In this paper, we propose a dual-module network architecture that employs domain discriminative feature module to encourage the invariant learn more features. The proposed can be applied any model utilizes features for unsupervised adaptation improve its ability extract We conduct experiments with Domain-Adversarial Training of Neural Networks (DANN) as representative algorithm. training proces...

Biometric signal based human-computer interface (HCI) has attracted increasing attention due to its wide application in healthcare, entertainment, neurocomputing, and so on. In recent years, deep learning approaches have made great progress on biometric processing. However, the state-of-the-art (SOTA) still suffer from model degradation across subjects or sessions. this work, we propose a novel...

In this paper, we propose an unsupervised domain adaptation for Word Sense Disambiguation (WSD) using Stacked Denoising Autoencoder (SdA). SdA is an unsupervised learning method of obtaining the abstract feature set of input data using Neural Network. The abstract feature set absorbs the difference of domains, and thus SdA can solve a problem of domain adaptation. However, SdA does not always c...

Unsupervised domain adaptation on person re-identification (re-ID), which adapts the model trained source dataset to target dataset, has drawn increasing attention over past few years. It is more practical than traditional supervised methods when applied in real-world scenarios since they require a huge number of manual annotations specific domain, unrealistic and even under personal privacy co...

Semantic segmentation is an important task for intelligent vehicles to understand the environment. Current deep learning based methods require large amounts of labeled data training. Manual annotation expensive, while simulators can provide accurate annotations. However, performance semantic model trained with synthetic datasets will significantly degenerate in actual scenes. Unsupervised domai...

In recent years, computer vision tasks have increasingly used deep learning techniques. some tasks, however, due to insufficient data, the model is not properly trained, leading a decrease in generalizability. When trained on dataset and tested another similar dataset, predicts near-random results. This paper presents an unsupervised multi-source domain adaptation that improves transfer increas...

Unsupervised person re-identification (re-ID) is becoming increasingly popular due to its power in real-world systems such as public security and intelligent transportation systems. However, the re-ID task challenged by problems of data distribution discrepancy across cameras lack label information. In this paper, we propose a coarse-to-fine heterogeneous graph alignment (HGA) method find cross...