Incorporating Copying Mechanism in Image Captioning for Learning Novel Objects
This addresses the limitation of requiring large training datasets for image captioning, enabling description of novel objects, though it is an incremental improvement on existing frameworks.
The paper tackles the problem of image captioning models being unable to describe objects not seen during training by proposing LSTM-C, which integrates a copying mechanism to incorporate novel objects from external datasets, achieving superior results compared to state-of-the-art models.
Image captioning often requires a large set of training image-sentence pairs. In practice, however, acquiring sufficient training pairs is always expensive, making the recent captioning models limited in their ability to describe objects outside of training corpora (i.e., novel objects). In this paper, we present Long Short-Term Memory with Copying Mechanism (LSTM-C) --- a new architecture that incorporates copying into the Convolutional Neural Networks (CNN) plus Recurrent Neural Networks (RNN) image captioning framework, for describing novel objects in captions. Specifically, freely available object recognition datasets are leveraged to develop classifiers for novel objects. Our LSTM-C then nicely integrates the standard word-by-word sentence generation by a decoder RNN with copying mechanism which may instead select words from novel objects at proper places in the output sentence. Extensive experiments are conducted on both MSCOCO image captioning and ImageNet datasets, demonstrating the ability of our proposed LSTM-C architecture to describe novel objects. Furthermore, superior results are reported when compared to state-of-the-art deep models.