# Where are the Masks: Instance Segmentation with Image-level Supervision

arXiv: https://arxiv.org/abs/1907.01430 · HTML: https://mlsanity.com/paper/1907.01430/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2019.

## Built on by (most cited first, 18 of 18)

- [Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data](https://mlsanity.com/paper/2103.16607/) (2021)
- [A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction](https://mlsanity.com/paper/2207.01223/) (2022)
- [A Survey of Self-Supervised and Few-Shot Object Detection](https://mlsanity.com/paper/2110.14711/) (2021)
- [Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinement](https://mlsanity.com/paper/2109.09477/) (2021)
- [Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images](https://mlsanity.com/paper/2104.01526/) (2021)
- [Weakly Supervised Instance Segmentation for Videos with Temporal Mask Consistency](https://mlsanity.com/paper/2103.12886/) (2021)
- [Learning to Detect Instance-level Salient Objects Using Complementary Image Labels](https://mlsanity.com/paper/2111.10137/) (2021)
- [Solve the Puzzle of Instance Segmentation in Videos: A Weakly Supervised Framework with Spatio-Temporal Collaboration](https://mlsanity.com/paper/2212.07592/) (2022)
- [WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition](https://mlsanity.com/paper/2402.14812/) (2024)
- [GaPro: Box-Supervised 3D Point Cloud Instance Segmentation Using Gaussian Processes as Pseudo Labelers](https://mlsanity.com/paper/2307.13251/) (2023)
- [Complete Instances Mining for Weakly Supervised Instance Segmentation](https://mlsanity.com/paper/2402.07633/) (2024)
- [Frustratingly Simple but Effective Zero-shot Detection and Segmentation: Analysis and a Strong Baseline](https://mlsanity.com/paper/2302.07319/) (2023)
- [UVIS: Unsupervised Video Instance Segmentation](https://mlsanity.com/paper/2406.06908/) (2024)
- [A Deep Learning Localization Method for Measuring Abdominal Muscle Dimensions in Ultrasound Images](https://mlsanity.com/paper/2109.14919/) (2021)
- [EM-Paste: EM-guided Cut-Paste with DALL-E Augmentation for Image-level Weakly Supervised Instance Segmentation](https://mlsanity.com/paper/2212.07629/) (2022)
- [Self-supervised Learning for Panoptic Segmentation of Multiple Fruit Flower Species](https://mlsanity.com/paper/2209.04618/) (2022)
- [ENInst: Enhancing Weakly-supervised Low-shot Instance Segmentation](https://mlsanity.com/paper/2302.09765/) (2023)
- [P2Seg: Pointly-supervised Segmentation via Mutual Distillation](https://mlsanity.com/paper/2401.09709/) (2024)

## Abstract (arXiv)

A major obstacle in instance segmentation is that existing methods often need many per-pixel labels in order to be effective. These labels require large human effort and for certain applications, such labels are not readily available. To address this limitation, we propose a novel framework that can effectively train with image-level labels, which are significantly cheaper to acquire. For instance, one can do an internet search for the term "car" and obtain many images where a car is present with minimal effort. Our framework consists of two stages: (1) train a classifier to generate pseudo masks for the objects of interest; (2) train a fully supervised Mask R-CNN on these pseudo masks. Our two main contribution are proposing a pipeline that is simple to implement and is amenable to different segmentation methods; and achieves new state-of-the-art results for this problem setup. Our results are based on evaluating our method on PASCAL VOC 2012, a standard dataset for weakly supervised methods, where we demonstrate major performance gains compared to existing methods with respect to mean average precision.