# Efficient Visual Fault Detection for Freight Train Braking System via Heterogeneous Self Distillation in the Wild

arXiv: https://arxiv.org/abs/2307.00701 · HTML: https://mlsanity.com/paper/2307.00701/

## 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 27 of its 46 references that are in the map.
- First posted on arXiv 3 Jul 2023.

## Placed in

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

## Builds on (most cited first, 27 of 27)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [CornerNet: Detecting Objects as Paired Keypoints](https://mlsanity.com/paper/1808.01244/) (2018)
- [Sparse R-CNN: End-to-End Object Detection with Learnable Proposals](https://mlsanity.com/paper/2011.12450/) (2020)
- [Cascade R-CNN: High Quality Object Detection and Instance Segmentation](https://mlsanity.com/paper/1906.09756/) (2019)
- [Caffe: Convolutional Architecture for Fast Feature Embedding](https://mlsanity.com/paper/1408.5093/) (2014)
- [Distilling Knowledge via Knowledge Review](https://mlsanity.com/paper/2104.09044/) (2021)
- [Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training](https://mlsanity.com/paper/2004.06002/) (2020)
- [AutoAssign: Differentiable Label Assignment for Dense Object Detection](https://mlsanity.com/paper/2007.03496/) (2020)
- [Grid R-CNN](https://mlsanity.com/paper/1811.12030/) (2018)
- [Localization Distillation for Dense Object Detection](https://mlsanity.com/paper/2102.12252/) (2021)
- [Instance-Conditional Knowledge Distillation for Object Detection](https://mlsanity.com/paper/2110.12724/) (2021)
- [CentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detection](https://mlsanity.com/paper/2003.09119/) (2020)
- [Multi-View Correlation Distillation for Incremental Object Detection](https://mlsanity.com/paper/2107.01787/) (2021)
- [LGD: Label-guided Self-distillation for Object Detection](https://mlsanity.com/paper/2109.11496/) (2021)
- [Improving Object Detection by Label Assignment Distillation](https://mlsanity.com/paper/2108.10520/) (2021)
- [Towards Balanced Learning for Instance Recognition](https://mlsanity.com/paper/2108.10175/) (2021)
- [DSLA: Dynamic smooth label assignment for efficient anchor-free object detection](https://mlsanity.com/paper/2208.00817/) (2022)

## Abstract (arXiv)

Efficient visual fault detection of freight trains is a critical part of ensuring the safe operation of railways under the restricted hardware environment. Although deep learning-based approaches have excelled in object detection, the efficiency of freight train fault detection is still insufficient to apply in real-world engineering. This paper proposes a heterogeneous self-distillation framework to ensure detection accuracy and speed while satisfying low resource requirements. The privileged information in the output feature knowledge can be transferred from the teacher to the student model through distillation to boost performance. We first adopt a lightweight backbone to extract features and generate a new heterogeneous knowledge neck. Such neck models positional information and long-range dependencies among channels through parallel encoding to optimize feature extraction capabilities. Then, we utilize the general distribution to obtain more credible and accurate bounding box estimates. Finally, we employ a novel loss function that makes the network easily concentrate on values near the label to improve learning efficiency. Experiments on four fault datasets reveal that our framework can achieve over 37 frames per second and maintain the highest accuracy in comparison with traditional distillation approaches. Moreover, compared to state-of-the-art methods, our framework demonstrates more competitive performance with lower memory usage and the smallest model size.