# FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation

arXiv: https://arxiv.org/abs/1907.12347 · HTML: https://mlsanity.com/paper/1907.12347/

## Key facts

- Cited by 160 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jul 2019.

## Built on by (most cited first, 30 of 160)

- [Language-driven Semantic Segmentation](https://mlsanity.com/paper/2201.03546/) (2022)
- [XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model](https://mlsanity.com/paper/2207.07115/) (2022)
- [OmniGen: Unified Image Generation](https://mlsanity.com/paper/2409.11340/) (2024)
- [Segment Anything in High Quality](https://mlsanity.com/paper/2306.01567/) (2023)
- [Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields](https://mlsanity.com/paper/2312.03203/) (2023)
- [OpenMask3D: Open-Vocabulary 3D Instance Segmentation](https://mlsanity.com/paper/2306.13631/) (2023)
- [Personalize Segment Anything Model with One Shot](https://mlsanity.com/paper/2305.03048/) (2023)
- [Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation](https://mlsanity.com/paper/2106.05210/) (2021)
- [Tracking Anything with Decoupled Video Segmentation](https://mlsanity.com/paper/2309.03903/) (2023)
- [Hypercorrelation Squeeze for Few-Shot Segmentation](https://mlsanity.com/paper/2104.01538/) (2021)
- [Putting the Object Back into Video Object Segmentation](https://mlsanity.com/paper/2310.12982/) (2023)
- [Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching](https://mlsanity.com/paper/2305.13310/) (2023)
- [Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion](https://mlsanity.com/paper/2103.07941/) (2021)
- [Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation](https://mlsanity.com/paper/2207.10866/) (2022)
- [Self-Support Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2207.11549/) (2022)
- [High-Quality Entity Segmentation](https://mlsanity.com/paper/2211.05776/) (2022)
- [Self-Guided and Cross-Guided Learning for Few-Shot Segmentation](https://mlsanity.com/paper/2103.16129/) (2021)
- [A Survey on Long-Tailed Visual Recognition](https://mlsanity.com/paper/2205.13775/) (2022)
- [Mining Latent Classes for Few-shot Segmentation](https://mlsanity.com/paper/2103.15402/) (2021)
- [Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation](https://mlsanity.com/paper/2207.08549/) (2022)
- [EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model](https://mlsanity.com/paper/2406.20076/) (2024)
- [Feature-Proxy Transformer for Few-Shot Segmentation](https://mlsanity.com/paper/2210.06908/) (2022)
- [CATs++: Boosting Cost Aggregation with Convolutions and Transformers](https://mlsanity.com/paper/2202.06817/) (2022)
- [Recurrent Dynamic Embedding for Video Object Segmentation](https://mlsanity.com/paper/2205.03761/) (2022)
- [Exploring Effective Factors for Improving Visual In-Context Learning](https://mlsanity.com/paper/2304.04748/) (2023)
- [Per-Clip Video Object Segmentation](https://mlsanity.com/paper/2208.01924/) (2022)
- [Open-vocabulary Semantic Segmentation with Frozen Vision-Language Models](https://mlsanity.com/paper/2210.15138/) (2022)
- [Few-shot Segmentation with Optimal Transport Matching and Message Flow](https://mlsanity.com/paper/2108.08518/) (2021)
- [RobustSAM: Segment Anything Robustly on Degraded Images](https://mlsanity.com/paper/2406.09627/) (2024)
- [Learning Quality-aware Dynamic Memory for Video Object Segmentation](https://mlsanity.com/paper/2207.07922/) (2022)

## Abstract (arXiv)

Over the past few years, we have witnessed the success of deep learning in image recognition thanks to the availability of large-scale human-annotated datasets such as PASCAL VOC, ImageNet, and COCO. Although these datasets have covered a wide range of object categories, there are still a significant number of objects that are not included. Can we perform the same task without a lot of human annotations? In this paper, we are interested in few-shot object segmentation where the number of annotated training examples are limited to 5 only. To evaluate and validate the performance of our approach, we have built a few-shot segmentation dataset, FSS-1000, which consists of 1000 object classes with pixelwise annotation of ground-truth segmentation. Unique in FSS-1000, our dataset contains significant number of objects that have never been seen or annotated in previous datasets, such as tiny daily objects, merchandise, cartoon characters, logos, etc. We build our baseline model using standard backbone networks such as VGG-16, ResNet-101, and Inception. To our surprise, we found that training our model from scratch using FSS-1000 achieves comparable and even better results than training with weights pre-trained by ImageNet which is more than 100 times larger than FSS-1000. Both our approach and dataset are simple, effective, and easily extensible to learn segmentation of new object classes given very few annotated training examples. Dataset is available at https://github.com/HKUSTCV/FSS-1000.