# Meta Input: How to Leverage Off-the-Shelf Deep Neural Networks

arXiv: https://arxiv.org/abs/2210.13186 · HTML: https://mlsanity.com/paper/2210.13186/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 45 references that are in the map.
- First posted on arXiv 21 Oct 2022.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Deep Visual Domain Adaptation: A Survey](https://mlsanity.com/paper/1802.03601/) (2018)
- [Deep Transfer Learning with Joint Adaptation Networks](https://mlsanity.com/paper/1605.06636/) (2016)
- [Deep Speech 2: End-to-End Speech Recognition in English and Mandarin](https://mlsanity.com/paper/1512.02595/) (2015)
- [Contrastive Adaptation Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1901.00976/) (2019)
- [Semantic Foggy Scene Understanding with Synthetic Data](https://mlsanity.com/paper/1708.07819/) (2017)
- [Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks](https://mlsanity.com/paper/1612.05424/) (2016)
- [Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation](https://mlsanity.com/paper/1803.11365/) (2018)
- [Fixing the train-test resolution discrepancy](https://mlsanity.com/paper/1906.06423/) (2019)
- [Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1607.03516/) (2016)
- [Adversarial Reprogramming of Neural Networks](https://mlsanity.com/paper/1806.11146/) (2018)
- [LipNet: End-to-End Sentence-level Lipreading](https://mlsanity.com/paper/1611.01599/) (2016)
- [On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law](https://mlsanity.com/paper/2005.09241/) (2020)
- [Dynamic Weighted Learning for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2103.13814/) (2021)
- [Cross-modal Adversarial Reprogramming](https://mlsanity.com/paper/2102.07325/) (2021)
- [Deep Transfer Network: Unsupervised Domain Adaptation](https://mlsanity.com/paper/1503.00591/) (2015)
- [Speaker-adaptive Lip Reading with User-dependent Padding](https://mlsanity.com/paper/2208.04498/) (2022)
- [Why Adversarial Reprogramming Works, When It Fails, and How to Tell the Difference](https://mlsanity.com/paper/2108.11673/) (2021)
- [Speaker Adaptive Training using Model Agnostic Meta-Learning](https://mlsanity.com/paper/1910.10605/) (2019)
- [Improved Input Reprogramming for GAN Conditioning](https://mlsanity.com/paper/2201.02692/) (2022)

## Abstract (arXiv)

These days, although deep neural networks (DNNs) have achieved a noticeable progress in a wide range of research area, it lacks the adaptability to be employed in the real-world applications because of the environment discrepancy problem. Such a problem originates from the difference between training and testing environments, and it is widely known that it causes serious performance degradation, when a pretrained DNN model is applied to a new testing environment. Therefore, in this paper, we introduce a novel approach that allows end-users to exploit pretrained DNN models in their own testing environment without modifying the models. To this end, we present a textitmeta input which is an additional input transforming the distribution of testing data to be aligned with that of training data. The proposed meta input can be optimized with a small number of testing data only by considering the relation between testing input data and its output prediction. Also, it does not require any knowledge of the network's internal architecture and modification of its weight parameters. Then, the obtained meta input is added to testing data in order to shift the distribution of testing data to that of originally used training data. As a result, end-users can exploit well-trained models in their own testing environment which can differ from the training environment. We validate the effectiveness and versatility of the proposed meta input by showing the robustness against the environment discrepancy through the comprehensive experiments with various tasks.