# Learning to Segment the Tail

arXiv: https://arxiv.org/abs/2004.00900 · HTML: https://mlsanity.com/paper/2004.00900/

## Key facts

- Cited by 54 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Apr 2020.

## Built on by (most cited first, 30 of 54)

- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [Distribution Alignment: A Unified Framework for Long-tail Visual Recognition](https://mlsanity.com/paper/2103.16370/) (2021)
- [Towards Open Vocabulary Learning: A Survey](https://mlsanity.com/paper/2306.15880/) (2023)
- [Reviving Iterative Training with Mask Guidance for Interactive Segmentation](https://mlsanity.com/paper/2102.06583/) (2021)
- [Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2104.00308/) (2021)
- [Self-supervised Learning is More Robust to Dataset Imbalance](https://mlsanity.com/paper/2110.05025/) (2021)
- [ReCo: Retrieve and Co-segment for Zero-shot Transfer](https://mlsanity.com/paper/2206.07045/) (2022)
- [Distributional Robustness Loss for Long-tail Learning](https://mlsanity.com/paper/2104.03066/) (2021)
- [FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation](https://mlsanity.com/paper/2102.12867/) (2021)
- [A Survey on Long-Tailed Visual Recognition](https://mlsanity.com/paper/2205.13775/) (2022)
- [Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2203.09811/) (2022)
- [Online Continual Learning for Embedded Devices](https://mlsanity.com/paper/2203.10681/) (2022)
- [Equalized Focal Loss for Dense Long-Tailed Object Detection](https://mlsanity.com/paper/2201.02593/) (2022)
- [On Model Calibration for Long-Tailed Object Detection and Instance Segmentation](https://mlsanity.com/paper/2107.02170/) (2021)
- [MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/2309.13042/) (2023)
- [Invariant Feature Learning for Generalized Long-Tailed Classification](https://mlsanity.com/paper/2207.09504/) (2022)
- [MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection](https://mlsanity.com/paper/2102.08884/) (2021)
- [Few-Shot Object Detection: A Comprehensive Survey](https://mlsanity.com/paper/2112.11699/) (2021)
- [A Systematic Review on Long-Tailed Learning](https://mlsanity.com/paper/2408.00483/) (2024)
- [Class-Balanced Distillation for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2104.05279/) (2021)
- [Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detection](https://mlsanity.com/paper/2104.05702/) (2021)
- [When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Method](https://mlsanity.com/paper/2211.10955/) (2022)
- [Simplifying Neural Network Training Under Class Imbalance](https://mlsanity.com/paper/2312.02517/) (2023)
- [PlayWorld: Learning Robot World Models from Autonomous Play](https://mlsanity.com/paper/2603.09030/) (2026)
- [Predicting and Enhancing the Fairness of DNNs with the Curvature of Perceptual Manifolds](https://mlsanity.com/paper/2303.12307/) (2023)
- [SuperDisco: Super-Class Discovery Improves Visual Recognition for the Long-Tail](https://mlsanity.com/paper/2304.00101/) (2023)
- [Input-Output Balanced Framework for Long-tailed LiDAR Semantic Segmentation](https://mlsanity.com/paper/2103.14269/) (2021)
- [Learning with Free Object Segments for Long-Tailed Instance Segmentation](https://mlsanity.com/paper/2202.11124/) (2022)
- [The Equalization Losses: Gradient-Driven Training for Long-tailed Object Recognition](https://mlsanity.com/paper/2210.05566/) (2022)
- [Rebalanced Zero-shot Learning](https://mlsanity.com/paper/2210.07031/) (2022)

## Abstract (arXiv)

Real-world visual recognition requires handling the extreme sample imbalance in large-scale long-tailed data. We propose a "divide&conquer" strategy for the challenging LVIS task: divide the whole data into balanced parts and then apply incremental learning to conquer each one. This derives a novel learning paradigm: class-incremental few-shot learning, which is especially effective for the challenge evolving over time: 1) the class imbalance among the old-class knowledge review and 2) the few-shot data in new-class learning. We call our approach Learning to Segment the Tail (LST). In particular, we design an instance-level balanced replay scheme, which is a memory-efficient approximation to balance the instance-level samples from the old-class images. We also propose to use a meta-module for new-class learning, where the module parameters are shared across incremental phases, gaining the learning-to-learn knowledge incrementally, from the data-rich head to the data-poor tail. We empirically show that: at the expense of a little sacrifice of head-class forgetting, we can gain a significant 8.3% AP improvement for the tail classes with less than 10 instances, achieving an overall 2.0% AP boost for the whole 1,230 classes.