Few-shot Learning with Multi-scale Self-supervision

01/06/2020
by   Hongguang Zhang, et al.
0

Learning concepts from the limited number of datapoints is a challenging task usually addressed by the so-called one- or few-shot learning. Recently, an application of second-order pooling in few-shot learning demonstrated its superior performance due to the aggregation step handling varying image resolutions without the need of modifying CNNs to fit to specific image sizes, yet capturing highly descriptive co-occurrences. However, using a single resolution per image (even if the resolution varies across a dataset) is suboptimal as the importance of image contents varies across the coarse-to-fine levels depending on the object and its class label e. g., generic objects and scenes rely on their global appearance while fine-grained objects rely more on their localized texture patterns. Multi-scale representations are popular in image deblurring, super-resolution and image recognition but they have not been investigated in few-shot learning due to its relational nature complicating the use of standard techniques. In this paper, we propose a novel multi-scale relation network based on the properties of second-order pooling to estimate image relations in few-shot setting. To optimize the model, we leverage a scale selector to re-weight scale-wise representations based on their second-order features. Furthermore, we propose to a apply self-supervised scale prediction. Specifically, we leverage an extra discriminator to predict the scale labels and the scale discrepancy between pairs of images. Our model achieves state-of-the-art results on standard few-shot learning datasets.

READ FULL TEXT
research
01/15/2022

Multi-level Second-order Few-shot Learning

We propose a Multi-level Second-order (MlSo) few-shot learning network f...
research
11/10/2018

Power Normalizing Second-order Similarity Network for Few-shot Learning

Second- and higher-order statistics of data points have played an import...
research
01/12/2022

Coarse-to-Fine Embedded PatchMatch and Multi-Scale Dynamic Aggregation for Reference-based Super-Resolution

Reference-based super-resolution (RefSR) has made significant progress i...
research
05/25/2021

Improving Few-shot Learning with Weakly-supervised Object Localization

Few-shot learning often involves metric learning-based classifiers, whic...
research
01/13/2021

Learning to Focus: Cascaded Feature Matching Network for Few-shot Image Recognition

Deep networks can learn to accurately recognize objects of a category by...
research
01/12/2020

Rethinking Class Relations: Absolute-relative Few-shot Learning

The majority of existing few-shot learning describe image relations with...
research
02/14/2023

Event-guided Multi-patch Network with Self-supervision for Non-uniform Motion Deblurring

Contemporary deep learning multi-scale deblurring models suffer from man...

Please sign up or login with your details

Forgot password? Click here to reset