Domain Adaptation With Neural Embedding Matching

Predicting the Generalization Ability of a Few-Shot Classifier

In the context of few-shot learning, one cannot measure the generalization ability of a trained classifier using validation sets, due to the small number of labeled samples. In this paper, we are interested in finding alternatives to answer the question: is my classifier generalizing well to new data? We investigate the case of transfer-based few-shot learning solutions, and consider three settings: (i) supervised where we only have access to a few labeled samples, (ii) semi-supervised where we have access to both a few labeled samples and a set of unlabeled samples and (iii) unsupervised where we only have access to unlabeled samples. For each setting, we propose reasonable measures that we empirically demonstrate to be correlated with the generalization ability of the considered classifiers. We also show that these simple measures can predict the generalization ability up to a certain confidence. We conduct our experiments on standard few-shot vision datasets.

Multi-Temporal Scene Classification and Scene Change Detection With Correlation Based Fusion

Classifying multi-temporal scene land-use categories and detecting their semantic scene-level changes for remote sensing imagery covering urban regions could straightly reflect the land-use transitions. Existing methods for scene change detection rarely focus on the temporal correlation of bi-temporal features, and are mainly evaluated on small scale scene change detection datasets. In this work, we proposed a CorrFusion module that fuses the highly correlated components in bi-temporal feature embeddings. We first extract the deep representations of the bi-temporal inputs with deep convolutional networks. Then the extracted features will be projected into a lower-dimensional space to extract the most correlated components and compute the instance-level correlation. The cross-temporal fusion will be performed based on the computed correlation in CorrFusion module. The final scene classification results are obtained with softmax layers. In the objective function, we introduced a new formulation to calculate the temporal correlation more efficiently and stably. The detailed derivation of backpropagation gradients for the proposed module is also given. Besides, we presented a much larger scale scene change detection dataset with more semantic categories and conducted extensive experiments on this dataset. The experimental results demonstrated that our proposed CorrFusion module could remarkably improve the multi-temporal scene classification and scene change detection results.

Subspace Distribution Adaptation Frameworks for Domain Adaptation

Domain adaptation tries to adapt a model trained from a source domain to a different but related target domain. Currently, prevailing methods for domain adaptation rely on either instance reweighting or feature transformation. Unfortunately, instance reweighting has difficulty in estimating the sample weights as the dimension increases, whereas feature transformation sometimes fails to make the transformed source and target distributions similar when the cross-domain discrepancy is large. In order to overcome the shortcomings of both methodologies, in this article, we model the unsupervised domain adaptation problem under the generalized covariate shift assumption and adapt the source distribution to the target distribution in a subspace by applying a distribution adaptation function. Accordingly, we propose two frameworks: Bregman-divergence-embedded structural risk minimization (BSRM) and joint structural risk minimization (JSRM). In the proposed frameworks, the subspace distribution adaptation function and the target prediction model are jointly learned. Under certain instantiations, convex optimization problems are derived from both frameworks. Experimental results on the synthetic and real-world text and image data sets show that the proposed methods outperform the state-of-the-art domain adaptation techniques with statistical significance.

Stroke Sequence-Dependent Deep Convolutional Neural Network for Online Handwritten Chinese Character Recognition

We propose a novel model, called stroke sequence-dependent deep convolutional neural network (SSDCNN), which uses the stroke sequence information and eight-directional features of Chinese characters for online handwritten Chinese character recognition (OLHCCR). SSDCNN learns the representation of OLHCCs by incorporating the natural sequence information of the strokes. Furthermore, it naturally incorporates the eight-directional features. First, SSDCNN inputs the stroke sequence and transforms it into stacks of feature maps following the writing order of the strokes. Second, the fixed-length, stroke sequence-dependent representations of OLHCC are derived through convolutional, residual, and max-pooling operations. Third, the stroke sequence-dependent representation is combined with the eight-directional features via a number of fully connected neural network layers. Finally, the Chinese characters are recognized using a softmax classifier. The SSDCNN is trained in two stages: 1) the whole architecture is pretrained using the training data until the performance converges to an acceptable degree. 2) The stroke sequence-dependent representation is combined with the eight-directional features by a fully connected neural network and a softmax layer for further training. The model was experimentally evaluated on the OLHCCR competition tasks of International Conference on Document Analysis and Recognition (ICDAR) 2013. The recognition error was a maximum 58.28% lower in SSDCNN than in a model using the eight-directional features alone (5.13% versus 2.14%). Owing to its high accuracy (97.86%), the proposed SSDCNN reduced the recognition error by approximately 18.0% as compared with that of the winning system in the ICDAR 2013 competition. SSDCNN integrated with an adaptation mechanism, called the SSDCNN+Adapt model, and reached a new state-of-the-art (SOTA) standard with an accuracy of 97.94%. The SSDCNN exploits the stroke sequence information to learn high-quality OLHCC representations. Moreover, the learned representation and the classical eight-directional features complement each other within the SSDCNN architecture.