Weak feature representation problem has influenced the performance of few-shot classification task for a long time. To alleviate this problem, recent researchers build connections between support and query instances through embedding patch features to generate discriminative representations. However, we observe that there exists semantic mismatches (foreground/ background) among these local patches, because the location and size of the target object are not fixed. What is worse, these mismatches result in unreliable similarity confidences, and complex dense connection exacerbates the problem. According to this, we propose a novel Clustered-patch Element Connection (CEC) layer to correct the mismatch problem. The CEC layer leverages Patch Cluster and Element Connection operations to collect and establish reliable connections with high similarity patch features, respectively. Moreover, we propose a CECNet, including CEC layer based attention module and distance metric. The former is utilized to generate a more discriminative representation benefiting from the global clustered-patch features, and the latter is introduced to reliably measure the similarity between pair-features. Extensive experiments demonstrate that our CECNet outperforms the state-of-the-art methods on classification benchmark. Furthermore, our CEC approach can be extended into few-shot segmentation and detection tasks, which achieves competitive performances.

Few-shot learning problem focuses on recognizing unseen classes given a few labeled images. In recent effort, more attention is paid to fine-grained feature embedding, ignoring the relationship among different distance metrics. In this paper, for the first time, we investigate the contributions of different distance metrics, and propose an adaptive fusion scheme, bringing significant improvements in few-shot classification. We start from a naive baseline of confidence summation and demonstrate the necessity of exploiting the complementary property of different distance metrics. By finding the competition problem among them, built upon the baseline, we propose an Adaptive Metrics Module (AMM) to decouple metrics fusion into metric-prediction fusion and metric-losses fusion. The former encourages mutual complementary, while the latter alleviates metric competition via multi-task collaborative learning. Based on AMM, we design a few-shot classification framework AMTNet, including the AMM and the Global Adaptive Loss (GAL), to jointly optimize the few-shot task and auxiliary self-supervised task, making the embedding features more robust. In the experiment, the proposed AMM achieves 2% higher performance than the naive metrics fusion module, and our AMTNet outperforms the state-of-the-arts on multiple benchmark datasets.

This paper focus on few-shot object detection~(FSOD) and instance segmentation~(FSIS), which requires a model to quickly adapt to novel classes with a few labeled instances. The existing methods severely suffer from bias classification because of the missing label issue which naturally exists in an instance-level few-shot scenario and is first formally proposed by us. Our analysis suggests that the standard classification head of most FSOD or FSIS models needs to be decoupled to mitigate the bias classification. Therefore, we propose an embarrassingly simple but effective method that decouples the standard classifier into two heads. Then, these two individual heads are capable of independently addressing clear positive samples and noisy negative samples which are caused by the missing label. In this way, the model can effectively learn novel classes while mitigating the effects of noisy negative samples. Without bells and whistles, our model without any additional computation cost and parameters consistently outperforms its baseline and state-of-the-art by a large margin on PASCAL VOC and MS-COCO benchmarks for FSOD and FSIS tasks.\footnote{\url{https://csgaobb.github.io/Projects/DCFS}.}

This paper studies target classification by using both feature data and kinematic measurements. The problem is tackled in a distributed architecture, where local deciders make decisions based on their local data and the center fuses local decisions, both by a multi-hypothesis sequential test. We adopt the matrix sequential probability ratio test (SPRT) for the local tests and the fusion rule. The centralized fusion and distributed fusion are compared. A lower bound on the overall average sample number of distributed fusion is presented to help determine the thresholds of the local tests to improve the performance of distributed fusion. Numerical results are provided to demonstrate the performance of our algortthm.

Recently there has been a lot of interest in geometrically motivated approaches dealing with data in high dimensional spaces. We consider the case where data is sampled from a low dimensional manifold which is embedded in high dimensional Euclidean space. In this paper, we propose a novel unsupervised linear subspace learning algorithm called Local and Global Manifold Preserving Embedding (LGMPE). Different from existing manifold learning based linear subspace learning algorithms which aims at preserving either single kind of local manifold structure or single kind of global manifold structure on the data manifold, LGMPE can preserve different local and global manifold structures simultaneously in the graph embedding framework. Several experiments on real face datasets demonstrate the effectiveness of the proposed algorithm.

A distributed interference coordination scheme is proposed to alleviate cross‐tier and inner‐tier interference in heterogeneous network (HetNet), consisting of a power control strategy based on game theory to acquire both Nash equilibrium among femtocells and Stackelberg equilibrium between femtocells and macrocells. Component carrier assignment is the other interference coordination dimension for HetNet with carrier aggregation. The proposed method is a two‐dimensional interference coordination scheme combining power control and component carrier assignment. The simulation results demonstrate the effectiveness and improvement of the proposed scheme.

Research in the areas of 3-D face recognition and 3-D facial expression analysis has intensified in recent years. However, most research has been focused on 3-D static data analysis. In this paper, we investigate the facial analysis problem using dynamic 3-D face model sequences. One of the major obstacles for analyzing such data is the lack of correspondences of features due to the variable number of vertices across individual models or 3-D model sequences. In this paper, we present an effective approach for establishing vertex correspondences using a tracking-model-based approach for vertex registration, coarse-to-fine model adaptation, and vertex motion trajectory (called vertex flow) estimation. We propose to establish correspondences across frame models based on a 2-D intermediary, which is generated using conformal mapping and a generic model adaptation algorithm. Based on our newly created 3-D dynamic face database, we also propose to use a spatiotemporal hidden Markov model (ST-HMM) that incorporates 3-D surface feature characterization to learn the spatial and temporal information of faces. The advantage of using 3-D dynamic data for face recognition has been evaluated by comparing our approach to three conventional approaches: 2-D-video-based temporal HMM model, conventional 2-D-texture-based approach (e.g., Gabor-wavelet-based approach), and static 3-D-model-based approaches. To further evaluate the usefulness of vertex flow and the adapted model, we have also applied a spatial-temporal face model descriptor for facial expression classification based on dynamic 3-D model sequences.

Face information processing relies on the quality of data resource. From the data modality point of view, a face database can be 2D or 3D, and static or dynamic. From the task point of view, the data can be used for research of computer based automatic face recognition, face expression recognition, face detection, or cognitive and psychological investigation. With the advancement of 3D imaging technologies, 3D dynamic facial sequences (called 4D data) have been used for face information analysis. In this paper, we focus on the modality of 3D dynamic data for the task of facial expression recognition. We present a newly created high-resolution 3D dynamic facial expression database, which is made available to the scientific research community. The database contains 606 3D facial expression sequences captured from 101 subjects of various ethnic backgrounds. The database has been validated through our facial expression recognition experiment using an HMM based 3D spatio-temporal facial descriptor. It is expected that such a database shall be used to facilitate the facial expression analysis from a static 3D space to a dynamic 3D space, with a goal of scrutinizing facial behavior at a higher level of detail in a real 3D spatio-temporal domain.