Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input
This addresses the challenge of multimodal learning for AI systems by enabling unsupervised discovery of visual objects and spoken words, though it is incremental as it builds on existing retrieval tasks.
The paper tackles the problem of learning to associate spoken audio captions with relevant image regions without any explicit supervision, demonstrating that neural networks can implicitly learn semantically-coupled object and word detectors from raw sensory input.
In this paper, we explore neural network models that learn to associate segments of spoken audio captions with the semantically relevant portions of natural images that they refer to. We demonstrate that these audio-visual associative localizations emerge from network-internal representations learned as a by-product of training to perform an image-audio retrieval task. Our models operate directly on the image pixels and speech waveform, and do not rely on any conventional supervision in the form of labels, segmentations, or alignments between the modalities during training. We perform analysis using the Places 205 and ADE20k datasets demonstrating that our models implicitly learn semantically-coupled object and word detectors.