Few-Shot Learning via Embedding Adaptation With Set-to-Set Functions

Ye, Han-Jia; Hu, Hexiang; Zhan, De-Chuan; Sha, Fei

doi:10.1109/cvpr42600.2020.00883

Cited by 534 publications

(288 citation statements)

References 15 publications

Supporting

Mentioning

287

Contrasting

Order By: Relevance

“…1. Metric learning methods (i.e., MatchingNets, 113 ProtoNets, 114 RelationNets, 115 Graph neural network (GraphNN), 116 Ridge regression, 117 TransductiveProp, 118 Fine-tuning Baseline, 119 URT, 120 DSN-MR, 121 CDFS, 122 DeepEMD, 123 EPNet, 124 ACC + Amphibian, 125 FEAT, 126 T A B L E 3 (Continued)…”

Section: Discussion About Different Meta-learningsmentioning

confidence: 99%

“…We can divide meta‐learning methods into three categories 140 : Metric learning methods (i.e., MatchingNets, 113 ProtoNets, 114 RelationNets, 115 Graph neural network (GraphNN), 116 Ridge regression, 117 TransductiveProp, 118 Fine‐tuning Baseline, 119 URT, 120 DSN‐MR, 121 CDFS, 122 DeepEMD, 123 EPNet, 124 ACC + Amphibian, 125 FEAT, 126 MsSoSN + SS + SD + DD, 127 RFS, 128 RFS + CRAT, 129 IDA, 130 LR + ICI, 131 FEAT + MLMT, 132 BOHB, 133 CSPN, 134 SUR, 135 SKD, 136 TAFSSL, 137 TRPN, 138 and TransMatch 139 ) learn a similarity space in which learning is particularly efficient for few‐shot examples. Memory network methods (i.e., Meta Networks, 103 TADAM, 104 MCFS, 105 and MRN 106 ) learn to store “experience” when learning seen tasks and then generalize it to unseen tasks. …”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Fighting fire with fire: A spatial–frequency ensemble relation network with generative adversarial learning for adversarial image classification

et al. 2021

View full text Add to dashboard Cite

Adversarial images generated by generative adversarial networks are not close to any existing benign images, and contain nonrobust features that have been identified as critical to the robustness of a machine learning model. Since adversarial images have an underlying distribution that differs from normal images, these kinds of images can offer valuable features for training a robust model. To deal with these special features, we focus on a novel machine learning task of adversarial images classification, where adversarial images can be used to investigate the problem of classifying adversarial images themselves. In the setting of this novel task, adversarial images are the ONLY kind of data used in training and testing, rather than not just a set of testing images as usual. To this end, we propose a novel spatial–frequency ensemble relation network with generative adversarial learning. First, we present a spatial–frequency ensemble representation learning to extract the feature of training images. Second, we design a meta‐learning‐based relation model to gain the relationship between images. Third, to achieve a robust model, we utilize generative adversarial learning and transform the relationship into a Jacobian matrix. Finally, we design a discriminator model that determines whether an adversarial image is from the matching category or not. Experimental results demonstrate that our approach achieves significantly higher performance compared with other state‐of‐the‐arts.

show abstract

Section: Discussion About Different Meta-learningsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Fighting fire with fire: A spatial–frequency ensemble relation network with generative adversarial learning for adversarial image classification

et al. 2021

View full text Add to dashboard Cite

show abstract

“…TADAM [ 51 ] boosts the performance of ProtoNets by metric scaling, task-conditioning, and auxiliary task co-training. MetaOptNet [ 52 ] and FEAT [ 54 ] follow the same spirit of learning task-specific embeddings to ensure the features are more discriminative for a given task.…”

Section: Related Workmentioning

confidence: 99%

RS-SSKD: Self-Supervision Equipped with Knowledge Distillation for Few-Shot Remote Sensing Scene Classification

Zhang

Wang

et al. 2021

Sensors

View full text Add to dashboard Cite

While growing instruments generate more and more airborne or satellite images, the bottleneck in remote sensing (RS) scene classification has shifted from data limits toward a lack of ground truth samples. There are still many challenges when we are facing unknown environments, especially those with insufficient training data. Few-shot classification offers a different picture under the umbrella of meta-learning: digging rich knowledge from a few data are possible. In this work, we propose a method named RS-SSKD for few-shot RS scene classification from a perspective of generating powerful representation for the downstream meta-learner. Firstly, we propose a novel two-branch network that takes three pairs of original-transformed images as inputs and incorporates Class Activation Maps (CAMs) to drive the network mining, the most relevant category-specific region. This strategy ensures that the network generates discriminative embeddings. Secondly, we set a round of self-knowledge distillation to prevent overfitting and boost the performance. Our experiments show that the proposed method surpasses current state-of-the-art approaches on two challenging RS scene datasets: NWPU-RESISC45 and RSD46-WHU. Finally, we conduct various ablation experiments to investigate the effect of each component of the proposed method and analyze the training time of state-of-the-art methods and ours.

show abstract

“…Hallucinator [47,2018] Saliency Network [48,2019] Learning task-specific features TADAM [22,2018] LGM-Net [27,2019] CTM [39,2019] FEAT [28,2020] XtarNet [40,2020] Learning via multi-task learning Self-supervised FSL [49,2019] TADAM [22,2018] Meta-learning for semi-supervised fewshot classification…”

Section: Learning With Data Augmentationmentioning

confidence: 99%

Revisiting metric learning for few-shot image classification

et al. 2020

Neurocomputing

View full text Add to dashboard Cite

The goal of few-shot learning is to recognize new visual concepts with just a few amount of labeled samples in each class. Recent effective metric-based few-shot approaches employ neural networks to learn a feature similarity comparison between query and support examples. However, the importance of feature embedding, i.e., exploring the relationship among training samples, is neglected. In this work, we present a simple yet powerful baseline for few-shot classification by emphasizing the importance of feature embedding. Specifically, we revisit the classical triplet network from deep metric learning, and extend it into a deep K-tuplet network for few-shot learning, utilizing the relationship among the input samples to learn a general representation learning via episode-training. Once trained, our network is able to extract discriminative features for unseen novel categories and can be seamlessly incorporated with a non-linear distance metric function to facilitate the few-shot classification. Our result on the miniImageNet benchmark outperforms other metric-based few-shot classification methods. More importantly, when evaluated on completely different datasets (Caltech-101, CUB-200, Stanford Dogs and Cars) using the model trained with miniImageNet, our method significantly outperforms prior methods, demonstrating its superior capability to generalize to unseen classes.

show abstract

Few-Shot Learning via Embedding Adaptation With Set-to-Set Functions

Cited by 534 publications

References 15 publications

Fighting fire with fire: A spatial–frequency ensemble relation network with generative adversarial learning for adversarial image classification

Fighting fire with fire: A spatial–frequency ensemble relation network with generative adversarial learning for adversarial image classification

RS-SSKD: Self-Supervision Equipped with Knowledge Distillation for Few-Shot Remote Sensing Scene Classification

Revisiting metric learning for few-shot image classification

Contact Info

Product

Resources

About