Few-Shot Learning With Localization in Realistic Settings

Wertheimer, Davis; Hariharan, Bharath

doi:10.1109/cvpr.2019.00672

Cited by 123 publications

(90 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It shows that when learning non-linear metric methods, with other network added, the training parameters in the model are increasing, it is easy for the network to overfit so as to cause a bad result. Besides, we compare our result with 17 state-of-the-art meta-metric learning algorithms, which are D-SVS [33], SN [34], SRPN [35], PML [29], DN4 [29], PCP [21], LCC [36], L2AE-D [37], IMP [23], PN [38], METRIC1 [39], DC [17], CovaMNET [40], AM3 [22], VFL [41], SHS [42], PARN [43]. As is shown in FIGURE 4, our results by combining Matching Network with fine-tuned ResNet50 outperform all of the state-of-the-art results, which illustrates the importance of transfer learning.…”

Section: )mentioning

confidence: 99%

Comparative Analysis on Classical Meta-Metric Models for Few-Shot Learning

Yang

Liu

2020

IEEE Access

View full text Add to dashboard Cite

Few-shot learning are methods and scenarios learned from a small amount of labeled data. While recent meta-metric learning methods have made significant progress, there are still questions about what is the key point of these methods and how they work. To address these problems, in this paper, we evaluate the effects of different parts in classical models. To be specific, we 1) use four typical networks AlexNet, VGG16, GoogLeNet, and ResNet50 to replace the original feature extraction part in the Matching Network, Prototypical Network, and Relation Network, and compare the best results with 17 state-of-the-art meta-metric learning algorithms. 2) fix the feature extraction part of the Matching Network, Prototypical Network and Relation Network, and change the similarity measurement part of each into L1, L2, Cosine. 3) conduct above three models on datasets of different granularity. The experimental results show that for all models evaluated, the addition of non-pretrained networks will make the classification results worse, which shows that it is easy to overfit when using deep networks for few-shot learning. Changes in similarity measurement methods have a significant impact on results, which shows the importance to choose a suitable measurement. Moreover, there are differences in performance on different granularity datasets.

show abstract

Section: )mentioning

confidence: 99%

Comparative Analysis on Classical Meta-Metric Models for Few-Shot Learning

Yang

Liu

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Fine-grained-based models. Now that few-shot learning in fine-grained scenarios has been studied, we chose some new work published as baselines-few-shot fine-grained image recognition (FSFG; Wei et al, 2019) and Meta-iNat (Wertheimer & Hariharan, 2019) and some other classical models that are validated on fine-grained data sets.…”

Section: Baselinesmentioning

confidence: 99%

“…Although there are some classic studies of few-shot learning in finegrained settings Wei, Wang, Liu, Shen, and Wu, 2019;Wertheimer & Hariharan, 2019), two problems remain to be solved in the existing methods. One problem is that a limited number of images per class can not represent the class distribution effectively, and image-level features are difficult to reflect the subtle visual differences between fine-grained images.…”

Section: Introductionmentioning

confidence: 99%

Fine-Grained 3D-Attention Prototypes for Few-Shot Learning

Liu

et al. 2020

Neural Computation

View full text Add to dashboard Cite

In the real world, a limited number of labeled finely grained images per class can hardly represent the class distribution effectively. Due to the more subtle visual differences in fine-grained images than simple images with obvious objects, that is, there exist smaller interclass and larger intraclass variations. To solve these issues, we propose an end-to-end attention-based model for fine-grained few-shot image classification (AFG) with the recent episode training strategy. It is composed mainly of a feature learning module, an image reconstruction module, and a label distribution module. The feature learning module mainly devises a 3D-Attention mechanism, which considers both the spatial positions and different channel attentions of the image features, in order to learn more discriminative local features to better represent the class distribution. The image reconstruction module calculates the mappings between local features and the original images. It is constrained by a designed loss function as auxiliary supervised information, so that the learning of each local feature does not need extra annotations. The label distribution module is used to predict the label distribution of a given unlabeled sample, and we use the local features to represent the image features for classification. By conducting comprehensive experiments on Mini-ImageNet and three fine-grained data sets, we demonstrate that the proposed model achieves superior performance over the competitors.

show abstract

“…The main ideas of the above studies can be summarized as designing the neural network structure, obtaining a good initialization, guiding the search steps or augmenting the dataset. In contrast to those studies, [14] and [27] focus on the different roles played by backgrounds and foregrounds in the classification task. [14] attempts to improve the performance of the model by enhancing main features with foregrounds.…”

Section: Introductionmentioning

confidence: 99%

“…In contrast to those studies, [14] and [27] focus on the different roles played by backgrounds and foregrounds in the classification task. [14] attempts to improve the performance of the model by enhancing main features with foregrounds. For this purpose, an additional network is introduced to locate the foregrounds, which brings the increase of the network complexity and the requirement of the dataset with bounding box.…”

Section: Introductionmentioning

confidence: 99%

Foreground Feature Attention Module Based on Unsupervised Saliency Detector for Few-Shot Learning

Kong

Xiong

et al. 2021

IEEE Access

View full text Add to dashboard Cite

In recent years, few-shot learning is proposed to solve the problem of lacking samples in deep learning. However, previous works are mainly concentrated on optimizing neural network structures or augmenting the dataset while ignoring the local relationship of the images. Considering that humans pay more attention to the foreground or prominent features of the images during image recognition, we proposed the foreground feature attention module (FFAM) based on an unsupervised saliency detector for few-shot learning. The FFAM consists of two parts: the foreground extraction module and the features attention module. More specifically, we first extract the foreground images by Robust Background Detector (RBD), one of the best unsupervised saliency detectors. Secondly, we employ the same embedding module to extract the features of both original images and foreground images. Finally, we introduce three improvements to enhance the foreground features and make our network focus on the foreground features without losing background information. Our proposed FFAM is more sensitive to the foreground features than previous approaches. Hence, it effectively recognizes those images with similar backgrounds. Extensive experiments are conducted on miniImagenet and tieredImagenet datasets. It is demonstrated that our proposed FFAM greatly improves the accuracy performance over baseline systems for both one-shot and few-shot classification tasks without increasing the network complexity.

show abstract

Few-Shot Learning With Localization in Realistic Settings

Cited by 123 publications

References 29 publications

Comparative Analysis on Classical Meta-Metric Models for Few-Shot Learning

Comparative Analysis on Classical Meta-Metric Models for Few-Shot Learning

Fine-Grained 3D-Attention Prototypes for Few-Shot Learning

Foreground Feature Attention Module Based on Unsupervised Saliency Detector for Few-Shot Learning

Contact Info

Product

Resources

About