# Dynamic-Net: Tuning the Objective Without Re-training for Synthesis Tasks

arXiv: https://arxiv.org/abs/1811.08760 · HTML: https://mlsanity.com/paper/1811.08760/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2018.

## Built on by (most cited first, 9 of 9)

- [A Theory of the Distortion-Perception Tradeoff in Wasserstein Space](https://mlsanity.com/paper/2107.02555/) (2021)
- [Pareto Set Learning for Expensive Multi-Objective Optimization](https://mlsanity.com/paper/2210.08495/) (2022)
- [Perception-Distortion Balanced ADMM Optimization for Single-Image Super-Resolution](https://mlsanity.com/paper/2208.03324/) (2022)
- [Very Lightweight Photo Retouching Network with Conditional Sequential Modulation](https://mlsanity.com/paper/2104.06279/) (2021)
- [Flexible Style Image Super-Resolution using Conditional Objective](https://mlsanity.com/paper/2201.04898/) (2022)
- [Hypernetwork-Based Adaptive Image Restoration](https://mlsanity.com/paper/2206.05970/) (2022)
- [Tunable Convolutions with Parametric Multi-Loss Optimization](https://mlsanity.com/paper/2304.00898/) (2023)
- [Adaptive Network Combination for Single-Image Reflection Removal: A Domain Generalization Perspective](https://mlsanity.com/paper/2204.01505/) (2022)
- [Contrastive Monotonic Pixel-Level Modulation](https://mlsanity.com/paper/2207.11517/) (2022)

## Abstract (arXiv)

One of the key ingredients for successful optimization of modern CNNs is identifying a suitable objective. To date, the objective is fixed a-priori at training time, and any variation to it requires re-training a new network. In this paper we present a first attempt at alleviating the need for re-training. Rather than fixing the network at training time, we train a "Dynamic-Net" that can be modified at inference time. Our approach considers an "objective-space" as the space of all linear combinations of two objectives, and the Dynamic-Net is emulating the traversing of this objective-space at test-time, without any further training. We show that this upgrades pre-trained networks by providing an out-of-learning extension, while maintaining the performance quality. The solution we propose is fast and allows a user to interactively modify the network, in real-time, in order to obtain the result he/she desires. We show the benefits of such an approach via several different applications.