paper-with-me

홈 › Papers

Classification of Occluded Objects using Fast Recurrent Processing

2015-05-06 · Ozgur Yilmaz

Recurrent neural networks are powerful tools for handling incomplete data problems in computer vision, thanks to their significant generative capabilities. However, the computational demand for these algorithms is too high to work in real time, without specialized hardware or software solutions. In this paper, we propose a framework for augmenting recurrent processing capabilities into a feedforward network without sacrificing much from computational efficiency. We assume a mixture model and generate samples of the last hidden layer according to the class decisions of the output layer, modify the hidden layer activity using the samples, and propagate to lower layers. For visual occlusion problem, the iterative procedure emulates feedforward-feedback loop, filling-in the missing hidden layer activity with meaningful representations. The proposed algorithm is tested on a widely used dataset, and shown to achieve 2$\times$ improvement in classification accuracy for occluded objects. When compared to Restricted Boltzmann Machines, our algorithm shows superior performance for occluded object classification.

📄 PDF Abstract BibTeX arXiv:1505.01350

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationComputational EfficiencyGeneral Classification

Methods 이 논문이 사용한 방법론

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…

Similar Papers 제목 키워드 기반

Recurrent Feedback Improves Recognition of Partially Occluded Objects

2021-04-21 · Markus Roland Ernst, Jochen Triesch, Thomas Burwick

Recurrent connectivity in the visual cortex is believed to aid object recognition for challenging conditions such as occlusion. Here we investigate if and how artificial neural networks also benefit from recurrence. We c…

ObjectObject Recognition

Recurrent Connectivity Aids Recognition of Partly Occluded Objects

2019-09-12 · Markus Roland Ernst, Jochen Triesch, Thomas Burwick

Feedforward convolutional neural networks are the prevalent model of core object recognition. For challenging conditions, such as occlusion, neuroscientists believe that the recurrent connectivity in the visual cortex ai…

ObjectObject Recognition

Recurrent computations for visual pattern completion

2017-06-07 · Hanlin Tang, Martin Schrimpf, Bill Lotter, Charlotte Moerman 외

Making inferences from partial information constitutes a critical aspect of cognition. During visual perception, pattern completion enables recognition of poorly visible or occluded objects. We combined psychophysics, ph…

Image Classification

Long-Term Occupancy Grid Prediction Using Recurrent Neural Networks

2018-09-11 · Marcel Schreiber, Stefan Hoermann, Klaus Dietmayer

We tackle the long-term prediction of scene evolution in a complex downtown scenario for automated driving based on Lidar grid fusion and recurrent neural networks (RNNs). A bird's eye view of the scene, including occupa…

Prediction

Compositional Convolutional Neural Networks: A Deep Architecture with Innate Robustness to Partial Occlusion

2020-03-10 · CVPR 2020 6 · Adam Kortylewski, Ju He, Qing Liu, Alan Yuille

Recent findings show that deep convolutional neural networks (DCNNs) do not generalize well under partial occlusion. Inspired by the success of compositional models at classifying partially occluded objects, we propose t…

General Classification