# Fast Neural Network Adaptation via Parameter Remapping and Architecture Search

arXiv: https://arxiv.org/abs/2001.02525 · HTML: https://mlsanity.com/paper/2001.02525/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jan 2020.

## Built on by (most cited first, 16 of 16)

- [Neural Architecture Search: Insights from 1000 Papers](https://mlsanity.com/paper/2301.08727/) (2023)
- [Visual Tuning](https://mlsanity.com/paper/2305.06061/) (2023)
- [Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets](https://mlsanity.com/paper/2107.00860/) (2021)
- [KNAS: Green Neural Architecture Search](https://mlsanity.com/paper/2111.13293/) (2021)
- [Towards Efficient 3D Object Detection with Knowledge Distillation](https://mlsanity.com/paper/2205.15156/) (2022)
- [Adversarial AutoMixup](https://mlsanity.com/paper/2312.11954/) (2023)
- [Neural Architecture Search for Dense Prediction Tasks in Computer Vision](https://mlsanity.com/paper/2202.07242/) (2022)
- [A Study on Knowledge Distillation from Weak Teacher for Scaling Up Pre-trained Language Models](https://mlsanity.com/paper/2305.18239/) (2023)
- [Surrogate-assisted Multi-objective Neural Architecture Search for Real-time Semantic Segmentation](https://mlsanity.com/paper/2208.06820/) (2022)
- [Privacy-preserving Online AutoML for Domain-Specific Face Detection](https://mlsanity.com/paper/2203.08399/) (2022)
- [Breaking the Architecture Barrier: A Method for Efficient Knowledge Transfer Across Networks](https://mlsanity.com/paper/2212.13970/) (2022)
- [AdaSpring: Context-adaptive and Runtime-evolutionary Deep Model Compression for Mobile Applications](https://mlsanity.com/paper/2101.11800/) (2021)
- [AutoAdapt: Automated Segmentation Network Search for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2106.13227/) (2021)
- [Learn to Explore: Meta NAS via Bayesian Optimization Guided Graph Generation](https://mlsanity.com/paper/2508.09467/) (2025)
- [Dynamic Normalization](https://mlsanity.com/paper/2101.06073/) (2021)
- [Neural Architecture Adaptation for Object Detection by Searching Channel Dimensions and Mapping Pre-trained Parameters](https://mlsanity.com/paper/2206.08509/) (2022)

## Abstract (arXiv)

Deep neural networks achieve remarkable performance in many computer vision tasks. Most state-of-the-art (SOTA) semantic segmentation and object detection approaches reuse neural network architectures designed for image classification as the backbone, commonly pre-trained on ImageNet. However, performance gains can be achieved by designing network architectures specifically for detection and segmentation, as shown by recent neural architecture search (NAS) research for detection and segmentation. One major challenge though, is that ImageNet pre-training of the search space representation (a.k.a. super network) or the searched networks incurs huge computational cost. In this paper, we propose a Fast Neural Network Adaptation (FNA) method, which can adapt both the architecture and parameters of a seed network (e.g. a high performing manually designed backbone) to become a network with different depth, width, or kernels via a Parameter Remapping technique, making it possible to utilize NAS for detection/segmentation tasks a lot more efficiently. In our experiments, we conduct FNA on MobileNetV2 to obtain new networks for both segmentation and detection that clearly out-perform existing networks designed both manually and by NAS. The total computation cost of FNA is significantly less than SOTA segmentation/detection NAS approaches: 1737× less than DPC, 6.8× less than Auto-DeepLab and 7.4× less than DetNAS. The code is available at https://github.com/JaminFong/FNA.