# Minimizing the Effect of Noise and Limited Dataset Size in Image Classification Using Depth Estimation as an Auxiliary Task with Deep Multitask Learning

arXiv: https://arxiv.org/abs/2208.10390 · HTML: https://mlsanity.com/paper/2208.10390/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 19 references that are in the map.
- First posted on arXiv 22 Aug 2022.

## Builds on (most cited first, 10 of 10)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching](https://mlsanity.com/paper/1708.09204/) (2017)
- [DepthTransfer: Depth Extraction from Video Using Non-parametric Sampling](https://mlsanity.com/paper/2001.00987/) (2019)
- [A Large RGB-D Dataset for Semi-supervised Monocular Depth Estimation](https://mlsanity.com/paper/1904.10230/) (2019)
- [MultiDepth: Single-Image Depth Estimation via Multi-Task Regression and Classification](https://mlsanity.com/paper/1907.11111/) (2019)
- [Estimated Depth Map Helps Image Classification](https://mlsanity.com/paper/1709.07077/) (2017)

## Abstract (arXiv)

Generalizability is the ultimate goal of Machine Learning (ML) image classifiers, for which noise and limited dataset size are among the major concerns. We tackle these challenges through utilizing the framework of deep Multitask Learning (dMTL) and incorporating image depth estimation as an auxiliary task. On a customized and depth-augmented derivation of the MNIST dataset, we show a) multitask loss functions are the most effective approach of implementing dMTL, b) limited dataset size primarily contributes to classification inaccuracy, and c) depth estimation is mostly impacted by noise. In order to further validate the results, we manually labeled the NYU Depth V2 dataset for scene classification tasks. As a contribution to the field, we have made the data in python native format publicly available as an open-source dataset and provided the scene labels. Our experiments on MNIST and NYU-Depth-V2 show dMTL improves generalizability of the classifiers when the dataset is noisy and the number of examples is limited.