# MIML-FCN+: Multi-instance Multi-label Learning via Fully Convolutional Networks with Privileged Information

## TL;DR

This paper introduces MIML-FCN+, a novel fully convolutional network that leverages privileged bag-level information in multi-instance multi-label learning, improving multi-object recognition performance.

## Contribution

It proposes a new two-stream FCN with a convex PI loss to utilize privileged bags, enhancing MIML learning with practical, readily available information.

## Key findings

- Outperforms state-of-the-art methods on benchmark datasets
- Effectively utilizes privileged bag information during training
- Demonstrates improved multi-object recognition accuracy

## Abstract

Multi-instance multi-label (MIML) learning has many interesting applications in computer visions, including multi-object recognition and automatic image tagging. In these applications, additional information such as bounding-boxes, image captions and descriptions is often available during training phrase, which is referred as privileged information (PI). However, as existing works on learning using PI only consider instance-level PI (privileged instances), they fail to make use of bag-level PI (privileged bags) available in MIML learning. Therefore, in this paper, we propose a two-stream fully convolutional network, named MIML-FCN+, unified by a novel PI loss to solve the problem of MIML learning with privileged bags. Compared to the previous works on PI, the proposed MIML-FCN+ utilizes the readily available privileged bags, instead of hard-to-obtain privileged instances, making the system more general and practical in real world applications. As the proposed PI loss is convex and SGD compatible and the framework itself is a fully convolutional network, MIML-FCN+ can be easily integrated with state of-the-art deep learning networks. Moreover, the flexibility of convolutional layers allows us to exploit structured correlations among instances to facilitate more effective training and testing. Experimental results on three benchmark datasets demonstrate the effectiveness of the proposed MIML-FCN+, outperforming state-of-the-art methods in the application of multi-object recognition.