DeepAI AI Chat
Log In Sign Up

Few-Shot Learning via Saliency-guided Hallucination of Samples

by   Hongguang Zhang, et al.

Learning new concepts from a few of samples is a standard challenge in computer vision. The main directions to improve the learning ability of few-shot training models include (i) a robust similarity learning and (ii) generating or hallucinating additional data from the limited existing samples. In this paper, we follow the latter direction and present a novel data hallucination model. Currently, most datapoint generators contain a specialized network (i.e., GAN) tasked with hallucinating new datapoints, thus requiring large numbers of annotated data for their training in the first place. In this paper, we propose a novel less-costly hallucination method for few-shot learning which utilizes saliency maps. To this end, we employ a saliency network to obtain the foregrounds and backgrounds of available image samples and feed the resulting maps into a two-stream network to hallucinate datapoints directly in the feature space from viable foreground-background combinations. To the best of our knowledge, we are the first to leverage saliency maps for such a task and we demonstrate their usefulness in hallucinating additional datapoints for few-shot learning. Our proposed network achieves the state of the art on publicly available datasets.


page 4

page 5

page 8

page 9

page 10


Dense Classification and Implanting for Few-Shot Learning

Training deep neural networks from few examples is a highly challenging ...

Multimodal Prototypical Networks for Few-shot Learning

Although providing exceptional results for many computer vision tasks, s...

XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning

Learning novel concepts while preserving prior knowledge is a long-stand...

Integrative Few-Shot Learning for Classification and Segmentation

We introduce the integrative task of few-shot classification and segment...

Deep Low-Shot Learning for Biological Image Classification and Visualization from Limited Training Samples

Predictive modeling is useful but very challenging in biological image a...

Mask-guided Vision Transformer (MG-ViT) for Few-Shot Learning

Learning with little data is challenging but often inevitable in various...

Deep Reinforcement One-Shot Learning for Artificially Intelligent Classification Systems

In recent years there has been a sharp rise in networking applications, ...