# Fully Convolutional Multi-Class Multiple Instance Learning

arXiv: https://arxiv.org/abs/1412.7144 · HTML: https://mlsanity.com/paper/1412.7144/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Dec 2014.

## Built on by (most cited first, 30 of 37)

- [DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification](https://mlsanity.com/paper/2203.12081/) (2022)
- [Mixed supervision for surface-defect detection: from weakly to fully supervised learning](https://mlsanity.com/paper/2104.06064/) (2021)
- [L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2204.03206/) (2022)
- [Unsupervised Semantic Segmentation with Self-supervised Object-centric Representations](https://mlsanity.com/paper/2207.05027/) (2022)
- [LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds](https://mlsanity.com/paper/2210.08064/) (2022)
- [Every Annotation Counts: Multi-label Deep Supervision for Medical Image Segmentation](https://mlsanity.com/paper/2104.13243/) (2021)
- [Referring Image Segmentation Using Text Supervision](https://mlsanity.com/paper/2308.14575/) (2023)
- [Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision](https://mlsanity.com/paper/2108.07682/) (2021)
- [Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentation](https://mlsanity.com/paper/2307.03407/) (2023)
- [A Spacecraft Dataset for Detection, Segmentation and Parts Recognition](https://mlsanity.com/paper/2106.08186/) (2021)
- [Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learning](https://mlsanity.com/paper/2309.01246/) (2023)
- [An Alternative to WSSS? An Empirical Study of the Segment Anything Model (SAM) on Weakly-Supervised Semantic Segmentation Problems](https://mlsanity.com/paper/2305.01586/) (2023)
- [Regression-based Deep-Learning predicts molecular biomarkers from pathology slides](https://mlsanity.com/paper/2304.05153/) (2023)
- [USAGE: A Unified Seed Area Generation Paradigm for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2303.07806/) (2023)
- [Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentation](https://mlsanity.com/paper/2108.07413/) (2021)
- [SOAR: Scene-debiasing Open-set Action Recognition](https://mlsanity.com/paper/2309.01265/) (2023)
- [Latent Space Regularization for Unsupervised Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2104.02633/) (2021)
- [ZScribbleSeg: Zen and the Art of Scribble Supervised Medical Image Segmentation](https://mlsanity.com/paper/2301.04882/) (2023)
- [Mixed-UNet: Refined Class Activation Mapping for Weakly-Supervised Semantic Segmentation with Multi-scale Inference](https://mlsanity.com/paper/2205.04227/) (2022)
- [Label-efficient Segmentation via Affinity Propagation](https://mlsanity.com/paper/2310.10533/) (2023)
- [Bag Graph: Multiple Instance Learning using Bayesian Graph Neural Networks](https://mlsanity.com/paper/2202.11132/) (2022)
- [Differentiable Projection for Constrained Deep Learning](https://mlsanity.com/paper/2111.10785/) (2021)
- [Open Vocabulary Semantic Scene Sketch Understanding](https://mlsanity.com/paper/2312.12463/) (2023)
- [Weakly-Supervised Image Forgery Localization via Vision-Language Collaborative Reasoning Framework](https://mlsanity.com/paper/2508.01338/) (2025)
- [Boundary-RL: Reinforcement Learning for Weakly-Supervised Prostate Segmentation in TRUS Images](https://mlsanity.com/paper/2308.11376/) (2023)
- [Key Patches Are All You Need: A Multiple Instance Learning Framework For Robust Medical Diagnosis](https://mlsanity.com/paper/2405.01654/) (2024)
- [Partial Scene Text Retrieval](https://mlsanity.com/paper/2411.10261/) (2024)
- [ISIM: Iterative Self-Improved Model for Weakly Supervised Segmentation](https://mlsanity.com/paper/2211.12455/) (2022)
- [Weakly-supervised detection of AMD-related lesions in color fundus images using explainable deep learning](https://mlsanity.com/paper/2212.00565/) (2022)
- [Context-Aware Weakly Supervised Image Manipulation Localization with SAM Refinement](https://mlsanity.com/paper/2503.20294/) (2025)

## Abstract (arXiv)

Multiple instance learning (MIL) can reduce the need for costly annotation in tasks such as semantic segmentation by weakening the required degree of supervision. We propose a novel MIL formulation of multi-class semantic segmentation learning by a fully convolutional network. In this setting, we seek to learn a semantic segmentation model from just weak image-level labels. The model is trained end-to-end to jointly optimize the representation while disambiguating the pixel-image label assignment. Fully convolutional training accepts inputs of any size, does not need object proposal pre-processing, and offers a pixelwise loss map for selecting latent instances. Our multi-class MIL loss exploits the further supervision given by images with multiple labels. We evaluate this approach through preliminary experiments on the PASCAL VOC segmentation challenge.