Cross-Domain Few-shot Learning學習目錄

[推薦第一篇閱讀的文章][Done]few-shot learning, zero-shot learning, one-shot learning,any-shot learning, C-way K-shot,Meta-learn



Inductive ZSL vs. Transductive ZSL

Generalized Zero-shot learning的評斷指標:
harmonic mean accuracy (H),跟F1 Score很類似的概念,能平衡Seen和UnSeen的Accuracy

harmonic mean accuracy (H)

[Done]Zero-Shot Learning — A Comprehensive Evaluation of the Good, the Bad and the Ugly

  • proposed the Harmonic mean of seen and unseen class accuracy as a unified measure for performance in GZSL setting
  • propose a new zero-shot learning dataset, the Animals with Attributes 2 (AWA2)
  • 提出了數種有Source Code的ZSL方法的HM比較

[網路上有人整理好的少樣本學習論文清單]Small Data Paper

Few shot learning的Standard tasks和Random tasks

取自Mutual-Information Based Few-Shot Classification

Zero-shot learning中dataset中的mat檔案是如何建立的?

========================================Zero-Shot Learning — A Comprehensive Evaluation of the Good, the Bad and the Ugly

Our image embeddings are 2048-dim top-layer pooling units of the 101-layered ResNet We use the original ResNet-101 that is pre-trained on ImageNet with 1K classes, i.e. the balanced subset, and we do not fine-tune it for any of the mentioned datasets

for aPY, AWA1, AWA2, CUB and SUN, we use the per-class attributes between values 0 and 1 that are provided with the datasets

For ImageNet as attributes of 21K classes are not available, we use Word2Vec [27] trained on Wikipedia provided by [14]. Note that an evaluation of class embeddings is out of the scope of this paper. We refer the reader to [9] for more details on the topic.

[27] T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado, and J. Dean, “Distributed representations of words and phrases and their compositionality,”in NIPS, 2013. 2, 3, 6

[14] S. Changpinyo, W.-L. Chao, B. Gong, and F. Sha, “Synthesized classifiers
for zero-shot learning,” in CVPR, 2016. 1, 2, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13

========================================Feature Generating Networks for Zero-Shot Learning(cvpr18xian)


As real CNN features, we extract 2048-dim toplayer pooling units of the 101-layered ResNet [21] from the entire image. We do not do any image pre-processing such as cropping or use any other data augmentation techniques. ResNet is pre-trained on ImageNet 1K and not fine-tuned. As synthetic CNN features, we generate 2048-dim CNN features using our f-xGAN model.


As the class embedding, unless it is stated otherwise, we use per-class attributes for AWA (85-dim), CUB (312-dim) and SUN (102-dim). Furthermore, for CUB and Flowers, we extract 1024-dim character-based CNN-RNN [35] features from fine-grained visual descriptions (10 sentences per image). None of the sentences are seen during training the CNN-RNN. We build per-class sentences by averaging the CNN-RNN features that belong to the same class.

Implementation details. In all f-xGAN models, both the generator and the discriminator are MLP with LeakyReLU activation. The generator consists of a single hidden layer with 4096 hidden units. Its output layer is ReLU because we aim to learn the top max-pooling units of ResNet-101. While the discriminator of f-GAN has one hidden layer with 1024 hidden units in order to stabilize the GAN training, the discriminators of f-WGAN and f-CLSWGAN have one hidden layer with 4096 hidden units as WGAN [19] does not have instability issues thus a stronger discriminator can be applied here. We do not apply batch normalization our empirical evaluation showed a significant degradation of the accuracy when batch normalization is used. The noise z is drawn from a unit Gaussian with the same dimensionality as the class embedding. We use λ = 10 as suggested in [19] and β = 0.01 across all the datasets

Latent Embeddings for Zero-shot Classification


Image and class embeddings. In our latent embedding (LatEm) model, the image embeddings (image features) and class embeddings (side information) are two essential components. To facilitate direct comparison with the state-of-the-art, we use the embeddings provided by [2]. Briefly, as image embeddings we use the 1, 024 dimensional outputs of the top-layer pooling units of the pre-trained GoogleNet [36] extracted from the whole image. We do not do any task specific pre-processing on images such as cropping foreground objects.


As class embeddings we evaluate four different alternatives, i.e. attributes (att), word2vec (w2v), glove (glo) and hierarchies (hie). Attributes [20, 9] are distinguishing properties of objects that are obtained through human annotation. For fine-grained datasets such as CUB and Dogs, as objects are visually very similar to each other, a large number of attributes are needed. Among the three datasets used, CUB contains 312 attributes, AWA contains 85 attributes while Dogs does not contain annotations for attributes. Our attribute class embedding is a vector per-class measuring the strength of each attribute based on human judgment.

Generalized Zero-Shot Learning using Multimodal Variational Auto-Encoder with Semantic Concepts


[Done] Will Multi-modal Data Improves Few-shot Learning?

[Done]Leveraging the Feature Distribution in Transfer-based Few-Shot Learning(PT+MAP)

[Done]Zero-sample surface defect detection and classification based on semantic feedback neural network
使用cylinder liner(汽缸) 瑕疵資料進行Zero shot learning

[Done]Anomaly Detection for Solder Joints Using β-VAE(使用β-VAE來進行焊點的異常偵測,效果比VAE還要好約略1個百分比)

[Done]Adaptive and Generative Zero-Shot Learning

[Done]Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders(CADA-VAE)

[Done]Concept Learners for Few-Shot Learning(COMET)

[Done]From Generalized zero-shot learning to long-tail with class descriptors(DRAGON)

[Done]Large-Scale Zero-Shot Image Classification from Rich and Diverse Textual Descriptions

[Done]f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning(f-VAEGAN)

[Done]Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification(tf-VAEGAN)

[Done]A Survey of Zero-Shot Learning: Settings, Methods, and Applications

[Done]Learning from Few Samples: A Survey

[Done]Generalizing from a Few Examples: A Survey on Few-Shot Learning

[Done][入門科普文][推薦第一篇閱讀的文章]Zero-Shot Learning
本文除了很入門的介紹Zero-Shot learning外,也有程式碼實作

[Done][入門科普文]What Is Zero-Shot Learning?

[Done][中文論文]A decadal survey of zero-shot image classification

[Done][中文論文]Research and Development on Zero-Shot Learning

[Done][課程教材]Meta Learning (Part 1)

[Done][課程教材]Meta Learning (Part 2)

[Done][課程教材]ML 108–2 Domain Adaptation.pdf

[Done][課程教材]Meta Learning & More

[Done][課程教材]Recurrent Neural Networks & Transformer (I) Meta-Learning; Few-Shot and Zero-Shot Classification (I)

[Done][課程教材]Meta-Learning; Few-Shot and Zero-Shot Classification (II)

[Done][課程教材]From Domain Adaptation to Domain Generalization

[Done] [2010.03522] A Survey of Deep Meta-Learning

[Done] [1904.04232] A Closer Look at Few-shot Classification

[Done][2101.11461] Machine learning with limited data

[Done][2001.08735] Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation

[Done] 【論文閱讀】[meta learning]cross-domain few-shot classification via learned feature-wise transformation

[Done] 小樣本學習跨域(Cross-domain)問題總結- 知乎

[Done] A Survey of Cross-Domain Few-shot Learning — 知乎


[Done]零次学习(Zero-Shot Learning)入门 — 知乎

[1710.03463] Learning to Generalize: Meta-Learning for Domain Generalization

[1912.07200] A Broader Study of Cross-Domain Few-Shot Learning

[2004.14164] MICK: A Meta-Learning Framework for Few-shot Relation Classification with Little Training Data

[2005.10544] Cross-Domain Few-Shot Learning with Meta Fine-Tuning

[2006.11384] A Transductive Multi-Head Model for Cross-Domain Few-Shot Learning

[2010.06498] Cross-Domain Few-Shot Learning by Representation Fusion

[2011.00179] Combining Domain-Specific Meta-Learners in the Parameter Space for Cross-Domain Few-Shot Classification

Explain and Improve: Cross-Domain Few-Shot-Learning Using Explanations



Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store