# The Devil is in the Tails: Fine-grained Classification in the Wild

arXiv: https://arxiv.org/abs/1709.01450 · HTML: https://mlsanity.com/paper/1709.01450/

## Key facts

- Cited by 89 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Sep 2017.

## Built on by (most cited first, 30 of 89)

- [Revisiting Weakly Supervised Pre-Training of Visual Perception Models](https://mlsanity.com/paper/2201.08371/) (2022)
- [MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions](https://mlsanity.com/paper/2105.07404/) (2021)
- [A Survey on Long-Tailed Visual Recognition](https://mlsanity.com/paper/2205.13775/) (2022)
- [On the Importance and Applicability of Pre-Training for Federated Learning](https://mlsanity.com/paper/2206.11488/) (2022)
- [Trustworthy Long-Tailed Classification](https://mlsanity.com/paper/2111.09030/) (2021)
- [Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition](https://mlsanity.com/paper/2207.01160/) (2022)
- [CoSSL: Co-Learning of Representation and Classifier for Imbalanced Semi-Supervised Learning](https://mlsanity.com/paper/2112.04564/) (2021)
- [Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective](https://mlsanity.com/paper/2111.03874/) (2021)
- [Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data](https://mlsanity.com/paper/2212.13827/) (2022)
- [Inducing Neural Collapse in Deep Long-tailed Learning](https://mlsanity.com/paper/2302.12453/) (2023)
- [Taxonomy of Machine Learning Safety: A Survey and Primer](https://mlsanity.com/paper/2106.04823/) (2021)
- [RoFL: Robustness of Secure Federated Learning](https://mlsanity.com/paper/2107.03311/) (2021)
- [Procrustean Training for Imbalanced Deep Learning](https://mlsanity.com/paper/2104.01769/) (2021)
- [Bugs in the Data: How ImageNet Misrepresents Biodiversity](https://mlsanity.com/paper/2208.11695/) (2022)
- [Balanced Knowledge Distillation for Long-tailed Learning](https://mlsanity.com/paper/2104.10510/) (2021)
- [Delving into Semantic Scale Imbalance](https://mlsanity.com/paper/2212.14613/) (2022)
- [Teacher's pet: understanding and mitigating biases in distillation](https://mlsanity.com/paper/2106.10494/) (2021)
- [Species Distribution Modeling for Machine Learning Practitioners: A Review](https://mlsanity.com/paper/2107.10400/) (2021)
- [Open Long-Tailed Recognition in a Dynamic World](https://mlsanity.com/paper/2208.08349/) (2022)
- [A Theoretical Analysis of the Learning Dynamics under Class Imbalance](https://mlsanity.com/paper/2207.00391/) (2022)
- [Evaluating Distributional Distortion in Neural Language Modeling](https://mlsanity.com/paper/2203.12788/) (2022)
- [A Study of the Generalizability of Self-Supervised Representations](https://mlsanity.com/paper/2109.09150/) (2021)
- [How unfair is private learning ?](https://mlsanity.com/paper/2206.03985/) (2022)
- [Margin Calibration for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2112.07225/) (2021)
- [Label-Noise Learning with Intrinsically Long-Tailed Data](https://mlsanity.com/paper/2208.09833/) (2022)
- [EAT: Towards Long-Tailed Out-of-Distribution Detection](https://mlsanity.com/paper/2312.08939/) (2023)
- [On Bridging Generic and Personalized Federated Learning for Image Classification](https://mlsanity.com/paper/2107.00778/) (2021)
- [Generalized Data Weighting via Class-level Gradient Manipulation](https://mlsanity.com/paper/2111.00056/) (2021)
- [Do Deep Networks Transfer Invariances Across Classes?](https://mlsanity.com/paper/2203.09739/) (2022)
- [Training Over-parameterized Models with Non-decomposable Objectives](https://mlsanity.com/paper/2107.04641/) (2021)

## Abstract (arXiv)

The world is long-tailed. What does this mean for computer vision and visual recognition? The main two implications are (1) the number of categories we need to consider in applications can be very large, and (2) the number of training examples for most categories can be very small. Current visual recognition algorithms have achieved excellent classification accuracy. However, they require many training examples to reach peak performance, which suggests that long-tailed distributions will not be dealt with well. We analyze this question in the context of eBird, a large fine-grained classification dataset, and a state-of-the-art deep network classification algorithm. We find that (a) peak classification performance on well-represented categories is excellent, (b) given enough data, classification performance suffers only minimally from an increase in the number of classes, (c) classification performance decays precipitously as the number of training examples decreases, (d) surprisingly, transfer learning is virtually absent in current methods. Our findings suggest that our community should come to grips with the question of long tails.