# Cross-Modal Knowledge Distillation for Acoustic Pedestrian Detection

arXiv: https://arxiv.org/abs/2609.31785 · HTML: https://mlsanity.com/paper/2609.31785/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 29 of its 40 references that are in the map.
- First posted on arXiv 24 Sep 2026.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 29 of 29)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [Long-tail learning via logit adjustment](https://mlsanity.com/paper/2007.07314/) (2020)
- [SoundNet: Learning Sound Representations from Unlabeled Video](https://mlsanity.com/paper/1610.09001/) (2016)
- [Characterizing and Avoiding Negative Transfer](https://mlsanity.com/paper/1811.09751/) (2018)
- [Distilling Audio-Visual Knowledge by Compositional Contrastive Learning](https://mlsanity.com/paper/2104.10955/) (2021)
- [There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledge](https://mlsanity.com/paper/2103.01353/) (2021)
- [The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation](https://mlsanity.com/paper/2206.06487/) (2022)
- [Confidence-Aware Multi-Teacher Knowledge Distillation](https://mlsanity.com/paper/2201.00007/) (2021)
- [XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning](https://mlsanity.com/paper/2211.13929/) (2022)
- [Balanced Knowledge Distillation for Long-tailed Learning](https://mlsanity.com/paper/2104.10510/) (2021)
- [DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets](https://mlsanity.com/paper/2404.02900/) (2024)
- [Federated Learning with Label-Masking Distillation](https://mlsanity.com/paper/2409.13136/) (2024)
- [Audio Embeddings as Teachers for Music Classification](https://mlsanity.com/paper/2306.17424/) (2023)
- [Hard Gate Knowledge Distillation -- Leverage Calibration for Robust and Reliable Language Model](https://mlsanity.com/paper/2210.12427/) (2022)
- [AV-PedAware: Self-Supervised Audio-Visual Fusion for Dynamic Pedestrian Awareness](https://mlsanity.com/paper/2411.06789/) (2024)
- [The Role of Teacher Calibration in Knowledge Distillation](https://mlsanity.com/paper/2508.20224/) (2025)
- [Self-Filtered Distillation with LLMs-generated Trust Indicators for Reliable Patent Classification](https://mlsanity.com/paper/2510.05431/) (2025)
- [ASPED: An Audio Dataset for Detecting Pedestrians](https://mlsanity.com/paper/2309.06531/) (2023)
- [Audio-Based Pedestrian Detection in the Presence of Vehicular Noise](https://mlsanity.com/paper/2509.19295/) (2025)

## Abstract (arXiv)

Audio-only pedestrian detection is attractive for urban sensing but limited by weak acoustic cues. An appealing strategy is cross-modal knowledge distillation, in which a video teacher supervises the audio student during training so that the deployed model runs on audio alone. Under this task's severe class imbalance and wide video-audio modality gap, however, what such distillation contributes is unclear. We introduce Trust-Filtered Distillation (TFD), which selectively suppresses teacher supervision on pedestrian samples, and interpret its logit formulation as conditional label smoothing under a shared temperature. Across ten distillation configurations under five-fold cross-session validation on ASPED, most methods yield modest gains in macro accuracy accompanied by small changes in PR-AUC. The main effect is higher no-pedestrian accuracy at the cost of lower pedestrian recall. Adding TFD to logit distillation strengthens this trade-off without improving mean PR-AUC. These findings clarify the benefits and limitations of selective cross-modal supervision by distinguishing operating-point shifts from discrimination gains in imbalanced acoustic detection.