# Adaptive Neural Networks for Intelligent Data-Driven Development

arXiv: https://arxiv.org/abs/2502.10603 · HTML: https://mlsanity.com/paper/2502.10603/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 23 references that are in the map.
- First posted on arXiv 14 Feb 2025.

## Builds on (most cited first, 16 of 16)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning](https://mlsanity.com/paper/2203.02053/) (2022)
- [AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One](https://mlsanity.com/paper/2312.06709/) (2023)
- [Incremental Learning Techniques for Semantic Segmentation](https://mlsanity.com/paper/1907.13372/) (2019)
- [GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models](https://mlsanity.com/paper/2210.02025/) (2022)
- [RECALL: Replay-based Continual Learning in Semantic Segmentation](https://mlsanity.com/paper/2108.03673/) (2021)
- [RbA: Segmenting Unknown Regions Rejected by All](https://mlsanity.com/paper/2211.14293/) (2022)
- [Two Video Data Sets for Tracking and Retrieval of Out of Distribution Objects](https://mlsanity.com/paper/2210.02074/) (2022)
- [A Likelihood Ratio-Based Approach to Segmenting Unknown Objects](https://mlsanity.com/paper/2409.06424/) (2024)
- [Building a Credible Case for Safety: Waymo's Approach for the Determination of Absence of Unreasonable Risk](https://mlsanity.com/paper/2306.01917/) (2023)
- [Have We Ever Encountered This Before? Retrieving Out-of-Distribution Road Obstacles from Driving Scenes](https://mlsanity.com/paper/2309.04302/) (2023)
- [Segment-Level Road Obstacle Detection Using Visual Foundation Model Priors and Likelihood Ratios](https://mlsanity.com/paper/2412.05707/) (2024)

## Built on by (most cited first, 3 of 3)

- [Out-of-Distribution Segmentation in Autonomous Driving: Problems and State of the Art](https://mlsanity.com/paper/2503.08695/) (2025)
- [Mcity Data Engine: Iterative Model Improvement Through Open-Vocabulary Data Selection](https://mlsanity.com/paper/2504.21614/) (2025)
- [Online Monitoring Framework for Automotive Time Series Data using JEPA Embeddings](https://mlsanity.com/paper/2602.09985/) (2026)

## Abstract (arXiv)

Advances in machine learning methods for computer vision tasks have led to their consideration for safety-critical applications like autonomous driving. However, effectively integrating these methods into the automotive development lifecycle remains challenging. Since the performance of machine learning algorithms relies heavily on the training data provided, the data and model development lifecycle play a key role in successfully integrating these components into the product development lifecycle. Existing models frequently encounter difficulties recognizing or adapting to novel instances not present in the original training dataset. This poses a significant risk for reliable deployment in dynamic environments. To address this challenge, we propose an adaptive neural network architecture and an iterative development framework that enables users to efficiently incorporate previously unknown objects into the current perception system. Our approach builds on continuous learning, emphasizing the necessity of dynamic updates to reflect real-world deployment conditions. Specifically, we introduce a pipeline with three key components: (1) a scalable network extension strategy to integrate new classes while preserving existing performance, (2) a dynamic OoD detection component that requires no additional retraining for newly added classes, and (3) a retrieval-based data augmentation process tailored for safety-critical deployments. The integration of these components establishes a pragmatic and adaptive pipeline for the continuous evolution of perception systems in the context of autonomous driving.