# Better (pseudo-)labels for semi-supervised instance segmentation

arXiv: https://arxiv.org/abs/2403.11675 · HTML: https://mlsanity.com/paper/2403.11675/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 16 references that are in the map.
- First posted on arXiv 18 Mar 2024.

## Builds on (most cited first, 12 of 12)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [EVA: Exploring the Limits of Masked Visual Representation Learning at Scale](https://mlsanity.com/paper/2211.07636/) (2022)
- [Cascade R-CNN: High Quality Object Detection and Instance Segmentation](https://mlsanity.com/paper/1906.09756/) (2019)
- [X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion](https://mlsanity.com/paper/2212.03863/) (2022)
- [Noisy Boundaries: Lemon or Lemonade for Semi-supervised Instance Segmentation?](https://mlsanity.com/paper/2203.13427/) (2022)
- [Relieving Long-tailed Instance Segmentation via Pairwise Class Balance](https://mlsanity.com/paper/2201.02784/) (2022)
- [Polite Teacher: Semi-Supervised Instance Segmentation with Mutual Learning and Pseudo-Label Thresholding](https://mlsanity.com/paper/2211.03850/) (2022)
- [Guided Distillation for Semi-Supervised Instance Segmentation](https://mlsanity.com/paper/2308.02668/) (2023)

## Built on by (most cited first, 1 of 1)

- [SemiOccam: A Robust Semi-Supervised Image Recognition Network Using Sparse Labels](https://mlsanity.com/paper/2506.03582/) (2025)

## Abstract (arXiv)

Despite the availability of large datasets for tasks like image classification and image-text alignment, labeled data for more complex recognition tasks, such as detection and segmentation, is less abundant. In particular, for instance segmentation annotations are time-consuming to produce, and the distribution of instances is often highly skewed across classes. While semi-supervised teacher-student distillation methods show promise in leveraging vast amounts of unlabeled data, they suffer from miscalibration, resulting in overconfidence in frequently represented classes and underconfidence in rarer ones. Additionally, these methods encounter difficulties in efficiently learning from a limited set of examples. We introduce a dual-strategy to enhance the teacher model's training process, substantially improving the performance on few-shot learning. Secondly, we propose a calibration correction mechanism that that enables the student model to correct the teacher's calibration errors. Using our approach, we observed marked improvements over a state-of-the-art supervised baseline performance on the LVIS dataset, with an increase of 2.8% in average precision (AP) and 10.3% gain in AP for rare classes.