paper-with-me

Papers

Convolutional Neural Networks Applied to House Numbers Digit Classification

2012-04-18 · Pierre Sermanet, Soumith Chintala, Yann Lecun

We classify digits of real-world house numbers using convolutional neural networks (ConvNets). ConvNets are hierarchical feature learning neural networks whose structure is biologically inspired. Unlike many popular vision approaches that are hand-designed, ConvNets can automatically learn a unique set of features optimized for a given task. We augmented the traditional ConvNet architecture by learning multi-stage features and by using Lp pooling and establish a new state-of-the-art of 94.85% accuracy on the SVHN dataset (45.2% error improvement). Furthermore, we analyze the benefits of different pooling methods and multi-stage features in ConvNets. The source code and a tutorial are available at eblearn.sf.net.

📄 PDF Abstract BibTeX arXiv:1204.3968

Code (2)

Factotum8/test_task_street_view_house_numbers tf
Pek20180909/SVHN tf

Tasks

ClassificationGeneral Classification

Similar Papers 제목 키워드 기반

CE-Dedup: Cost-Effective Convolutional Neural Nets Training based on Image Deduplication

2021-08-23 · Xuan Li, Liqiong Chang, Xue Liu

Attributed to the ever-increasing large image datasets, Convolutional Neural Networks (CNNs) have become popular for vision-based tasks. It is generally admirable to have larger-sized datasets for higher network training…

image-classificationImage Classification

Does human speech follow Benford's Law?

2022-03-24 · Leo Hsu, Visar Berisha

Researchers have observed that the frequencies of leading digits in many man-made and naturally occurring datasets follow a logarithmic curve, with digits that start with the number 1 accounting for $\sim 30\%$ of all nu…

Winner-Take-All Autoencoders

2014-09-09 · NeurIPS 2015 12 · Alireza Makhzani, Brendan Frey

In this paper, we propose a winner-take-all method for learning hierarchical sparse representations in an unsupervised fashion. We first introduce fully-connected winner-take-all autoencoders which use mini-batch statist…

All

Recurrent Attention Models with Object-centric Capsule Representation for Multi-object Recognition

2021-10-11 · Hossein Adeli, Seoyoung Ahn, Gregory Zelinsky

The visual system processes a scene using a sequence of selective glimpses, each driven by spatial and object-based attention. These glimpses reflect what is relevant to the ongoing task and are selected through recurren…

DecoderObjectObject Recognition

The SVHN Dataset Is Deceptive for Probabilistic Generative Models Due to a Distribution Mismatch

2023-10-30 · Tim Z. Xiao, Johannes Zenn, Robert Bamler

The Street View House Numbers (SVHN) dataset is a popular benchmark dataset in deep learning. Originally designed for digit classification tasks, the SVHN dataset has been widely used as a benchmark for various other tas…

Classification