Relational Generalized Few-Shot Learning

By Xiahan Shi, Leonard Salewski, Martin Schiegg, Zeynep Akata, Max Welling. 2019

27 citations recorded by the source corpus.

Transferring learned models to novel tasks is a challenging problem, particularly if only very few labeled examples are available. Although this few-shot learning setup has received a lot of attention recently, most proposed methods focus on discriminating novel classes only. Instead, we consider the extended setup of generalized few-shot learning (GFSL), where the model is required to perform classification on the joint label space consisting of both previously seen and novel classes. We propose a graph-based framework that explicitly models relationships between all seen and novel classes in the joint label space. Our model Graph-convolutional Global Prototypical Networks (GcGPN) incorporates these inter-class relations using graph-convolution in order to embed novel class representations into the existing space of previously seen classes in a globally consistent manner. Our approach ensures both fast adaptation and global discrimination, which is the major challenge in GFSL. We demonstrate the benefits of our model on two challenging benchmark datasets.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgetting (2021, methodology): “For the state-of-the-art comparison, we average over 600 episodes [39, 27, 8], for all other experiments over 100 episodes.”
CG-BERT: Conditional Text Generation with BERT for Generalized Few-shot Intent Detection (2020, methodology): “The performance of FSL models deteriorates drastically in discriminating the joint label space, despite their good performance on novel label space (Shi et al., 2019).”
Progressive One-shot Human Parsing (2020, unknown): “…in OS3, while both base classes and novel classes should be recognized simultaneously during evaluation in OSHP as shown in Figure 1 (b), which is indeed a variant of generalized few-shot learning (GFSL) problem (Gidaris and Komodakis 2018; Ren et al. 2019; Shi et al. 2019; Ye et al. 2019).”
Semantic Matching and Aggregation Network for Few-shot Intent Detection (2020, methodology): “The sampling procedure for GFSL is conducted in a similar way as (Shi et al., 2019).”