paper-with-me

홈 › Papers

Max-Margin Boltzmann Machines for Object Segmentation

2014-06-01 · CVPR 2014 6 · Jimei Yang, Simon Safar, Ming-Hsuan Yang

We present Max-Margin Boltzmann Machines (MMBMs) for object segmentation. MMBMs are essentially a class of Conditional Boltzmann Machines that model the joint distribution of hidden variables and output labels conditioned on input observations. In addition to image-to-label connections, we build direct image-to-hidden connections to facilitate global shape prediction, and thus derive a simple Iterated Conditional Modes algorithm for efficient maximum a posteriori inference. We formulate a max-margin objective function for discriminative training, and analyze the effects of different margin functions on learning. We evaluate MMBMs using three datasets against state-of-the-art methods to demonstrate the strength of the proposed algorithms.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

ObjectSemantic Segmentation

Similar Papers 제목 키워드 기반

What is (missing or wrong) in the scene? A Hybrid Deep Boltzmann Machine For Contextualized Scene Modeling

2017-10-16 · İlker Bozcan, Yağmur Oymak, İdil Zeynep Alemdar, Sinan Kalkan

Scene models allow robots to reason about what is in the scene, what else should be in it, and what should not be in it. In this paper, we propose a hybrid Boltzmann Machine (BM) for scene modeling where relations betwee…

General ClassificationScene Classification

Boltzmann Encoded Adversarial Machines

2018-04-23 · Charles K. Fisher, Aaron M. Smith, Jonathan R. Walsh

Restricted Boltzmann Machines (RBMs) are a class of generative neural network that are typically trained to maximize a log-likelihood objective function. We argue that likelihood-based training strategies may fail becaus…

Defence against adversarial attacks using classical and quantum-enhanced Boltzmann machines

2020-12-21 · Aidan Kehoe, Peter Wittek, Yanbo Xue, Alejandro Pozas-Kerstjens

We provide a robust defence to adversarial attacks on discriminative algorithms. Neural networks are naturally vulnerable to small, tailored perturbations in the input data that lead to wrong predictions. On the contrary…

Generative training of quantum Boltzmann machines with hidden units

2019-05-23 · Nathan Wiebe, Leonard Wossnig

In this article we provide a method for fully quantum generative training of quantum Boltzmann machines with both visible and hidden units while using quantum relative entropy as an objective. This is significant because…

Transductive Boltzmann Machines

2018-05-21 · Mahito Sugiyama, Koji Tsuda, Hiroyuki Nakahara

We present transductive Boltzmann machines (TBMs), which firstly achieve transductive learning of the Gibbs distribution. While exact learning of the Gibbs distribution is impossible by the family of existing Boltzmann m…

Transductive Learning