MIML-FCN+: Multi-instance Multi-label Learning via Fully Convolutional Networks with Privileged Information
This work addresses a specific bottleneck in computer vision applications like image tagging by enabling the use of more readily available bag-level privileged information, though it is incremental as it builds on existing PI and MIML frameworks.
The paper tackles the problem of multi-instance multi-label learning with privileged information by proposing MIML-FCN+, a two-stream fully convolutional network with a novel PI loss that utilizes bag-level privileged information instead of instance-level, making it more practical. Experimental results on three benchmark datasets show it outperforms state-of-the-art methods in multi-object recognition.
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.