# Deep Multiple Instance Learning for Zero-shot Image Tagging

arXiv: https://arxiv.org/abs/1803.06051 · HTML: https://mlsanity.com/paper/1803.06051/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Mar 2018.

## Built on by (most cited first, 8 of 8)

- [DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations](https://mlsanity.com/paper/2206.09541/) (2022)
- [Zero-Shot Learning on 3D Point Cloud Objects and Beyond](https://mlsanity.com/paper/2104.04980/) (2021)
- [DualCoOp++: Fast and Effective Adaptation to Multi-Label Recognition with Limited Annotations](https://mlsanity.com/paper/2308.01890/) (2023)
- [Recover and Match: Open-Vocabulary Multi-Label Recognition through Knowledge-Constrained Optimal Transport](https://mlsanity.com/paper/2503.15337/) (2025)
- [Diverse and Tailored Image Generation for Zero-shot Multi-label Classification](https://mlsanity.com/paper/2404.03144/) (2024)
- [Category-Adaptive Cross-Modal Semantic Refinement and Transfer for Open-Vocabulary Multi-Label Recognition](https://mlsanity.com/paper/2412.06190/) (2024)
- [DART: Dual Adaptive Refinement Transfer for Open-Vocabulary Multi-Label Recognition](https://mlsanity.com/paper/2508.05585/) (2025)
- [Recursive Training for Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/2103.00086/) (2021)

## Abstract (arXiv)

In-line with the success of deep learning on traditional recognition problem, several end-to-end deep models for zero-shot recognition have been proposed in the literature. These models are successful to predict a single unseen label given an input image, but does not scale to cases where multiple unseen objects are present. In this paper, we model this problem within the framework of Multiple Instance Learning (MIL). To the best of our knowledge, we propose the first end-to-end trainable deep MIL framework for the multi-label zero-shot tagging problem. Due to its novel design, the proposed framework has several interesting features: (1) Unlike previous deep MIL models, it does not use any off-line procedure (e.g., Selective Search or EdgeBoxes) for bag generation. (2) During test time, it can process any number of unseen labels given their semantic embedding vectors. (3) Using only seen labels per image as weak annotation, it can produce a bounding box for each predicted labels. We experiment with the NUS-WIDE dataset and achieve superior performance across conventional, zero-shot and generalized zero-shot tagging tasks.