, leveraging annotated data in a different domain, a problem known as unsupervis…

Domain AdaptationSegmentationSemantic SegmentationUnsupervised Domain Adaptation

Disrupting Semantic and Abstract Features for Better Adversarial Transferability

2025-07-21 · Yuyang Luo, Xiaosen Wang, Zhijin Ge, Yingzhe He arxiv

Adversarial examples pose significant threats to deep neural networks (DNNs), and their property of transferability in the black-box setting has led to the emergence of transfer-based attacks, making it feasible to targe…

Feature Importance

Physics Inspired Hybrid Attention for SAR Target Recognition

2023-09-27 · Zhongling Huang, Chong Wu, Xiwen Yao, Zhicheng Zhao 외

There has been a recent emphasis on integrating physical models and deep neural networks (DNNs) for SAR target recognition, to improve performance and achieve a higher level of physical interpretability. The attributed s…

Feature Importance

Scan, Materialize, Simulate: A Generalizable Framework for Physically Grounded Robot Planning

2025-05-20 · Amine Elhafsi, Daniel Morton, Marco Pavone

Autonomous robots must reason about the physical consequences of their actions to operate effectively in unstructured, real-world environments. We present Scan, Materialize, Simulate (SMS), a unified framework that combi…

Semantic Segmentation