Diversity Transfer Network for Few-Shot Learning

• URL: http://arxiv.org/abs/1912.13182v1
• Date: Tue, 31 Dec 2019 05:44:38 GMT
• Title: Diversity Transfer Network for Few-Shot Learning
• Authors: Mengting Chen, Yuxin Fang, Xinggang Wang, Heng Luo, Yifeng Geng, Xinyu Zhang, Chang Huang, Wenyu Liu, Bo Wang
• Abstract summary: We propose a novel generative framework, Diversity Transfer Network (DTN), that learns to transfer latent diversities from known categories. An organized auxiliary task co-training over known categories is proposed to stabilize the meta-training process of DTN. The results show that DTN, with single-stage training and faster convergence speed, obtains the state-of-the-art results among the feature generation based few-shot learning methods.
• Score: 34.36438817417749
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Few-shot learning is a challenging task that aims at training a classifier for unseen classes with only a few training examples. The main difficulty of few-shot learning lies in the lack of intra-class diversity within insufficient training samples. To alleviate this problem, we propose a novel generative framework, Diversity Transfer Network (DTN), that learns to transfer latent diversities from known categories and composite them with support features to generate diverse samples for novel categories in feature space. The learning problem of the sample generation (i.e., diversity transfer) is solved via minimizing an effective meta-classification loss in a single-stage network, instead of the generative loss in previous works. Besides, an organized auxiliary task co-training over known categories is proposed to stabilize the meta-training process of DTN. We perform extensive experiments and ablation studies on three datasets, i.e., \emph{mini}ImageNet, CIFAR100 and CUB. The results show that DTN, with single-stage training and faster convergence speed, obtains the state-of-the-art results among the feature generation based few-shot learning methods. Code and supplementary material are available at: \texttt{https://github.com/Yuxin-CV/DTN}

Related papers

• COSCO: A Sharpness-Aware Training Framework for Few-shot Multivariate Time Series Classification [19.593625378366472]
  We propose a new learning framework named COSCO consisting of a sharpness-aware minimization (SAM) optimization and a Prototypical loss function. Our experiments demonstrate our proposed method outperforms the existing baseline methods.
  arXiv  Detail & Related papers  (2024-09-15T07:41:55Z)
• Memorizing Complementation Network for Few-Shot Class-Incremental Learning [109.4206979528375]
  We propose a Memorizing Complementation Network (MCNet) to ensemble multiple models that complements the different memorized knowledge with each other in novel tasks. We develop a Prototype Smoothing Hard-mining Triplet (PSHT) loss to push the novel samples away from not only each other in current task but also the old distribution.
  arXiv  Detail & Related papers  (2022-08-11T02:32:41Z)
• BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning [93.38239238988719]
  We propose to enable deep neural networks with the ability to learn the sample relationships from each mini-batch. BatchFormer is applied into the batch dimension of each mini-batch to implicitly explore sample relationships during training. We perform extensive experiments on over ten datasets and the proposed method achieves significant improvements on different data scarcity applications.
  arXiv  Detail & Related papers  (2022-03-03T05:31:33Z)
• Exploiting Invariance in Training Deep Neural Networks [4.169130102668252]
  Inspired by two basic mechanisms in animal visual systems, we introduce a feature transform technique that imposes invariance properties in the training of deep neural networks. The resulting algorithm requires less parameter tuning, trains well with an initial learning rate 1.0, and easily generalizes to different tasks. Tested on ImageNet, MS COCO, and Cityscapes datasets, our proposed technique requires fewer iterations to train, surpasses all baselines by a large margin, seamlessly works on both small and large batch size training, and applies to different computer vision tasks of image classification, object detection, and semantic segmentation.
  arXiv  Detail & Related papers  (2021-03-30T19:18:31Z)
• Learning Invariant Representations across Domains and Tasks [81.30046935430791]
  We propose a novel Task Adaptation Network (TAN) to solve this unsupervised task transfer problem. In addition to learning transferable features via domain-adversarial training, we propose a novel task semantic adaptor that uses the learning-to-learn strategy to adapt the task semantics. TAN significantly increases the recall and F1 score by 5.0% and 7.8% compared to recently strong baselines.
  arXiv  Detail & Related papers  (2021-03-03T11:18:43Z)
• Improving filling level classification with adversarial training [90.01594595780928]
  We investigate the problem of classifying - from a single image - the level of content in a cup or a drinking glass. We use adversarial training in a generic source dataset and then refine the training with a task-specific dataset. We show that transfer learning with adversarial training in the source domain consistently improves the classification accuracy on the test set.
  arXiv  Detail & Related papers  (2021-02-08T08:32:56Z)
• Separable Batch Normalization for Robust Facial Landmark Localization with Cross-protocol Network Training [41.82379935715916]
  A big, diverse and balanced training data is the key to the success of deep neural network training. A small dataset without diverse and balanced training samples cannot support the training of a deep network effectively. This paper presents a novel Separable Batch Normalization (SepBN) module with a Cross-protocol Network Training (CNT) strategy for robust facial landmark localization.
  arXiv  Detail & Related papers  (2021-01-17T13:04:06Z)
• Few-Shot Learning with Intra-Class Knowledge Transfer [100.87659529592223]
  We consider the few-shot classification task with an unbalanced dataset. Recent works have proposed to solve this task by augmenting the training data of the few-shot classes using generative models. We propose to leverage the intra-class knowledge from the neighbor many-shot classes with the intuition that neighbor classes share similar statistical information.
  arXiv  Detail & Related papers  (2020-08-22T18:15:38Z)
• Imbalanced Data Learning by Minority Class Augmentation using Capsule Adversarial Networks [31.073558420480964]
  We propose a method to restore the balance in imbalanced images, by coalescing two concurrent methods. In our model, generative and discriminative networks play a novel competitive game. The coalescing of capsule-GAN is effective at recognizing highly overlapping classes with much fewer parameters compared with the convolutional-GAN.
  arXiv  Detail & Related papers  (2020-04-05T12:36:06Z)
• Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches [67.51747235117]
  Fine-grained visual classification (FGVC) is much more challenging than traditional classification tasks. Recent works mainly tackle this problem by focusing on how to locate the most discriminative parts. We propose a novel framework for fine-grained visual classification to tackle these problems.
  arXiv  Detail & Related papers  (2020-03-08T19:27:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.