# Progressive Multi-task Anti-Noise Learning and Distilling Frameworks for Fine-grained Vehicle Recognition

arXiv: https://arxiv.org/abs/2401.14336 · HTML: https://mlsanity.com/paper/2401.14336/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 68 references that are in the map.
- First posted on arXiv 25 Jan 2024.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data](https://mlsanity.com/paper/1703.11008/) (2017)
- [Similarity-Preserving Knowledge Distillation](https://mlsanity.com/paper/1907.09682/) (2019)
- [Fantastic Generalization Measures and Where to Find Them](https://mlsanity.com/paper/1912.02178/) (2019)
- [Do Deep Nets Really Need to be Deep?](https://mlsanity.com/paper/1312.6184/) (2013)
- [Correlation Congruence for Knowledge Distillation](https://mlsanity.com/paper/1904.01802/) (2019)
- [Learning without Memorizing](https://mlsanity.com/paper/1811.08051/) (2018)
- [Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons](https://mlsanity.com/paper/1811.03233/) (2018)
- [Learning Deep Representations with Probabilistic Knowledge Transfer](https://mlsanity.com/paper/1803.10837/) (2018)
- [AutoFormer: Searching Transformers for Visual Recognition](https://mlsanity.com/paper/2107.00651/) (2021)
- [Sobolev Training for Neural Networks](https://mlsanity.com/paper/1706.04859/) (2017)
- [TransFG: A Transformer Architecture for Fine-grained Recognition](https://mlsanity.com/paper/2103.07976/) (2021)
- [A Large-Scale Car Dataset for Fine-Grained Categorization and Verification](https://mlsanity.com/paper/1506.08959/) (2015)
- [TResNet: High Performance GPU-Dedicated Architecture](https://mlsanity.com/paper/2003.13630/) (2020)
- [Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches](https://mlsanity.com/paper/2003.03836/) (2020)
- [Neural Architecture Transfer](https://mlsanity.com/paper/2005.05859/) (2020)
- [Channel Interaction Networks for Fine-Grained Image Categorization](https://mlsanity.com/paper/2003.05235/) (2020)
- [Grafit: Learning fine-grained image representations with coarse labels](https://mlsanity.com/paper/2011.12982/) (2020)
- [WINNet: Wavelet-inspired Invertible Network for Image Denoising](https://mlsanity.com/paper/2109.06381/) (2021)
- [Look-into-Object: Self-supervised Structure Modeling for Object Recognition](https://mlsanity.com/paper/2003.14142/) (2020)

## Built on by (most cited first, 1 of 1)

- [An Analysis of Multi-Task Architectures for the Hierarchic Multi-Label Problem of Vehicle Model and Make Classification](https://mlsanity.com/paper/2603.01746/) (2026)

## Abstract (arXiv)

Fine-grained vehicle recognition (FGVR) is an essential fundamental technology for intelligent transportation systems, but very difficult because of its inherent intra-class variation. Most previous FGVR studies only focus on the intra-class variation caused by different shooting angles, positions, etc., while the intra-class variation caused by image noise has received little attention. This paper proposes a progressive multi-task anti-noise learning (PMAL) framework and a progressive multi-task distilling (PMD) framework to solve the intra-class variation problem in FGVR due to image noise. The PMAL framework achieves high recognition accuracy by treating image denoising as an additional task in image recognition and progressively forcing a model to learn noise invariance. The PMD framework transfers the knowledge of the PMAL-trained model into the original backbone network, which produces a model with about the same recognition accuracy as the PMAL-trained model, but without any additional overheads over the original backbone network. Combining the two frameworks, we obtain models that significantly exceed previous state-of-the-art methods in recognition accuracy on two widely-used, standard FGVR datasets, namely Stanford Cars, and CompCars, as well as three additional surveillance image-based vehicle-type classification datasets, namely Beijing Institute of Technology (BIT)-Vehicle, Vehicle Type Image Data 2 (VTID2), and Vehicle Images Dataset for Make Model Recognition (VIDMMR), without any additional overheads over the original backbone networks. The source code is available at https://github.com/Dichao-Liu/Anti-noise_FGVR