Contrastive learning and supervised learning have both seen significant progress and success. However, thus far they have largely been treated as two separate objectives, brought together only by having a shared neural network. In this paper we show that through the perspective of hybrid discriminative-generative training of energy-based models we can make a direct connection between contrastive learning and supervised learning. Beyond presenting this unified view, we show our specific choice of approximation of the energy-based loss outperforms the existing practice in terms of classification accuracy of WideResNet on CIFAR-10 and CIFAR-100. It also leads to improved performance on robustness, out-of-distribution detection, and calibration.
National University of Singapore（新加坡国立大学）；Chinese Academy of Sciences（中国科学院）；SEA AI Lab（SEA AI实验室）
Contrastive self-supervised learning (CSL) has attracted increasing attention for model pre-training via unlabeled data. The resulted CSL models provide instance-discriminative visual features that are uniformly scattered in the feature space. During deployment, the common practice is to directly fine-tune CSL models with cross-entropy, which however may not be the best strategy in practice. Although cross-entropy tends to separate inter-class features, the resulting models still have limited capability for reducing intra-class feature scattering that exists in CSL models. In this paper, we in…
The pretasks are mainly built on mutual information estimation, which requires data augmentation to construct positive samples with similar semantics to learn invariant signals and negative samples with dissimilar semantics in order to empower representation discriminability. However, an appropriate data augmentation configuration depends heavily on lots of empirical trials such as choosing the compositions of data augmentation techniques and the corresponding hyperparameter settings. We propose an augmentation-free graph contrastive learning method, invariant-discriminative graph contrastive …
Unsupervised representation learning has recently received lots of interest due to its powerful generalizability through effectively leveraging large-scale unlabeled data. There are two prevalent approaches for this, contrastive learning and generative pre-training, where the former learns representations from instance-wise discrimination tasks and the latter learns them from estimating the likelihood. These seemingly orthogonal approaches have their own strengths and weaknesses. Contrastive learning tends to extract semantic information and discards details irrelevant for classifying objects,…
Tsinghua University（清华大学）；Tsinghua National Laboratory for Information Science and Technology (TNList)（清华信息科学与技术国家实验室）；Anhui University（安徽大学）；Renmin University of China（中国人民大学）
Deep supervised learning has achieved great success in the last decade. However, its deficiencies of dependence on manual labels and vulnerability to attacks have driven people to explore a better solution. As an alternative, self-supervised learning attracts many researchers for its soaring performance on representation learning in the last several years. Self-supervised representation learning leverages input data itself as supervision and benefits almost all types of downstream tasks. In this survey, we take a look into new self-supervised learning methods for representation in computer vis…
Shenzhen Institute of Advanced Study, UESTC（电子科技大学深圳高等研究院）
Unsupervised out-of-distribution (OOD) Detection aims to separate the samples falling outside the distribution of training data without label information. Among numerous branches, contrastive learning has shown its excellent capability of learning discriminative representation in OOD detection. However, for its limited vision, merely focusing on instance-level relationship between augmented samples, it lacks attention to the relationship between samples with same semantics. Based on the classic contrastive learning, we propose Cluster-aware Contrastive Learning (CCL) framework for unsupervised…
Self-supervised learning is a popular and powerful method for utilizing large amounts of unlabeled data, for which a wide variety of training objectives have been proposed in the literature. In this study, we perform a Bayesian analysis of state-of-the-art self-supervised learning objectives and propose a unified formulation based on likelihood learning. Our analysis suggests a simple method for integrating self-supervised learning with generative models, allowing for the joint training of these two seemingly distinct approaches. We refer to this combined framework as GEDI, which stands for GE…
University of Trento（特伦托大学）；Xiamen University（厦门大学）；Fondazione Bruno Kessler（布鲁诺·凯塞勒基金会）
In this paper, we address Novel Class Discovery (NCD), the task of unveiling new classes in a set of unlabeled samples given a labeled dataset with known classes. We exploit the peculiarities of NCD to build a new framework, named Neighborhood Contrastive Learning (NCL), to learn discriminative representations that are important to clustering performance. Our contribution is twofold. First, we find that a feature extractor trained on the labeled set generates representations in which a generic query sample and its neighbors are likely to share the same class. We exploit this observation to ret…
Carnegie Mellon University（卡内基梅隆大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Salesforce Research（赛富时研究院）；Harvard Medical School, Harvard University（哈佛医学院（哈佛大学））；Fanhan Tech.（泛函科技）
AI Safety is a major concern in many deep learning applications such as autonomous driving. Given a trained deep learning model, an important natural problem is how to reliably verify the model's prediction. In this paper, we propose a novel framework -- deep verifier networks (DVN) to verify the inputs and outputs of deep discriminative models with deep generative models. Our proposed model is based on conditional variational auto-encoders with disentanglement constraints. We give both intuitive and theoretical justifications of the model. Our verifier network is trained independently with th…
Advanced graph neural networks have shown great potentials in graph classification tasks recently. Different from node classification where node embeddings aggregated from local neighbors can be directly used to learn node labels, graph classification requires a hierarchical accumulation of different levels of topological information to generate discriminative graph embeddings. Still, how to fully explore graph structures and formulate an effective graph classification pipeline remains rudimentary. In this paper, we propose a novel graph neural network based on supervised contrastive learning …
Supervised learning, characterized by both discriminative and generative learning, seeks to predict the values of single (or sometimes multiple) predefined target attributes based on a predefined set of predictor attributes. For applications where the information available and predictions to be made may vary from instance to instance, we propose the task of target-agnostic learning where arbitrary disjoint sets of attributes can be used for each of predictors and targets for each to-be-predicted instance. For this task, we survey a wide range of techniques available for handling missing values…
Graph Structure Refinement with Energy-based Contrastive Learning
Beihang University（北京航空航天大学）；Postdoctoral Research Station at China RongTong Academy of Sciences Group Corporation Limited（中国融通集团博士后科研工作站）；Eastern Institute of Technology（宁波工程学院）；Ningbo Institute of Digital Twin, Eastern Institute of Technology（宁波工程学院宁波数字孪生研究院）
In this paper, we present a framework for contrastive learning for audio representations, in a self supervised frame work without access to any ground truth labels. The core idea in self supervised contrastive learning is to map an audio signal and its various augmented versions (representative of salient aspects of audio like pitch, timbre etc.) to a space where they are close together, and are separated from other different signals. In addition we also explore generative models based on state of the art transformer based architectures for learning latent spaces for audio signals, without acc…
The pattern theory of Grenander is a mathematical framework where patterns are represented by probability models on random variables of algebraic structures. In this paper, we review three families of probability models, namely, the discriminative models, the descriptive models, and the generative models. A discriminative model is in the form of a classifier. It specifies the conditional probability of the class label given the input signal. A descriptive model specifies the probability distribution of the signal, based on an energy function defined on the signal. A generative model assumes th…
The projected belief network (PBN) is a layered generative network with tractable likelihood function, and is based on a feed-forward neural network (FF-NN). It can therefore share an embodiment with a discriminative classifier and can inherit the best qualities of both types of network. In this paper, a convolutional PBN is constructed that is both fully discriminative and fully generative and is tested on spectrograms of spoken commands. It is shown that the network displays excellent qualities from either the discriminative or generative viewpoint. Random data synthesis and visible data rec…
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Microsoft Research Cambridge（微软研究院剑桥实验室）
Computer vision is hard because of a large variability in lighting, shape, and texture; in addition the image signal is non-additive due to occlusion. Generative models promised to account for this variability by accurately modelling the image formation process as a function of latent variables with prior beliefs. Bayesian posterior inference could then, in principle, explain the observation. While intuitively appealing, generative models for computer vision have largely failed to deliver on that promise due to the difficulty of posterior inference. As a result the community has favoured effic…
IBM GBS France（IBM 全球商业服务法国分公司）；SAMOVAR（萨莫瓦实验室）；Telecom SudParis（巴黎南泰尔电信学院）；Institut Polytechnique de Paris（巴黎理工学院）
We deal with Bayesian generative and discriminative classifiers. Given a model distribution $p(x, y)$, with the observation $y$ and the target $x$, one computes generative classifiers by firstly considering $p(x, y)$ and then using the Bayes rule to calculate $p(x | y)$. A discriminative model is directly given by $p(x | y)$, which is used to compute discriminative classifiers. However, recent works showed that the Bayesian Maximum Posterior classifier defined from the Naive Bayes (NB) or Hidden Markov Chain (HMC), both generative models, can also match the discriminative classifier definition…
We study the problem of identifying viewers of arbitrary images based on their eye gaze. Psychological research has derived generative stochastic models of eye movements. In order to exploit this background knowledge within a discriminatively trained classification model, we derive Fisher kernels from different generative models of eye gaze. Experimentally, we find that the performance of the classifier strongly depends on the underlying generative model. Using an SVM with Fisher kernel improves the classification performance over the underlying generative model.
Montreal Institute for Learning Algorithms（蒙特利尔学习算法研究所）；Université de Montréal（蒙特利尔大学）
We explore the question of whether the representations learned by classifiers can be used to enhance the quality of generative models. Our conjecture is that labels correspond to characteristics of natural data which are most salient to humans: identity in faces, objects in images, and utterances in speech. We propose to take advantage of this by using the representations from discriminative classifiers to augment the objective function corresponding to a generative model. In particular we enhance the objective function of the variational autoencoder, a popular generative model, with a discrim…
College of Computing（计算机学院）；Georgia Institute of Technology（佐治亚理工学院）
Automatic image annotation (AIA) raises tremendous challenges to machine learning as it requires modeling of data that are both ambiguous in input and output, e.g., images containing multiple objects and labeled with multiple semantic tags. Even more challenging is that the number of candidate tags is usually huge (as large as the vocabulary size) yet each image is only related to a few of them. This paper presents a hybrid generative-discriminative classifier to simultaneously address the extreme data-ambiguity and overfitting-vulnerability issues in tasks such as AIA. Particularly: (1) an Ex…
We empirically characterize the performance of discriminative and generative LSTM models for text classification. We find that although RNN-based generative models are more powerful than their bag-of-words ancestors (e.g., they account for conditional dependencies across words in a document), they have higher asymptotic error rates than discriminatively trained RNN models. However we also find that generative models approach their asymptotic error rate more rapidly than their discriminative counterparts---the same pattern that Ng & Jordan (2001) proved holds for linear classification models th…
Adversarial Training (AT) is known as an effective approach to enhance the robustness of deep neural networks. Recently researchers notice that robust models with AT have good generative ability and can synthesize realistic images, while the reason behind it is yet under-explored. In this paper, we demystify this phenomenon by developing a unified probabilistic framework, called Contrastive Energy-based Models (CEM). On the one hand, we provide the first probabilistic characterization of AT through a unified understanding of robustness and generative ability. On the other hand, our unified fra…
University of Southern California（南加州大学）；University of Pennsylvania（宾夕法尼亚大学）
Metrics specifying distances between data points can be learned in a discriminative manner or from generative models. In this paper, we show how to unify generative and discriminative learning of metrics via a kernel learning framework. Specifically, we learn local metrics optimized from parametric generative models. These are then used as base kernels to construct a global kernel that minimizes a discriminative training criterion. We consider both linear and nonlinear combinations of local metric kernels. Our empirical results show that these combinations significantly improve performance on …
Telecom SudParis（南巴黎电信学院）；Institut Polytechnique de Paris（巴黎综合理工学院）；IBM GSB France（IBM法国全球企业服务部）
For classification tasks, probabilistic models can be categorized into two disjoint classes: generative or discriminative. It depends on the posterior probability computation of the label $x$ given the observation $y$, $p(x | y)$. On the one hand, generative classifiers, like the Naive Bayes or the Hidden Markov Model (HMM), need the computation of the joint probability p(x,y), before using the Bayes rule to compute $p(x | y)$. On the other hand, discriminative classifiers compute $p(x | y)$ directly, regardless of the observations' law. They are intensively used nowadays, with models as Logis…
Generative classifiers have been shown promising to detect illegal inputs including adversarial examples and out-of-distribution samples. Supervised Deep Infomax~(SDIM) is a scalable end-to-end framework to learn generative classifiers. In this paper, we propose a modification of SDIM termed SDIM-\emph{logit}. Instead of training generative classifier from scratch, SDIM-\emph{logit} first takes as input the logits produced any given discriminative classifier, and generate logit representations; then a generative classifier is derived by imposing statistical constraints on logit representations…
University of Pittsburgh（匹兹堡大学）；The University of Melbourne（墨尔本大学）；The University of Sydney（悉尼大学）；Carnegie Mellon University（卡内基梅隆大学）
Majority of state-of-the-art deep learning methods are discriminative approaches, which model the conditional distribution of labels given inputs features. The success of such approaches heavily depends on high-quality labeled instances, which are not easy to obtain, especially as the number of candidate classes increases. In this paper, we study the complementary learning problem. Unlike ordinary labels, complementary labels are easy to obtain because an annotator only needs to provide a yes/no answer to a randomly chosen candidate class for each instance. We propose a generative-discriminati…
We study unsupervised learning by developing introspective generative modeling (IGM) that attains a generator using progressively learned deep convolutional neural networks. The generator is itself a discriminator, capable of introspection: being able to self-evaluate the difference between its generated samples and the given training data. When followed by repeated discriminative learning, desirable properties of modern discriminative classifiers are directly inherited by the generator. IGM learns a cascade of CNN classifiers using a synthesis-by-classification algorithm. In the experiments, …
Deep generative models (DGMs) are effective on learning multilayered representations of complex data and performing inference of input data by exploring the generative ability. However, little work has been done on examining or empowering the discriminative ability of DGMs on making accurate predictions. This paper presents max-margin deep generative models (mmDGMs), which explore the strongly discriminative principle of max-margin learning to improve the discriminative power of DGMs, while retaining the generative capability. We develop an efficient doubly stochastic subgradient algorithm for…
Generative models are known to be difficult to assess. Recent works, especially on generative adversarial networks (GANs), produce good visual samples of varied categories of images. However, the validation of their quality is still difficult to define and there is no existing agreement on the best evaluation process. This paper aims at making a step toward an objective evaluation process for generative models. It presents a new method to assess a trained generative model by evaluating the test accuracy of a classifier trained with generated data. The test set is composed of real images. There…
We propose a new modeling approach that is a generalization of generative and discriminative models. The core idea is to use an implicit parameterization of a joint probability distribution by specifying only the conditional distributions. The proposed scheme combines the advantages of both worlds -- it can use powerful complex discriminative models as its parts, having at the same time better generalization capabilities. We thoroughly evaluate the proposed method for a simple classification task with artificial data and illustrate its advantages for real-word scenarios on a semantic image seg…
When working with three-dimensional data, choice of representation is key. We explore voxel-based models, and present evidence for the viability of voxellated representations in applications including shape modeling and object classification. Our key contributions are methods for training voxel-based variational autoencoders, a user interface for exploring the latent space learned by the autoencoder, and a deep convolutional neural network architecture for object classification. We address challenges unique to voxel-based representations, and empirically evaluate our models on the ModelNet ben…
Towards the Unification of Generative and Discriminative Visual Foundation Model: A Survey
University of California Los Angeles（加利福尼亚大学洛杉矶分校）；Rice University（莱斯大学）；Carnegie Mellon University（卡内基梅隆大学）；University of Michigan（密歇根大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Walmart Global Tech（沃尔玛全球技术公司）；Santa Clara University（圣克拉拉大学）；Shanghai AI Laboratory（上海人工智能实验室）；Johns Hopkins University（约翰斯·霍普金斯大学）
Tokyo Institute of Technology（东京工业大学）；Meijo University（名城大学）
Conditional random fields (CRFs) are usually specified by graphical models but in this paper we propose to use probabilistic logic programs and specify them generatively. Our intension is first to provide a unified approach to CRFs for complex modeling through the use of a Turing complete language and second to offer a convenient way of realizing generative-discriminative pairs in machine learning to compare generative and discriminative models and choose the best model. We implemented our approach as the D-PRISM language by modifying PRISM, a logic-based probabilistic modeling language for ge…
BI Norwegian Business School（BI挪威商学院）；UiT The Arctic University of Norway（挪威北极大学）；Norwegian Computing Center（挪威计算中心）
Deep generative models with latent variables have been used lately to learn joint representations and generative processes from multi-modal data. These two learning mechanisms can, however, conflict with each other and representations can fail to embed information on the data modalities. This research studies the realistic scenario in which all modalities and class labels are available for model training, but where some modalities and labels required for downstream tasks are missing. We show, in this scenario, that the variational lower bound limits mutual information between joint representat…
University of Chicago（芝加哥大学）；Toyota Technological Institute at Chicago（芝加哥丰田理工学院）；Peking University（北京大学）；Peng Cheng Laboratory（鹏城实验室）
While discriminative neural network classifiers are generally preferred, recent work has shown advantages of generative classifiers in term of data efficiency and robustness. In this paper, we focus on natural language inference (NLI). We propose GenNLI, a generative classifier for NLI tasks, and empirically characterize its performance by comparing it to five baselines, including discriminative models and large-scale pretrained language representation models like BERT. We explore training objectives for discriminative fine-tuning of our generative classifiers, showing improvements over log lo…
Bridging Generative and Discriminative Noisy-Label Learning via Direction-Agnostic EM Formulation
Cornell Tech（康奈尔科技）；Cornell University（康奈尔大学）；Department of Radiology, Stanford University（斯坦福大学放射科）；Oxford University（牛津大学）；Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey（视觉、语音和信号处理中心（CVSSP）、塞维利亚大学）
Interpretable Generative and Discriminative Learning for Multimodal and Incomplete Clinical Data
Department of Health Sciences and Technology (DHEST), ETH Zurich（健康科学与技术系，苏黎世联邦理工学院）；Department of Signal Theory and Communications, Universidad Carlos III de Madrid（信号理论与通信系，卡洛斯三世大学）；UCL Hawkes Institute, Department of Computer Science, University College London（UCL Hawkes研究所，伦敦大学学院计算机科学系）；Instituto de Investigación Sanitaria Gregorio Marañón (IiSGM), Madrid（Gregorio Marañón卫生研究所（IiSGM），马德里）
The paradigm shift from shallow classifiers with hand-crafted features to end-to-end trainable deep learning models has shown significant improvements on supervised learning tasks. Despite the promising power of deep neural networks (DNN), how to alleviate overfitting during training has been a research topic of interest. In this paper, we present a Generative-Discriminative Variational Model (GDVM) for visual classification, in which we introduce a latent variable inferred from inputs for exhibiting generative abilities towards prediction. In other words, our GDVM casts the supervised learnin…
University College London（伦敦大学学院）；Shanghai Jiao Tong University（上海交通大学）；Alibaba Group（阿里巴巴集团）；Tianjin University（天津大学）；Birkbeck, University of London（伦敦大学伯贝克学院）
This paper provides a unified account of two schools of thinking in information retrieval modelling: the generative retrieval focusing on predicting relevant documents given a query, and the discriminative retrieval focusing on predicting relevancy given a query-document pair. We propose a game theoretical minimax game to iteratively optimise both models. On one hand, the discriminative model, aiming to mine signals from labelled and unlabelled data, provides guidance to train the generative model towards fitting the underlying relevance distribution over documents given the query. On the othe…
Tandem mass spectrometry (MS/MS) is a high-throughput technology used toidentify the proteins in a complex biological sample, such as a drop of blood. A collection of spectra is generated at the output of the process, each spectrum of which is representative of a peptide (protein subsequence) present in the original complex sample. In this work, we leverage the log-likelihood gradients of generative models to improve the identification of such spectra. In particular, we show that the gradient of a recently proposed dynamic Bayesian network (DBN) may be naturally employed by a kernel-based disc…
Masked Face Recognition with Generative-to-Discriminative Representations
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security at University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；Cloud Music Inc.（网易云音乐）；Department of Communication Engineering, Shanghai University（上海大学通信工程系）
