As a concrete application of multi-view learning, multi-view classification improves the traditional classification methods significantly by integrating various views optimally. Although most of the previous efforts have been demonstrated the superiority of multi-view learning, it can be further improved by comprehensively embedding more powerful cross-view interactive information and a more reliable multi-view fusion strategy in intensive studies. To fulfill this goal, we propose a novel multi-view learning framework to make the multi-view classification better aimed at the above-mentioned two aspects. That is, we seamlessly embed various intra-view information, cross-view multi-dimension bilinear interactive information, and a new view ensemble mechanism into a unified framework to make a decision via the optimization. In particular, we train different deep neural networks to learn various intra-view representations, and then dynamically learn multi-dimension bilinear interactive information from different bilinear similarities via the bilinear function between views. After that, we adaptively fuse the representations of multiple views by flexibly tuning the parameters of the view-weight, which not only avoids the trivial solution of weight but also provides a new way to select a few discriminative views that are beneficial to make a decision for the multi-view classification. Extensive experiments on six publicly available datasets demonstrate the effectiveness of the proposed method.
Given a content image and a style image, the goal of style transfer is to synthesize an output image by transferring the target style to the content image. Currently, most of the methods address the problem with global style transfer, assuming styles can be represented by global statistics, such as Gram matrices or covariance matrices. In this paper, we make a different assumption that local semantically aligned (or similar) regions between the content and style images should share similar style patterns. Based on this assumption, content features and style features are seen as two sets of manifolds and a manifold alignment based style transfer (MAST) method is proposed. MAST is a subspace learning method which learns a common subspace of the content and style features. In the common subspace, content and style features with larger feature similarity or the same semantic meaning are forced to be close. The learned projection matrices are added with orthogonality constraints so that the mapping can be bidirectional, which allows us to project the content features into the common subspace, and then into the original style space. By using a pre-trained decoder, promising stylized images are obtained. The method is further extended to allow users to specify corresponding semantic regions between content and style images or using semantic segmentation maps as guidance. Extensive experiments show the proposed MAST achieves appealing results in style transfer.
Skin disease classification from images is crucial to dermatological diagnosis. However, identifying skin lesions involves a variety of aspects in terms of size, color, shape, and texture. To make matters worse, many categories only contain very few samples, posing great challenges to conventional machine learning algorithms and even human experts. Inspired by the recent success of Few-Shot Learning (FSL) in natural image classification, we propose to apply FSL to skin disease identification to address the extreme scarcity of training sample problem. However, directly applying FSL to this task does not work well in practice, and we find that the problem can be largely attributed to the incompatibility between Cross Entropy (CE) and episode training, which are both commonly used in FSL. Based on a detailed analysis, we propose the Query-Relative (QR) loss, which proves superior to CE under episode training and is closely related to recently proposed mutual information estimation. Moreover, we further strengthen the proposed QR loss with a novel adaptive hard margin strategy. Comprehensive experiments validate the effectiveness of the proposed FSL scheme and the possibility to diagnosis rare skin disease with a few labeled samples.
The automatic extraction of animal \reb{3D} pose from images without markers is of interest in a range of scientific fields. Most work to date predicts animal pose from RGB images, based on 2D labelling of joint positions. However, due to the difficult nature of obtaining training data, no ground truth dataset of 3D animal motion is available to quantitatively evaluate these approaches. In addition, a lack of 3D animal pose data also makes it difficult to train 3D pose-prediction methods in a similar manner to the popular field of body-pose prediction. In our work, we focus on the problem of 3D canine pose estimation from RGBD images, recording a diverse range of dog breeds with several Microsoft Kinect v2s, simultaneously obtaining the 3D ground truth skeleton via a motion capture system. We generate a dataset of synthetic RGBD images from this data. A stacked hourglass network is trained to predict 3D joint locations, which is then constrained using prior models of shape and pose. We evaluate our model on both synthetic and real RGBD images and compare our results to previously published work fitting canine models to images. Finally, despite our training set consisting only of dog data, visual inspection implies that our network can produce good predictions for images of other quadrupeds -- e.g. horses or cats -- when their pose is similar to that contained in our training set.
Few-shot learning aims to learn a new concept when only a few training examples are available, which has been extensively explored in recent years. However, most of the current works heavily rely on a large-scale labeled auxiliary set to train their models in an episodic-training paradigm. Such a kind of supervised setting basically limits the widespread use of few-shot learning algorithms, especially in real-world applications. Instead, in this paper, we develop a novel framework called \emph{Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation} (ULDA), which pays attention to the distribution diversity inside each constructed pretext few-shot task when using data augmentation. Importantly, we highlight the value and importance of the distribution diversity in the augmentation-based pretext few-shot tasks. In ULDA, we systemically investigate the effects of different augmentation techniques and propose to strengthen the distribution diversity (or difference) between the query set and support set in each few-shot task, by augmenting these two sets separately (i.e. shifting). In this way, even incorporated with simple augmentation techniques (e.g. random crop, color jittering, or rotation), our ULDA can produce a significant improvement. In the experiments, few-shot models learned by ULDA can achieve superior generalization performance and obtain state-of-the-art results in a variety of established few-shot learning tasks on \emph{mini}ImageNet and \emph{tiered}ImageNet. %The code will be released soon. The source code is available in \textcolor{blue}{\emph{https://github.com/WonderSeven/ULDA}}.
The core idea of metric-based few-shot image classification is to directly measure the relations between query images and support classes to learn transferable feature embeddings. Previous work mainly focuses on image-level feature representations, which actually cannot effectively estimate a class's distribution due to the scarcity of samples. Some recent work shows that local descriptor based representations can achieve richer representations than image-level based representations. However, such works are still based on a less effective instance-level metric, especially a symmetric metric, to measure the relations between query images and support classes. Given the natural asymmetric relation between a query image and a support class, we argue that an asymmetric measure is more suitable for metric-based few-shot learning. To that end, we propose a novel Asymmetric Distribution Measure (ADM) network for few-shot learning by calculating a joint local and global asymmetric measure between two multivariate local distributions of queries and classes. Moreover, a task-aware Contrastive Measure Strategy (CMS) is proposed to further enhance the measure function. On popular miniImageNet and tieredImageNet, we achieve $3.02\%$ and $1.56\%$ gains over the state-of-the-art method on the $5$-way $1$-shot task, respectively, validating our innovative design of asymmetric distribution measures for few-shot learning.
Few-shot image classification requires the classifier to robustly cope with unseen classes even if there are only a few samples for each class. Recent advances benefit from the meta-learning process where episodic tasks are formed to train a model that can adapt to class change. However, these tasks are independent to each other and existing works mainly rely on limited samples of individual support set in a single meta task. This strategy leads to severe meta shift issues across multiple tasks, meaning the learned prototypes or class descriptors are not stable as each task only involves their own support set. To avoid this problem, we propose a concise Class Regularization Network which aggregates the embedding features of all samples in the entire training set and further regularizes the generated class descriptor. The key is to train a class encoder and decoder structure that can encode the embedding sample features into a class domain with trained class basis, and generate a more stable and general class descriptor from the decoder. We evaluate our work by extensive comparisons with previous methods on two benchmark datasets (MiniImageNet and CUB). The results show that our method achieves state-of-the-art performance over previous work.
The robustness of deep learning models against adversarial attacks has received increasing attention in recent years. However, both deep learning and adversarial training rely on the availability of a large amount of labeled data and usually do not generalize well to new, unseen classes when only a few training samples are accessible. To address this problem, we explicitly introduce a new challenging problem -- how to learn a robust deep model with limited training samples per class, called defensive few-shot learning in this paper. Simply employing the existing adversarial training techniques in the literature cannot solve this problem. This is because few-shot learning needs to learn transferable knowledge from disjoint auxiliary data, and thus it is invalid to assume the sample-level distribution consistency between the training and test sets as commonly assumed in existing adversarial training techniques. In this paper, instead of assuming such a distribution consistency, we propose to make this assumption at a task-level in the episodic training paradigm in order to better transfer the defense knowledge. Furthermore, inside each task, we design a task-conditioned distribution constraint to narrow the distribution gap between clean and adversarial examples at a sample-level. These give rise to a novel mechanism called multi-level distribution based adversarial training (MDAT) for learning transferable adversarial defense. In addition, a unified $\mathcal{F}_{\beta}$ score is introduced to evaluate different defense methods under the same principle. Extensive experiments demonstrate that MDAT achieves higher effectiveness and robustness over existing alternatives in the few-shot case.
Understanding physical phenomena is a key competence that enables humans and animals to act and interact under uncertain perception in previously unseen environments containing novel objects and their configurations. In this work, we consider the problem of autonomous block stacking and explore solutions to learning manipulation under physics constraints with visual perception inherent to the task. Inspired by the intuitive physics in humans, we first present an end-to-end learning-based approach to predict stability directly from appearance, contrasting a more traditional model-based approach with explicit 3D representations and physical simulation. We study the model's behavior together with an accompanied human subject test. It is then integrated into a real-world robotic system to guide the placement of a single wood block into the scene without collapsing existing tower structure. To further automate the process of consecutive blocks stacking, we present an alternative approach where the model learns the physics constraint through the interaction with the environment, bypassing the dedicated physics learning as in the former part of this work. In particular, we are interested in the type of tasks that require the agent to reach a given goal state that may be different for every new trial. Thereby we propose a deep reinforcement learning framework that learns policies for stacking tasks which are parametrized by a target structure.
Few-shot learning in image classification aims to learn a classifier to classify images when only few training examples are available for each class. Recent work has achieved promising classification performance, where an image-level feature based measure is usually used. In this paper, we argue that a measure at such a level may not be effective enough in light of the scarcity of examples in few-shot learning. Instead, we think a local descriptor based image-to-class measure should be taken, inspired by its surprising success in the heydays of local invariant features. Specifically, building upon the recent episodic training mechanism, we propose a Deep Nearest Neighbor Neural Network (DN4 in short) and train it in an end-to-end manner. Its key difference from the literature is the replacement of the image-level feature based measure in the final layer by a local descriptor based image-to-class measure. This measure is conducted online via a $k$-nearest neighbor search over the deep local descriptors of convolutional feature maps. The proposed DN4 not only learns the optimal deep local descriptors for the image-to-class measure, but also utilizes the higher efficiency of such a measure in the case of example scarcity, thanks to the exchangeability of visual patterns across the images in the same class. Our work leads to a simple, effective, and computationally efficient framework for few-shot learning. Experimental study on benchmark datasets consistently shows its superiority over the related state-of-the-art, with the largest absolute improvement of $17\%$ over the next best. The source code can be available from \UrlFont{https://github.com/WenbinLee/DN4.git}.