# InstaNAS: Instance-aware Neural Architecture Search

arXiv: https://arxiv.org/abs/1811.10201 · HTML: https://mlsanity.com/paper/1811.10201/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2018.

## Built on by (most cited first, 13 of 13)

- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [A Comprehensive Survey on Hardware-Aware Neural Architecture Search](https://mlsanity.com/paper/2101.09336/) (2021)
- [Computation-efficient Deep Learning for Computer Vision: A Survey](https://mlsanity.com/paper/2308.13998/) (2023)
- [Boost Test-Time Performance with Closed-Loop Inference](https://mlsanity.com/paper/2203.10853/) (2022)
- [Collaboration of Experts: Achieving 80% Top-1 Accuracy on ImageNet with 100M FLOPs](https://mlsanity.com/paper/2107.03815/) (2021)
- [Searching Meta Reasoning Skeleton to Guide LLM Reasoning](https://mlsanity.com/paper/2510.04116/) (2025)
- [Rapid Elastic Architecture Search under Specialized Classes and Resource Constraints](https://mlsanity.com/paper/2108.01224/) (2021)
- [M-FasterSeg: An Efficient Semantic Segmentation Network Based on Neural Architecture Search](https://mlsanity.com/paper/2112.07918/) (2021)
- [An Intelligent End-to-End Neural Architecture Search Framework for Electricity Forecasting Model Development](https://mlsanity.com/paper/2203.13563/) (2022)
- [A Survey on Multi-Objective Neural Architecture Search](https://mlsanity.com/paper/2307.09099/) (2023)
- [Rule Based Learning with Dynamic (Graph) Neural Networks](https://mlsanity.com/paper/2406.09954/) (2024)
- [MIDAS: Mosaic Input-Specific Differentiable Architecture Search](https://mlsanity.com/paper/2602.17700/) (2026)
- [HERCULES: Hardware-Efficient, Robust, Continual Learning Neural Architecture Search](https://mlsanity.com/paper/2605.04103/) (2026)

## Abstract (arXiv)

Conventional Neural Architecture Search (NAS) aims at finding a single architecture that achieves the best performance, which usually optimizes task related learning objectives such as accuracy. However, a single architecture may not be representative enough for the whole dataset with high diversity and variety. Intuitively, electing domain-expert architectures that are proficient in domain-specific features can further benefit architecture related objectives such as latency. In this paper, we propose InstaNAS---an instance-aware NAS framework---that employs a controller trained to search for a "distribution of architectures" instead of a single architecture; This allows the model to use sophisticated architectures for the difficult samples, which usually comes with large architecture related cost, and shallow architectures for those easy samples. During the inference phase, the controller assigns each of the unseen input samples with a domain expert architecture that can achieve high accuracy with customized inference costs. Experiments within a search space inspired by MobileNetV2 show InstaNAS can achieve up to 48.8% latency reduction without compromising accuracy on a series of datasets against MobileNetV2.