# ELFIS: Expert Learning for Fine-grained Image Recognition Using Subsets

arXiv: https://arxiv.org/abs/2303.09269 · HTML: https://mlsanity.com/paper/2303.09269/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 58 references that are in the map.
- First posted on arXiv 16 Mar 2023.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [Frustratingly Simple Few-Shot Object Detection](https://mlsanity.com/paper/2003.06957/) (2020)
- [Fine-Grained Image Analysis with Deep Learning: A Survey](https://mlsanity.com/paper/2111.06119/) (2021)
- [Online Knowledge Distillation with Diverse Peers](https://mlsanity.com/paper/1912.00350/) (2019)
- [Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification](https://mlsanity.com/paper/2205.02151/) (2022)
- [Interpretable and Accurate Fine-grained Recognition via Region Grouping](https://mlsanity.com/paper/2005.10411/) (2020)
- [Maximum-Entropy Fine-Grained Classification](https://mlsanity.com/paper/1809.05934/) (2018)
- [SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data](https://mlsanity.com/paper/2012.04846/) (2020)
- [Grafit: Learning fine-grained image representations with coarse labels](https://mlsanity.com/paper/2011.12982/) (2020)
- [Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification](https://mlsanity.com/paper/2101.06635/) (2021)
- [Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks](https://mlsanity.com/paper/1504.08289/) (2015)
- [Subset Feature Learning for Fine-Grained Category Classification](https://mlsanity.com/paper/1505.02269/) (2015)
- [ClustGeo: an R package for hierarchical clustering with spatial constraints](https://mlsanity.com/paper/1707.03897/) (2017)

## Abstract (arXiv)

Fine-Grained Visual Recognition (FGVR) tackles the problem of distinguishing highly similar categories. One of the main approaches to FGVR, namely subset learning, tries to leverage information from existing class taxonomies to improve the performance of deep neural networks. However, these methods rely on the existence of handcrafted hierarchies that are not necessarily optimal for the models. In this paper, we propose ELFIS, an expert learning framework for FGVR that clusters categories of the dataset into meta-categories using both dataset-inherent lexical and model-specific information. A set of neural networks-based experts are trained focusing on the meta-categories and are integrated into a multi-task framework. Extensive experimentation shows improvements in the SoTA FGVR benchmarks of up to +1.3% of accuracy using both CNNs and transformer-based networks. Overall, the obtained results evidence that ELFIS can be applied on top of any classification model, enabling the obtention of SoTA results. The source code will be made public soon.