Adversarial Feature Hallucination Networks for Few-Shot Learning

By K. Li, Yulun Zhang, Kunpeng Li, Yun Raymond Fu. 2020

302 citations recorded by the source corpus.

The recent flourish of deep learning in various tasks is largely accredited to the rich and accessible labeled data. Nonetheless, massive supervision remains a luxury for many real applications, boosting great interest in label-scarce techniques such as few-shot learning (FSL), which aims to learn concept of new classes with a few labeled samples. A natural approach to FSL is data augmentation and many recent works have proved the feasibility by proposing various data synthesis models. However, these models fail to well secure the discriminability and diversity of the synthesized data and thus often produce undesirable results. In this paper, we propose Adversarial Feature Hallucination Networks (AFHN) which is based on conditional Wasserstein Generative Adversarial networks (cWGAN) and hallucinates diverse and discriminative features conditioned on the few labeled samples. Two novel regularizers, i.e., the classification regularizer and the anti-collapse regularizer, are incorporated into AFHN to encourage discriminability and diversity of the synthesized features, respectively. Ablation study verifies the effectiveness of the proposed cWGAN based feature hallucination framework and the proposed regularizers. Comparative results on three common benchmark datasets substantiate the superiority of AFHN to existing data augmentation based FSL approaches and other state-of-the-art ones.

Subfields: Artificial Intelligence, Radiology, Nuclear Medicine and Imaging

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 Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning (2021, methodology): “Augmentation-based methods [14] synthesize more data from the novel classes in different ways to facilitate standard learning.”
Few-Shot Learning With a Strong Teacher (2021, background): “Data augmentation approaches hallucinate additional examples of novel classes based on their few examples [41], [42], [43].”
Camouflaged Object Detection with Feature Decomposition and Edge Reconstruction (2023, methodology): “Unlike existing heuristic-based feature aggregation strategies simply using concatenation [22, 24], GFA is specifically designed to address the key issue of COD, i.”
DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning (2020, background): “classification problem, such as works based on graph theories [66], [67], [68], [69], reinforcement learning [70], differentiable SVM [71], generative models [72], [73], [74], [75], [76], [77], [78], [79], [80], transductive learning [81], [82], [83], [84], [85], recurrent models [86], [87], self-su”
A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities (2022, methodology): “Li et al. [58] proposed the adversarial feature phantom network-AFHN.”
Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networks (2021, background): “In the GAN domain, various models and training strategies have been proposed for few-shot domain adaptation tasks (Bousmalis et al., 2017; ZHANG et al., 2018; Li et al., 2020; Liu et al., 2019).”
Semantics-Driven Generative Replay for Few-Shot Class Incremental Learning (2022, methodology): “Our GAN model, though, is different from that of [16, 19] as we use a novel anti mode collapse regularizer to deal with mode-collapse and we constrain the generated feature space as per a latent semantic space to enforce discriminability.”