# Relaxed Multiple-Instance SVM with Application to Object Discovery

arXiv: https://arxiv.org/abs/1510.01027 · HTML: https://mlsanity.com/paper/1510.01027/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Oct 2015.

## Built on by (most cited first, 7 of 7)

- [Weakly Supervised Object Localization and Detection: A Survey](https://mlsanity.com/paper/2104.07918/) (2021)
- [All Grains, One Scheme (AGOS): Learning Multi-grain Instance Representation for Aerial Scene Classification](https://mlsanity.com/paper/2205.03371/) (2022)
- [Contrastive Proposal Extension with LSTM Network for Weakly Supervised Object Detection](https://mlsanity.com/paper/2110.07511/) (2021)
- [Cross-Level Multi-Instance Distillation for Self-Supervised Fine-Grained Visual Categorization](https://mlsanity.com/paper/2401.08860/) (2024)
- [Two-phase weakly supervised object detection with pseudo ground truth mining](https://mlsanity.com/paper/2104.00231/) (2021)
- [PGTRNet: Two-phase Weakly Supervised Object Detection with Pseudo Ground Truth Refinement](https://mlsanity.com/paper/2108.11439/) (2021)
- [HUWSOD: Holistic Self-training for Unified Weakly Supervised Object Detection](https://mlsanity.com/paper/2406.19394/) (2024)

## Abstract (arXiv)

Multiple-instance learning (MIL) has served as an important tool for a wide range of vision applications, for instance, image classification, object detection, and visual tracking. In this paper, we propose a novel method to solve the classical MIL problem, named relaxed multiple-instance SVM (RMI-SVM). We treat the positiveness of instance as a continuous variable, use Noisy-OR model to enforce the MIL constraints, and jointly optimize the bag label and instance label in a unified framework. The optimization problem can be efficiently solved using stochastic gradient decent. The extensive experiments demonstrate that RMI-SVM consistently achieves superior performance on various benchmarks for MIL. Moreover, we simply applied RMI-SVM to a challenging vision task, common object discovery. The state-of-the-art results of object discovery on Pascal VOC datasets further confirm the advantages of the proposed method.