# High-Resolution Range Profile Classifiers Require Aspect-Angle Awareness

arXiv: https://arxiv.org/abs/2603.00087 · HTML: https://mlsanity.com/paper/2603.00087/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 17 references that are in the map.
- First posted on arXiv 16 Feb 2026.

## Builds on (most cited first, 5 of 5)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Modulating early visual processing by language](https://mlsanity.com/paper/1707.00683/) (2017)
- [From Unsupervised to Semi-supervised Anomaly Detection Methods for HRRP Targets](https://mlsanity.com/paper/2106.11168/) (2021)
- [MFN Decomposition and Related Metrics for High-Resolution Range Profiles Generative Models](https://mlsanity.com/paper/2602.13296/) (2026)

## Abstract (arXiv)

We revisit High-Resolution Range Profile (HRRP) classification with aspect-angle conditioning. While prior work often assumes that aspect-angle information is incomplete during training or unavailable at inference, we study a setting where angles are available for all training samples and explicitly provided to the classifier. Using three datasets and a broad range of conditioning strategies and model architectures, we show that both single-profile and sequential classifiers benefit consistently from aspect-angle awareness, with an average accuracy gain of about 7% and improvements of up to 10%, depending on the model and dataset. In practice, aspect angles are not directly measured and must be estimated. We show that a causal Kalman filter can estimate them online with a median error of 5textdegree, and that training and inference with estimated angles preserves most of the gains, supporting the proposed approach in realistic conditions.