Joint Visual Denoising and Classification using Deep Learning

TL;DR

This paper introduces a joint deep learning framework that simultaneously denoises and classifies handwritten images, leveraging shared representations to improve accuracy and image clarity over traditional pipeline methods.

Contribution

It proposes a novel 3-pathway deep architecture for combined visual restoration and recognition, outperforming separate pipelines by at least 20% in classification accuracy.

Findings

Achieves at least 20% better classification accuracy than separate pipelines.

Produces clearer recovered images from noisy handwritten data.

Demonstrates effectiveness on MNIST and USPS datasets with structured noise.

Abstract

Visual restoration and recognition are traditionally addressed in pipeline fashion, i.e. denoising followed by classification. Instead, observing correlations between the two tasks, for example clearer image will lead to better categorization and vice visa, we propose a joint framework for visual restoration and recognition for handwritten images, inspired by advances in deep autoencoder and multi-modality learning. Our model is a 3-pathway deep architecture with a hidden-layer representation which is shared by multi-inputs and outputs, and each branch can be composed of a multi-layer deep model. Thus, visual restoration and classification can be unified using shared representation via non-linear mapping, and model parameters can be learnt via backpropagation. Using MNIST and USPS data corrupted with structured noise, the proposed framework performs at least 20\% better in classification than separate pipelines, as well as clearer recovered images. The noise model and the reproducible source code is available at {\url{https://github.com/ganggit/jointmodel}}.