Transductive Episodic-Wise Adaptive Metric for Few-Shot Learning

By Limeng Qiao, Yemin Shi, Jia Li, Yaowei Wang, Tiejun Huang, Yonghong Tian. 2019

197 citations recorded by the source corpus.

Few-shot learning, which aims at extracting new concepts rapidly from extremely few examples of novel classes, has been featured into the meta-learning paradigm recently. Yet, the key challenge of how to learn a generalizable classifier with the capability of adapting to specific tasks with severely limited data still remains in this domain. To this end, we propose a Transductive Episodic-wise Adaptive Metric (TEAM) framework for few-shot learning, by integrating the meta-learning paradigm with both deep metric learning and transductive inference. With exploring the pairwise constraints and regularization prior within each task, we explicitly formulate the adaptation procedure into a standard semi-definite programming problem. By solving the problem with its closed-form solution on the fly with the setup of transduction, our approach efficiently tailors an episodic-wise metric for each task to adapt all features from a shared task-agnostic embedding space into a more discriminative task-specific metric space. Moreover, we further leverage an attention-based bi-directional similarity strategy for extracting the more robust relationship between queries and prototypes. Extensive experiments on three benchmark datasets show that our framework is superior to other existing approaches and achieves the state-of-the-art performance in the few-shot literature.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Meta & Continual Learning

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

In Meta & Continual Learning

Citations in the corpus

Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need? (2020, neutral): “7 ± n/a TEWAM [37] ResNet-12 70.”
Few-Shot Learning via Embedding Adaptation With Set-to-Set Functions (2018, methodology): “We cite the results of Semi-ProtoNet and TPN from [16] and [14] respectively.”
Compositional Few-Shot Recognition with Primitive Discovery and Enhancing (2020, methodology): “hmarks, while experiments on few-shot video classification are conducted on the Kinetics dataset [30]. CUB contains 200 fine-grained bird classes and 11,788 images in total. Following the settings in [8, 45], we split the dataset into 100 training classes, 50 validation classes and 50 test classes. ”
DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection (2021, background): “In the literature, a large amount of studies that follow the idea of meta-learning to alleviate severe over-fitting can be divided into two streams, namely, optimization approaches [1, 13, 22, 26, 30, 32] and metric approaches [21, 29, 38, 40, 44].”
BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network (2020, methodology): “ multi-level feature fusion [37] is essential for many computer vision tasks, such as object detection [8,21,26,68], semantic segmentation [29,30, 32,65], co-attention tasks [19,70] and classication [38,40,51]. Here, we attempt to utilize this idea for RGB-D salient object detection (SOD) [4,72], wh”
Proxy Anchor Loss for Deep Metric Learning (2020, background): “Learning a semantic distance metric has been a crucial step for many applications such as content-based image retrieval [14, 21, 27, 29], face verification [18, 25], person re-identification [3, 38], few-shot learning [24, 26, 30], and representation learning [14, 33, 41].”