NIPS 2018 迁移学习相关论文

文章目录
[NIPS2018](https://nips.cc/Conferences/2018/Schedule)
Unsupervisedly Learned Latent Graps as Transferable Representations
Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies
Learning Latent Subspaces in Variational Autoencoders
Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement Learning
Uncertainty-Aware Few-Shot Learning with Probabilistic Model-Agnostic Meta-Learning
Multitask Reinforcement Learning for Zero-shot Generalization with Subtask Dependencies
Stacked Semantics-Guided Attention Model for Fine-Grained Zero-Shot Learning
Delta-encoder: an effective sample synthesis method for few-shot object recognition
MetaGAN: An Adversarial Approach to Few-Shot Learning
One-Shot Unsupervised Cross Domain Translation
Generalized Zero-Shot Learning with Deep Calibration Network
Low-shot Learning via Covariance-Preserving Adversarial Augmentation Network
Improved few-shot learning with task conditioning and metric scaling
Adapted Deep Embeddings: A Synthesis of Methods for k-Shot Inductive Transfer Learning
NIPS2018
Unsupervisedly Learned Latent Graps as Transferable Representations
Zhilin Yang · Zhizhen Zhao · Bhuwan Dhingra · Kaiming He · William W Cohen · Ruslan Salakhutdinov · Yann LeCun

Modern deep transfer learning approaches have mainly focused on learning \emph{generic} feature vectors from one task that are transferable to other tasks, such as word embeddings in language and pretrained convolutional features in vision. However, these approaches usually transfer unary features and largely ignore more structured graphical representations. This work explores the possibility of learning generic latent graphs that capture dependencies between pairs of data units (e.g., words or pixels) from large-scale unlabeled data and transferring the graphs to downstream tasks. Our proposed transfer learning framework improves performance on various tasks including question answering, natural language inference, sentiment analysis, and image classification. We also show that the learned graphs are generic enough to be transferred to different types of input embeddings or features.

学习通用的隐含图结构，抓住数据单元对之间的依赖关系。（无标注数据里的结构化图表示）
论文下载

Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies
Alessandro Achille · Tom Eccles · Loic Matthey · Chris Burgess · Nicholas Watters · Alexander Lerchner · Irina Higgins

Intelligent behaviour in the real-world requires the ability to acquire new knowledge from an ongoing sequence of experiences while preserving and reusing past knowledge. We propose a novel algorithm for unsupervised representation learning from piece-wise stationary visual data: Variational Autoencoder with Shared Embeddings (VASE). Based on the Minimum Description Length principle, VASE automatically detects shifts in the data distribution and allocates spare representational capacity to new knowledge, while simultaneously protecting previously learnt representations from catastrophic forgetting. Our approach encourages the learnt representations to be disentangled, which imparts a number of desirable properties: VASE can deal sensibly with ambiguous inputs, it can enhance its own representations through imagination-based exploration, and most importantly, it exhibits semantically meaningful sharing of latents between different datasets. Compared to baselines with entangled representations, our approach is able to reason beyond surface-level statistics and perform semantically meaningful cross-domain inference.

实现了语义丰富的跨领域推理
论文下载

Learning Latent Subspaces in Variational Autoencoders
Jack Klys · Jake Snell · Richard Zemel

We present a method for training variational autoencoders on labelled datasets which encode information corresponding to the labels in explicitly predetermined subspaces of the latent space. We motivate our model from both an information theoretic perspective as well as a adversarial game perspective. By separating labelled information into a less complicated space we allow the model to more easily disentangle representations. This provides a form of semi-supervised learning of attributes. Since these subspaces can be chosen a priori, setting them to be low-dimensional provides a form of dimensionality reduction. We demonstrate the utility of our model on attribute manipulation tasks with several image datasets.

在标记数据集上训练变分自编码器，属性的半监督学习

Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement Learning
Ofir Marom · Benjamin Rosman

Object-oriented representations in reinforcement learning have shown promise in transfer learning, with previous research introducing a propositional object-oriented framework that has provably efficient learning bounds with respect to sample complexity. However, this framework has limitations in terms of the classes of tasks it can efficiently learn. In this paper we introduce a novel object-oriented framework that has provably efficient learning bounds and can solve a broader range of tasks. Additionally, we show that this framework is capable of zero-shot transfer of transition dynamics across tasks and demonstrate this empirically for the Taxi and Sokoban domains.

增强学习+迁移学习，实现了零样本迁移
https://nips.cc/Conferences/2018/Schedule?showEvent=11239

Uncertainty-Aware Few-Shot Learning with Probabilistic Model-Agnostic Meta-Learning
Kelvin Xu · Chelsea Finn · Sergey Levine

Meta-learning for few-shot learning entails acquiring a prior over previous tasks and experiences, such that new tasks be learned from small amounts of data. However, a critical challenge in few-shot learning is task ambiguity: even when a powerful prior can be meta-learned from a large number of prior tasks, a small dataset for a new task can simply be too ambiguous to acquire a single model (e.g., a classifier) for that task that is accurate. In this paper, we propose a probabilistic meta-learning algorithm that can sample models for a new task from a model distribution. Our approach extends model-agnostic meta-learning, which adapts to new tasks via gradient descent, to incorporate a parameter distribution that is trained via a variational lower bound. At meta-test time, our algorithm adapts via a simple procedure that injects noise into gradient descent, and at meta-training time, the model is trained such that this stochastic adaptation procedure produces samples from the approximate model posterior. Our experimental results show that our method can sample plausible classifiers and regressors in ambiguous few-shot learning problems.

元学习+小样本学习
小样本学习的关键挑战是任务模糊，论文提出使用一个概率元学习方法，从模型分布中为新任务采样一些模型。
论文下载

Multitask Reinforcement Learning for Zero-shot Generalization with Subtask Dependencies
SUNGRYULL SOHN · Junhyuk Oh · Honglak Lee

We introduce a new RL problem where the agent is required to execute a given subtask graph which describes a set of subtasks and their dependency. Unlike existing approaches that explicitly describe what the agent should do, our problem only describes properties of subtasks and relationships among them, which requires the agent to perform a complex reasoning to find the optimal subtask to execute. To solve this problem, we propose a neural subtask graph solver (NSS) which encodes the subtask graph using a recursive neural network. To overcome the difficulty of training, we propose a novel non-parametric gradient-based policy to pre-train our NSS agent and further finetune it through actor-critic method. The experimental results on two 2D visual domains show that our agent can perform a complex reasoning to find the optimal way of executing the subtask graph and generalize well to the unseen subtask graphs. In addition, we compare our agent with a Monte-Carlo tree search (MCTS) method showing that our method is much more efficient than MCTS, and the performance of NSS can be further improved by combining it with MCTS.

https://nips.cc/Conferences/2018/Schedule?showEvent=11689
多任务增强学习，零样本泛化，子任务依赖

Stacked Semantics-Guided Attention Model for Fine-Grained Zero-Shot Learning
yunlong yu · Zhong Ji · Yanwei Fu · Jichang Guo · Yanwei Pang · Zhongfei (Mark) Zhang

Zero-Shot Learning (ZSL) is achieved via aligning the semantic relationships between the global image feature vector and the corresponding class semantic descriptions. However, using the global features to represent fine-grained images may lead to sub-optimal results since they neglect the discriminative differences of local regions. Besides, different regions contain distinct discriminative information. The important regions should contribute more to the prediction. To this end, we propose a novel stacked semantics-guided attention (S2GA) model to obtain semantic relevant features by using individual class semantic features to progressively guide the visual features to generate an attention map for weighting the importance of different local regions. Feeding both the integrated visual features and the class semantic features into a multi-class classification architecture, the proposed framework can be trained end-to-end. Extensive experimental results on CUB and NABird datasets show that the proposed approach has a consistent improvement on both fine-grained zero-shot classification and retrieval tasks.

https://nips.cc/Conferences/2018/Schedule?showEvent=11582

基于堆栈语义指导注意力模型的细粒度两样本学习
出发点：局部区域的判别性差异，不同区域的不同判别性信息。

利用注意力图来指导，给不同局部区域加权
端到端训练
Delta-encoder: an effective sample synthesis method for few-shot object recognition
Eli Schwartz · Leonid Karlinsky · Joseph Shtok · Sivan Harary · Mattias Marder · Abhishek Kumar · Rogerio S Feris · Raja Giryes · Alex Bronstein

Learning to classify new categories based on just one or a few examples is a long-standing challenge in modern computer vision. In this work, we proposes a simple yet effective method for few-shot (and one-shot) object recognition. Our approach is based on a modified auto-encoder, denoted Delta-encoder, that learns to synthesize new samples for an unseen category just by seeing few examples from it. The synthesized samples are then used to train a classifier. The proposed approach learns to both extract transferable intra-class deformations, or “deltas”, between same-class pairs of training examples, and to apply those deltas to the few provided examples of a novel class (unseen during training) in order to efficiently synthesize samples from that new class. The proposed method improves over the state-of-the-art in one-shot object-recognition and compares favorably in the few-shot case. Upon acceptance code will be made available.

https://nips.cc/Conferences/2018/Schedule?showEvent=11291
样本合成法 小样本目标识别

MetaGAN: An Adversarial Approach to Few-Shot Learning
Ruixiang ZHANG · Tong Che · Zoubin Ghahramani · Yoshua Bengio · Yangqiu Song

In this paper, we propose a conceptually simple and general framework called MetaGAN for few-shot learning problems. Most state-of-the-art few-shot classification models can be integrated with MetaGAN in a principled and straightforward way. By introducing an adversarial generator conditioned on tasks, we augment vanilla few-shot classification models with the ability to discriminate between real and fake data. We argue that this GAN-based approach can help few-shot classifiers to learn sharper decision boundary, which could generalize better. We show that with our MetaGAN framework, we can extend supervised few-shot learning models to naturally cope with unsupervised data. Different from previous work in semi-supervised few-shot learning, our algorithms can deal with semi-supervision at both sample-level and task-level. We give theoretical justifications of the strength of MetaGAN, and validate the effectiveness of MetaGAN on challenging few-shot image classification benchmarks.

https://nips.cc/Conferences/2018/Schedule?showEvent=11246
GAN 基于对抗的小样本学习

One-Shot Unsupervised Cross Domain Translation
Sagie Benaim · Lior Wolf

Given a single image x from domain A and a set of images from domain B, our task is to generate the analogous of x in B. We argue that this task could be a key AI capability that underlines the ability of cognitive agents to act in the world and present empirical evidence that the existing unsupervised domain translation methods fail on this task. Our method follows a two step process. First, a variational autoencoder for domain B is trained. Then, given the new sample
x, we create a variational autoencoder for domain A by adapting the layers that are close to the image in order to directly fit x, and only indirectly adapt the other layers. Our experiments indicate that the new method does as well, when trained on one sample x, as the existing domain transfer methods, when these enjoy a multitude of training samples from domain A. Our code will be made publicly available.

https://nips.cc/Conferences/2018/Schedule?showEvent=11222

单样本无监督跨域转换

Generalized Zero-Shot Learning with Deep Calibration Network
Shichen Liu · Mingsheng Long · Jianmin Wang · Michael Jordan

A technical challenge of deep learning is recognizing target classes without seen data. Zero-shot learning leverages semantic representations such as attributes or class prototypes to bridge source and target classes. Existing standard zero-shot learning methods may be prone to overfitting the seen data of source classes as they are blind to the semantic representations of target classes. In this paper, we study generalized zero-shot learning that assumes accessible to target classes for unseen data during training, and prediction on unseen data is made by searching on both source and target classes. We propose a novel Deep Calibration Network (DCN) approach towards this generalized zero-shot learning paradigm, which enables simultaneous calibration of deep networks on the confidence of source classes and uncertainty of target classes. Our approach maps visual features of images and semantic representations of class prototypes to a common embedding space such that the compatibility of seen data to both source and target classes are maximized. We show superior accuracy of our approach over the state of the art on benchmark datasets for generalized zero-shot learning, including AwA, CUB, SUN, and aPY.

https://nips.cc/Conferences/2018/Schedule?showEvent=11213
基于深度矫正网络的广义零样本学习
将视觉特征和语义表示映射到一个共同的嵌入空间

Low-shot Learning via Covariance-Preserving Adversarial Augmentation Network
Hang Gao · Zheng Shou · Alireza Zareian · Qianru Sun · Shih-Fu Chang

Feature augmentation attacks low-shot learning problem by easing the catastrophic forgetting and over-fitting issues in low data regime. However, previous works either erroneously assume that any intra-class variances of base classes are sharable with any novel classes, or employ naive generation methods to hallucinate finite examples without modeling their latent distributions. In this work, we propose Covariance-Preserving Adversarial Augmentation Network for low-shot learning to overcome existing limits. We regulate generation within base-novel class pairs that are semantically adaptable. For better feature generation quality, a new Generative Adversarial Network is designed to model the latent distribution of each novel class given its base counterparts. Since direct estimation on novel classes can be inductively biased, we explicitly preserve covariance information as the variability’’ of base examples during generation process. Empirical evidences show that our model can generate realistic yet diverse examples, leading to substantial improvements on the ImageNet benchmark over the state-of-the-art.

https://nips.cc/Conferences/2018/Schedule?showEvent=11118
特征增强，灾难性遗忘和过适配问题，隐含分布，GAN
因为直接预测新类存在归纳式偏置，我们在生成过程显式保持协方差信息作为基础样本的可变性

Improved few-shot learning with task conditioning and metric scaling
Boris Oreshkin · Alexandre Lacoste ·

Few-shot learning has become essential for producing models that generalize from few examples. In this work, we identify that metric scaling and metric task conditioning are important to improve the performance of few-shot algorithms. Our analysis reveals that a simple metric scaling completely changes the nature of learner parameter updates and closes the accuracy gap for the cosine similarity, providing improvements up to 14% in accuracy on the mini-Imagenet 5-way 5-shot classification task. We further propose a simple and effective way of conditioning a learner on the task sample set, resulting in learning a task-dependent metric space. Moreover, we propose and empirically test a practical end-to-end optimization procedure based on auxiliary task co-training to learn a task-dependent metric space. The resulting few-shot learning model based on the task-dependent scaled metric achieves state of the art on mini-Imagenet. We confirm these results on another few-shot dataset that we introduce in this paper based on CIFAR100.

https://nips.cc/Conferences/2018/Schedule?showEvent=11094
度量缩放+度量任务条件，基于任务依赖的度量空间

Adapted Deep Embeddings: A Synthesis of Methods for k-Shot Inductive Transfer Learning
Tyler Scott · Michael Mozer · Karl.ridgeway@colora Ridgeway

The focus in machine learning has branched beyond training classifiers on a single task to investigating how previously acquired knowledge in a source domain can be leveraged to facilitate learning in a related target domain, known as inductive transfer learning. Three active lines of research have independently explored transfer learning using neural networks. In weight transfer, a model trained on the source domain is used as an initialization point for a network to be trained on the target domain. In deep metric learning, the source domain is used to construct an embedding that captures class structure in both the source and target domains. In few-shot learning, the focus is on generalizing well in the target domain based on a limited number of labeled examples. We compare state-of-the-art methods from these three paradigms and also explore hybrid adapted-embedding methods that use limited target-domain data to fine tune embeddings constructed from source-domain data. We conduct a systematic comparison of methods in a variety of domains, varying the number of labeled instances available in the target domain (k), as well as the number of target-domain classes. The following are the major results: (1) Deep embeddings are far superior, compared to weight transfer, as a starting point for inter-domain transfer or model re-use (2) Our hybrid methods robustly outperform every few-shot learning and every deep metric learning method previously proposed, with a mean error reduction of 30% over state-of-the-art. (3) Among loss functions for discovering embeddings, the histogram loss (Ustinova & Lempitsky, 2016) is most robust. We hope our results will motivate a unification of research in weight transfer, deep metric learning, and few-shot learning.

https://nips.cc/Conferences/2018/Schedule?showEvent=11035
适应的深度映射：k样本归纳迁移学习的方法的综合

深度网络迁移学习的三条线
1）权重迁移，将源域上训练的模型作为目标域上训练网络的起始点
2）深度度量学习，在源域上构建能够捕获源域和目标域两个域的类结构的嵌入
3）小样本学习，关键是在标记样本有限的目标域上泛化效果好。
结果：
1）更好
2）更鲁棒
3）直方图损失
--------------------- 
作者：一亩高粱 
来源：CSDN 
原文：https://blog.csdn.net/cp_oldy/article/details/82630729 
版权声明：本文为博主原创文章，转载请附上博文链接！