# Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts

arXiv: https://arxiv.org/abs/2008.01178 · HTML: https://mlsanity.com/paper/2008.01178/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Aug 2020.

## Built on by (most cited first, 10 of 10)

- [Improving Object Detection in Art Images Using Only Style Transfer](https://mlsanity.com/paper/2102.06529/) (2021)
- [Mixed Supervised Object Detection by Transferring Mask Prior and Semantic Similarity](https://mlsanity.com/paper/2110.14191/) (2021)
- [Semi-supervised Human Pose Estimation in Art-historical Images](https://mlsanity.com/paper/2207.02976/) (2022)
- [Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art History](https://mlsanity.com/paper/2301.05124/) (2023)
- [Self-Supervision Enhances Instance-based Multiple Instance Learning Methods in Digital Pathology: A Benchmark Study](https://mlsanity.com/paper/2505.01109/) (2025)
- [Investigating Modality Bias in Audio Visual Video Parsing](https://mlsanity.com/paper/2203.16860/) (2022)
- [LOCL: Learning Object-Attribute Composition using Localization](https://mlsanity.com/paper/2210.03780/) (2022)
- [Context-Infused Visual Grounding for Art](https://mlsanity.com/paper/2410.12369/) (2024)
- [No Annotations for Object Detection in Art through Stable Diffusion](https://mlsanity.com/paper/2412.06286/) (2024)
- [Large-image Object Detection for Fine-grained Recognition of Punches Patterns in Medieval Panel Painting](https://mlsanity.com/paper/2501.12489/) (2025)

## Abstract (arXiv)

Weakly supervised object detection (WSOD) using only image-level annotations has attracted a growing attention over the past few years. Whereas such task is typically addressed with a domain-specific solution focused on natural images, we show that a simple multiple instance approach applied on pre-trained deep features yields excellent performances on non-photographic datasets, possibly including new classes. The approach does not include any fine-tuning or cross-domain learning and is therefore efficient and possibly applicable to arbitrary datasets and classes. We investigate several flavors of the proposed approach, some including multi-layers perceptron and polyhedral classifiers. Despite its simplicity, our method shows competitive results on a range of publicly available datasets, including paintings (People-Art, IconArt), watercolors, cliparts and comics and allows to quickly learn unseen visual categories.