The goal of few-shot classification is to classify new categories with few labeled examples within each class. Nowadays, the excellent performance in handling few-shot classification problems is shown by metric-based meta-learning methods. However, it is very hard for previous methods to discriminate the fine-grained sub-categories in the embedding space without fine-grained labels. This may lead to unsatisfactory generalization to fine-grained subcategories, and thus affects model interpretation. To tackle this problem, we introduce the contrastive loss into few-shot classification for learning latent fine-grained structure in the embedding space. Furthermore, to overcome the drawbacks of random image transformation used in current contrastive learning in producing noisy and inaccurate image pairs (i.e., views), we develop a learning-to-learn algorithm to automatically generate different views of the same image. Extensive experiments on standard few-shot learning benchmarks demonstrate the superiority of our method.
Few-Shot image classification aims to utilize pretrained knowledge learned from a large-scale dataset to tackle a series of downstream classification tasks. Typically, each task involves only few training examples from brand-new categories. This requires the pretraining models to focus on well-generalizable knowledge, but ignore domain-specific information. In this paper, we observe that image background serves as a source of domain-specific knowledge, which is a shortcut for models to learn in the source dataset, but is harmful when adapting to brand-new classes. To prevent the model from learning this shortcut knowledge, we propose COSOC, a novel Few-Shot Learning framework, to automatically figure out foreground objects at both pretraining and evaluation stage. COSOC is a two-stage algorithm motivated by the observation that foreground objects from different images within the same class share more similar patterns than backgrounds. At the pretraining stage, for each class, we cluster contrastive-pretrained features of randomly cropped image patches, such that crops containing only foreground objects can be identified by a single cluster. We then force the pretraining model to focus on found foreground objects by a fusion sampling strategy; at the evaluation stage, among images in each training class of any few-shot task, we seek for shared contents and filter out background. The recognized foreground objects of each class are used to match foreground of testing images. Extensive experiments tailored to inductive FSL tasks on two benchmarks demonstrate the state-of-the-art performance of our method.
Variational autoencoders (VAEs) have been widely applied for text modeling. In practice, however, they are troubled by two challenges: information underrepresentation and posterior collapse. The former arises as only the last hidden state of LSTM encoder is transformed into the latent space, which is generally insufficient to summarize the data. The latter is a long-standing problem during the training of VAEs as the optimization is trapped to a disastrous local optimum. In this paper, we propose Discrete Auto-regressive Variational Attention Model (DAVAM) to address the challenges. Specifically, we introduce an auto-regressive variational attention approach to enrich the latent space by effectively capturing the semantic dependency from the input. We further design discrete latent space for the variational attention and mathematically show that our model is free from posterior collapse. Extensive experiments on language modeling tasks demonstrate the superiority of DAVAM against several VAE counterparts.
Convolutional Neural Networks (CNNs) have achieved tremendous success in a number of learning tasks including image classification. Recent advanced models in CNNs, such as ResNets, mainly focus on the skip connection to avoid gradient vanishing. DenseNet designs suggest creating additional bypasses to transfer features as an alternative strategy in network design. In this paper, we design Attentive Feature Integration (AFI) modules, which are widely applicable to most recent network architectures, leading to new architectures named AFI-Nets. AFI-Nets explicitly model the correlations among different levels of features and selectively transfer features with a little overhead.AFI-ResNet-152 obtains a 1.24% relative improvement on the ImageNet dataset while decreases the FLOPs by about 10% and the number of parameters by about 9.2% compared to ResNet-152.
Sentiment analysis (SA) is an important research area in cognitive computation-thus in-depth studies of patterns of sentiment analysis are necessary. At present, rich resource data-based SA has been well developed, while the more challenging and practical multi-source unsupervised SA (i.e. a target domain SA by transferring from multiple source domains) is seldom studied. The challenges behind this problem mainly locate in the lack of supervision information, the semantic gaps among domains (i.e., domain shifts), and the loss of knowledge. However, existing methods either lack the distinguishable capacity of the semantic gaps among domains or lose private knowledge. To alleviate these problems, we propose a two-stage domain adaptation framework. In the first stage, a multi-task methodology-based shared-private architecture is employed to explicitly model the domain common features and the domain-specific features for the labeled source domains. In the second stage, two elaborate mechanisms are embedded in the shared private architecture to transfer knowledge from multiple source domains. The first mechanism is a selective domain adaptation (SDA) method, which transfers knowledge from the closest source domain. And the second mechanism is a target-oriented ensemble (TOE) method, in which knowledge is transferred through a well-designed ensemble method. Extensive experiment evaluations verify that the performance of the proposed framework outperforms unsupervised state-of-the-art competitors. What can be concluded from the experiments is that transferring from very different distributed source domains may degrade the target-domain performance, and it is crucial to choose the proper source domains to transfer from.
Tensor Decomposition Networks(TDNs) prevail for their inherent compact architectures. For providing convenience, we present a toolkit named TedNet that is based on the Pytorch framework, to give more researchers a flexible way to exploit TDNs. TedNet implements 5 kinds of tensor decomposition(i.e., CANDECOMP/PARAFAC(CP), Block-Term Tucker(BT), Tucker-2, Tensor Train(TT) and Tensor Ring(TR)) on traditional deep neural layers, the convolutional layer and the fully-connected layer. By utilizing these basic layers, it is simple to construct a variety of TDNs like TR-ResNet, TT-LSTM, etc. TedNet is available at https://github.com/tnbar/tednet.
Auto-Encoder (AE)-based deep subspace clustering (DSC) methods have achieved impressive performance due to the powerful representation extracted using deep neural networks while prioritizing categorical separability. However, self-reconstruction loss of an AE ignores rich useful relation information and might lead to indiscriminative representation, which inevitably degrades the clustering performance. It is also challenging to learn high-level similarity without feeding semantic labels. Another unsolved problem facing DSC is the huge memory cost due to $n\times n$ similarity matrix, which is incurred by the self-expression layer between an encoder and decoder. To tackle these problems, we use pairwise similarity to weigh the reconstruction loss to capture local structure information, while a similarity is learned by the self-expression layer. Pseudo-graphs and pseudo-labels, which allow benefiting from uncertain knowledge acquired during network training, are further employed to supervise similarity learning. Joint learning and iterative training facilitate to obtain an overall optimal solution. Extensive experiments on benchmark datasets demonstrate the superiority of our approach. By combining with the $k$-nearest neighbors algorithm, we further show that our method can address the large-scale and out-of-sample problems.
In this work, we generalize the reaction-diffusion equation in statistical physics, Schr\"odinger equation in quantum mechanics, Helmholtz equation in paraxial optics into the neural partial differential equations (NPDE), which can be considered as the fundamental equations in the field of artificial intelligence research. We take finite difference method to discretize NPDE for finding numerical solution, and the basic building blocks of deep neural network architecture, including multi-layer perceptron, convolutional neural network and recurrent neural networks, are generated. The learning strategies, such as Adaptive moment estimation, L-BFGS, pseudoinverse learning algorithms and partial differential equation constrained optimization, are also presented. We believe it is of significance that presented clear physical image of interpretable deep neural networks, which makes it be possible for applying to analog computing device design, and pave the road to physical artificial intelligence.
Disentanglement is defined as the problem of learninga representation that can separate the distinct, informativefactors of variations of data. Learning such a representa-tion may be critical for developing explainable and human-controllable Deep Generative Models (DGMs) in artificialintelligence. However, disentanglement in GANs is not a triv-ial task, as the absence of sample likelihood and posteriorinference for latent variables seems to prohibit the forwardstep. Inspired by contrastive learning (CL), this paper, froma new perspective, proposes contrastive disentanglement ingenerative adversarial networks (CD-GAN). It aims at dis-entangling the factors of inter-class variation of visual datathrough contrasting image features, since the same factorvalues produce images in the same class. More importantly,we probe a novel way to make use of limited amount ofsupervision to the largest extent, to promote inter-class dis-entanglement performance. Extensive experimental resultson many well-known datasets demonstrate the efficacy ofCD-GAN for disentangling inter-class variation.
Deep semi-supervised learning is a fast-growing field with a range of practical applications. This paper provides a comprehensive survey on both fundamentals and recent advances in deep semi-supervised learning methods from model design perspectives and unsupervised loss functions. We first present a taxonomy for deep semi-supervised learning that categorizes existing methods, including deep generative methods, consistency regularization methods, graph-based methods, pseudo-labeling methods, and hybrid methods. Then we offer a detailed comparison of these methods in terms of the type of losses, contributions, and architecture differences. In addition to the past few years' progress, we further discuss some shortcomings of existing methods and provide some tentative heuristic solutions for solving these open problems.