# Fine-grained Recognition: Accounting for Subtle Differences between Similar Classes

arXiv: https://arxiv.org/abs/1912.06842 · HTML: https://mlsanity.com/paper/1912.06842/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Dec 2019.

## Built on by (most cited first, 24 of 24)

- [Fine-Grained Image Analysis with Deep Learning: A Survey](https://mlsanity.com/paper/2111.06119/) (2021)
- [Feature Fusion Vision Transformer for Fine-Grained Visual Categorization](https://mlsanity.com/paper/2107.02341/) (2021)
- [Fine-Grained Object Classification via Self-Supervised Pose Alignment](https://mlsanity.com/paper/2203.15987/) (2022)
- [SIM-Trans: Structure Information Modeling Transformer for Fine-grained Visual Categorization](https://mlsanity.com/paper/2208.14607/) (2022)
- [Fine-grained Recognition with Learnable Semantic Data Augmentation](https://mlsanity.com/paper/2309.00399/) (2023)
- [Transformer with Peak Suppression and Knowledge Guidance for Fine-grained Image Recognition](https://mlsanity.com/paper/2107.06538/) (2021)
- [Learning with Noisy labels via Self-supervised Adversarial Noisy Masking](https://mlsanity.com/paper/2302.06805/) (2023)
- [Fine-Grained Visual Classification using Self Assessment Classifier](https://mlsanity.com/paper/2205.10529/) (2022)
- [Hierarchical Few-Shot Object Detection: Problem, Benchmark and Method](https://mlsanity.com/paper/2210.03940/) (2022)
- [Fine-Grained Zero-Shot Object Detection](https://mlsanity.com/paper/2507.10358/) (2025)
- [Fine-Grained Visual Classification via Simultaneously Learning of Multi-regional Multi-grained Features](https://mlsanity.com/paper/2102.00367/) (2021)
- [Context-Semantic Quality Awareness Network for Fine-Grained Visual Categorization](https://mlsanity.com/paper/2403.10298/) (2024)
- [Feature Boosting, Suppression, and Diversification for Fine-Grained Visual Classification](https://mlsanity.com/paper/2103.02782/) (2021)
- [BR-NPA: A Non-Parametric High-Resolution Attention Model to improve the Interpretability of Attention](https://mlsanity.com/paper/2106.02566/) (2021)
- [Parsing Objects at a Finer Granularity: A Survey](https://mlsanity.com/paper/2212.13693/) (2022)
- [M2Former: Multi-Scale Patch Selection for Fine-Grained Visual Recognition](https://mlsanity.com/paper/2308.02161/) (2023)
- [Self-Supervised Learning for Fine-Grained Visual Categorization](https://mlsanity.com/paper/2105.08788/) (2021)
- [ViT-FOD: A Vision Transformer based Fine-grained Object Discriminator](https://mlsanity.com/paper/2203.12816/) (2022)
- [Distilling Local Texture Features for Colorectal Tissue Classification in Low Data Regimes](https://mlsanity.com/paper/2401.01164/) (2024)
- [ConceptHash: Interpretable Fine-Grained Hashing via Concept Discovery](https://mlsanity.com/paper/2406.08457/) (2024)
- [Sequential Random Network for Fine-grained Image Classification](https://mlsanity.com/paper/2103.07230/) (2021)
- [Spatial Transformer Network with Transfer Learning for Small-scale Fine-grained Skeleton-based Tai Chi Action Recognition](https://mlsanity.com/paper/2206.15002/) (2022)
- [DCFG: Diverse Cross-Channel Fine-Grained Feature Learning and Progressive Fusion Siamese Tracker for Thermal Infrared Target Tracking](https://mlsanity.com/paper/2504.14311/) (2025)
- [GeoVision Labeler: Zero-Shot Geospatial Classification with Vision and Language Models](https://mlsanity.com/paper/2505.24340/) (2025)

## Abstract (arXiv)

The main requisite for fine-grained recognition task is to focus on subtle discriminative details that make the subordinate classes different from each other. We note that existing methods implicitly address this requirement and leave it to a data-driven pipeline to figure out what makes a subordinate class different from the others. This results in two major limitations: First, the network focuses on the most obvious distinctions between classes and overlooks more subtle inter-class variations. Second, the chance of misclassifying a given sample in any of the negative classes is considered equal, while in fact, confusions generally occur among only the most similar classes. Here, we propose to explicitly force the network to find the subtle differences among closely related classes. In this pursuit, we introduce two key novelties that can be easily plugged into existing end-to-end deep learning pipelines. On one hand, we introduce diversification block which masks the most salient features for an input to force the network to use more subtle cues for its correct classification. Concurrently, we introduce a gradient-boosting loss function that focuses only on the confusing classes for each sample and therefore moves swiftly along the direction on the loss surface that seeks to resolve these ambiguities. The synergy between these two blocks helps the network to learn more effective feature representations. Comprehensive experiments are performed on five challenging datasets. Our approach outperforms existing methods using similar experimental setting on all five datasets.