CVPR 2019

Label Set Operations (LaSO) Networks for Multi-Label Few-Shot Learning

Data augmentation is one of the leading methods to tackle the problem of few-shot learning, but current synthesis approaches only address the scenario of a single label per image, when in reality real life images may contain multiple objects. The IBM team came up with a novel technique for synthesizing samples with multiple labels.

Continue reading

RepMet: Representative-Based Metric Learning for Classification and Few-Shot Object Detection

Deep neural networks have demonstrated good results for few-shot learning. However, very few works have investigated the problem of few-shot object detection. A team of IBM researchers developed a novel approach for Distance Metric Learning (DML).

Continue reading

IBM Research AI at CVPR 2019

The annual conference on Computer Vision and Pattern Recognition (CVPR 2019) takes place June 16–20 in Long Beach, CA. There, IBM Research AI will present technical papers describing our latest results in our quest to give AI systems sight.

Continue reading