On the Performance of Multidimensional Constellation Shaping for Linear and Nonlinear Optical Fiber Channel

Multidimensional constellation shaping of up to 32 dimensions with different spectral efficiencies are compared through AWGN and fiber-optic simulations. The results show that no constellation is universal and the balance of required and effective SNRs should be jointly considered for the specific optical transmission scenario.

Analytical Model of Nonlinear Fiber Propagation for General Dual-Polarization Four-Dimensional Modulation Format

Coherent dual-polarization (DP) optical transmission systems encode information on the four available degrees of freedom of an optical field: the two polarization states, each with two quadrature components. Such systems naturally operate based on a four-dimensional (4D) signal space. Having a general analytical model to accurately estimate nonlinear interference (NLI) is key to analyze such transmission systems as well as to study how different DP-4D formats are affected by NLI. However, the available models in the literature are not completely general. They either do not apply to the entire DP-4D formats or do not consider all the NLI contributions. In this paper we develop a model that applies to the entire class of DP-4D modulation formats. Our model takes self-channel interference, cross-channel interference and multiple-channel interference effects into account. As an application of our model, we further study the effects of signal-noise interactions in long-haul transmission via the proposed model. When compared to previous results in the literature, our model is more accurate at predicting the contribution of NLI for both low and high dispersion fibers in single- and multi-channel transmission systems. For the NLI, we report an average gap from split step Fourier simulation results below 0.15dB. The simulation results further show that by considering signal-noise interactions, the proposed model in long-haul transmission improves the NLI power accuracy prediction by up to 8.5%.

Geometrically-Shaped Multi-Dimensional Modulation Formats in Coherent Optical Transmission Systems

Shaping modulation formats in multi-dimensional (MD) space is an effective approach to harvest spectral efficiency gains in both the additive white Gaussian noise (AWGN) channel and the optical fiber channel. In the first part of this paper, existing MD geometrically-shaped modulations for fiber optical communications are reviewed. It is shown that large gains can be obtained by exploiting correlation in the dimensions or/and by increasing the cardinality of the modulation format. Practical limitations and challenges are also discussed together with efficient solutions. In the second part, we extend the recently proposed four-dimensional (4D) modulation format family based on the constraint of orthant-symmetry to high spectrum efficiencies up to 10 bit/4D-sym by maximizing generalized mutual information for AWGN channel. Reach increases of up to 25% for a multi-span optical fiber transmission system are reported. Lastly,with the help of a recently introduced nonlinear interference (NLI) model, an optimization for designing nonlinear-tolerant 4D modulation formats is introduced for a single-span optical fiber system. Simulation results show that the proposed NLI model-based 4D modulation format could increase the effective SNRs by 0.25 dB with respect to the AWGN channel-optimal 4D modulation format.

Extension and Validation of 4D Model for Improving the Accuracy of Modulation-Dependent Nonlinear Interference

Existing nonlinear interference (NLI) model underestimates the NLI of dual polarization four-dimensional (4D) modulation in long-haul transmission, due to the ignorance of nonlinearity caused by signal-ASE interaction. We propose an enhanced 4D model by lifting an underlying assumption, which could improve the performance prediction accuracy.

Short Range Correlation Transformer for Occluded Person Re-Identification

Occluded person re-identification is one of the challenging areas of computer vision, which faces problems such as inefficient feature representation and low recognition accuracy. Convolutional neural network pays more attention to the extraction of local features, therefore it is difficult to extract features of occluded pedestrians and the effect is not so satisfied. Recently, vision transformer is introduced into the field of re-identification and achieves the most advanced results by constructing the relationship of global features between patch sequences. However, the performance of vision transformer in extracting local features is inferior to that of convolutional neural network. Therefore, we design a partial feature transformer-based person re-identification framework named PFT. The proposed PFT utilizes three modules to enhance the efficiency of vision transformer. (1) Patch full dimension enhancement module. We design a learnable tensor with the same size as patch sequences, which is full-dimensional and deeply embedded in patch sequences to enrich the diversity of training samples. (2) Fusion and reconstruction module. We extract the less important part of obtained patch sequences, and fuse them with original patch sequence to reconstruct the original patch sequences. (3) Spatial Slicing Module. We slice and group patch sequences from spatial direction, which can effectively improve the short-range correlation of patch sequences. Experimental results over occluded and holistic re-identification datasets demonstrate that the proposed PFT network achieves superior performance consistently and outperforms the state-of-the-art methods.

Utilizing BERT Intermediate Layers for Aspect Based Sentiment Analysis and Natural Language Inference

Aspect based sentiment analysis aims to identify the sentimental tendency towards a given aspect in text. Fine-tuning of pretrained BERT performs excellent on this task and achieves state-of-the-art performances. Existing BERT-based works only utilize the last output layer of BERT and ignore the semantic knowledge in the intermediate layers. This paper explores the potential of utilizing BERT intermediate layers to enhance the performance of fine-tuning of BERT. To the best of our knowledge, no existing work has been done on this research. To show the generality, we also apply this approach to a natural language inference task. Experimental results demonstrate the effectiveness and generality of the proposed approach.

CatGAN: Category-aware Generative Adversarial Networks with Hierarchical Evolutionary Learning for Category Text Generation

Generating multiple categories of texts is a challenging task and draws more and more attention. Since generative adversarial nets (GANs) have shown competitive results on general text generation, they are extended for category text generation in some previous works. However, the complicated model structures and learning strategies limit their performance and exacerbate the training instability. This paper proposes a category-aware GAN (CatGAN) which consists of an efficient category-aware model for category text generation and a hierarchical evolutionary learning algorithm for training our model. The category-aware model directly measures the gap between real samples and generated samples on each category, then reducing this gap will guide the model to generate high-quality category samples. The Gumbel-Softmax relaxation further frees our model from complicated learning strategies for updating CatGAN on discrete data. Moreover, only focusing on the sample quality normally leads the mode collapse problem, thus a hierarchical evolutionary learning algorithm is introduced to stabilize the training procedure and obtain the trade-off between quality and diversity while training CatGAN. Experimental results demonstrate that CatGAN outperforms most of the existing state-of-the-art methods.