# MIDAS: Mosaic Input-Specific Differentiable Architecture Search

arXiv: https://arxiv.org/abs/2602.17700 · HTML: https://mlsanity.com/paper/2602.17700/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 38 references that are in the map.
- First posted on arXiv 6 Feb 2026.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search](https://mlsanity.com/paper/1812.03443/) (2018)
- [NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search](https://mlsanity.com/paper/2001.00326/) (2020)
- [Recurrent Models of Visual Attention](https://mlsanity.com/paper/1406.6247/) (2014)
- [SNAS: Stochastic Neural Architecture Search](https://mlsanity.com/paper/1812.09926/) (2018)
- [PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search](https://mlsanity.com/paper/1907.05737/) (2019)
- [Searching for A Robust Neural Architecture in Four GPU Hours](https://mlsanity.com/paper/1910.04465/) (2019)
- [Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation](https://mlsanity.com/paper/1904.12760/) (2019)
- [Understanding and Robustifying Differentiable Architecture Search](https://mlsanity.com/paper/1909.09656/) (2019)
- [Evaluating the Search Phase of Neural Architecture Search](https://mlsanity.com/paper/1902.08142/) (2019)
- [Stabilizing Differentiable Architecture Search via Perturbation-based Regularization](https://mlsanity.com/paper/2002.05283/) (2020)
- [Rethinking Architecture Selection in Differentiable NAS](https://mlsanity.com/paper/2108.04392/) (2021)
- [DARTS-: Robustly Stepping out of Performance Collapse Without Indicators](https://mlsanity.com/paper/2009.01027/) (2020)
- [NAS evaluation is frustratingly hard](https://mlsanity.com/paper/1912.12522/) (2019)
- [β-DARTS: Beta-Decay Regularization for Differentiable Architecture Search](https://mlsanity.com/paper/2203.01665/) (2022)
- [Best Practices for Scientific Research on Neural Architecture Search](https://mlsanity.com/paper/1909.02453/) (2019)
- [iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients](https://mlsanity.com/paper/2106.10784/) (2021)
- [Progressive DARTS: Bridging the Optimization Gap for NAS in the Wild](https://mlsanity.com/paper/1912.10952/) (2019)
- [DCNAS: Densely Connected Neural Architecture Search for Semantic Image Segmentation](https://mlsanity.com/paper/2003.11883/) (2020)
- [DOTS: Decoupling Operation and Topology in Differentiable Architecture Search](https://mlsanity.com/paper/2010.00969/) (2020)
- [InstaNAS: Instance-aware Neural Architecture Search](https://mlsanity.com/paper/1811.10201/) (2018)
- [Partial Connection Based on Channel Attention for Differentiable Neural Architecture Search](https://mlsanity.com/paper/2208.00791/) (2022)

## Abstract (arXiv)

Differentiable Neural Architecture Search (NAS) provides efficient, gradient-based methods for automatically designing neural networks, yet its adoption remains limited in practice. We present MIDAS, a novel approach that modernizes DARTS by replacing static architecture parameters with dynamic, input-specific parameters computed via self-attention. To improve robustness, MIDAS (i) localizes the architecture selection by computing it separately for each spatial patch of the activation map, and (ii) introduces a parameter-free, topology-aware search space that models node connectivity and simplifies selecting the two incoming edges per node. We evaluate MIDAS on the DARTS, NAS-Bench-201, and RDARTS search spaces. In DARTS, it reaches 97.42% top-1 on CIFAR-10 and 83.38% on CIFAR-100. In NAS-Bench-201, it consistently finds globally optimal architectures. In RDARTS, it sets the state of the art on two of four search spaces on CIFAR-10. We further analyze why MIDAS works, showing that patchwise attention improves discrimination among candidate operations, and the resulting input-specific parameter distributions are class-aware and predominantly unimodal, providing reliable guidance for decoding.