Towards Contextual Learning in Few-shot Object Classification
This addresses a limitation in few-shot learning for computer vision by enabling better classification in realistic, multi-object scenes, though it is incremental as it builds on existing methods.
The paper tackles the problem of few-shot object classification in complex scenes with multiple objects, proposing plug-and-play modules that leverage contextual learning to improve performance, achieving superior results on Visual Genome and Open Images datasets.
Few-shot Learning (FSL) aims to classify new concepts from a small number of examples. While there have been an increasing amount of work on few-shot object classification in the last few years, most current approaches are limited to images with only one centered object. On the opposite, humans are able to leverage prior knowledge to quickly learn new concepts, such as semantic relations with contextual elements. Inspired by the concept of contextual learning in educational sciences, we propose to make a step towards adopting this principle in FSL by studying the contribution that context can have in object classification in a low-data regime. To this end, we first propose an approach to perform FSL on images of complex scenes. We develop two plug-and-play modules that can be incorporated into existing FSL methods to enable them to leverage contextual learning. More specifically, these modules are trained to weight the most important context elements while learning a particular concept, and then use this knowledge to ground visual class representations in context semantics. Extensive experiments on Visual Genome and Open Images show the superiority of contextual learning over learning individual objects in isolation.