Chenwei Wang

Chenwei Wang, Xiaoyu Liu, Yulin Huang et al.

Convolutional neural networks (CNNs) have achieved high performance in synthetic aperture radar (SAR) automatic target recognition (ATR). However, the performance of CNNs depends heavily on a large amount of training data. The insufficiency of labeled training SAR images limits the recognition performance and even invalidates some ATR methods. Furthermore, under few labeled training data, many existing CNNs are even ineffective. To address these challenges, we propose a Semi-supervised SAR ATR Framework with transductive Auxiliary Segmentation (SFAS). The proposed framework focuses on exploiting the transductive generalization on available unlabeled samples with an auxiliary loss serving as a regularizer. Through auxiliary segmentation of unlabeled SAR samples and information residue loss (IRL) in training, the framework can employ the proposed training loop process and gradually exploit the information compilation of recognition and segmentation to construct a helpful inductive bias and achieve high performance. Experiments conducted on the MSTAR dataset have shown the effectiveness of our proposed SFAS for few-shot learning. The recognition performance of 94.18\% can be achieved under 20 training samples in each class with simultaneous accurate segmentation results. Facing variances of EOCs, the recognition ratios are higher than 88.00\% when 10 training samples each class.

Yang Zhang, Chenwei Wang, Ouyang Lu et al.

Vision-Language-Action (VLA) models pre-trained on large, diverse datasets show remarkable potential for general-purpose robotic manipulation. However, a primary bottleneck remains in adapting these models to downstream tasks, especially when the robot's embodiment or the task itself differs from the pre-training data. This discrepancy leads to a significant mismatch in action distributions, demanding extensive data and compute for effective fine-tuning. To address this challenge, we introduce \textbf{Align-Then-stEer (\texttt{ATE})}, a novel, data-efficient, and plug-and-play adaptation framework. \texttt{ATE} first aligns disparate action spaces by constructing a unified latent space, where a variational autoencoder constrained by reverse KL divergence embeds adaptation actions into modes of the pre-training action latent distribution. Subsequently, it steers the diffusion- or flow-based VLA's generation process during fine-tuning via a guidance mechanism that pushes the model's output distribution towards the target domain. We conduct extensive experiments on cross-embodiment and cross-task manipulation in both simulation and real world. Compared to direct fine-tuning of representative VLAs, our method improves the average multi-task success rate by up to \textbf{9.8\%} in simulation and achieves a striking \textbf{32\% success rate gain} in a real-world cross-embodiment setting. Our work presents a general and lightweight solution that greatly enhances the practicality of deploying VLA models to new robotic platforms and tasks.

Zelin Li, Chenwei Wang, Zhaoke Huang et al.

3D fluorescence microscopy is essential for understanding fundamental life processes through long-term live-cell imaging. However, due to inherent issues in imaging principles, it faces significant challenges including spatially varying noise and anisotropic resolution, where the axial resolution lags behind the lateral resolution up to 4.5 times. Meanwhile, laser power is kept low to maintain cell viability, leading to inaccessible low-noise and high-resolution paired ground truth (GT). To tackle these limitations, a dual Cycle-consistent Diffusion is proposed to effectively mine intra-volume imaging priors within 3D cell volumes in an unsupervised manner, i.e., Volume Tells (VTCD), achieving de-noising and super-resolution (SR) simultaneously. Specifically, a spatially iso-distributed denoiser is designed to exploit the noise distribution consistency between adjacent low-noise and high-noise regions within the 3D cell volume, suppressing the spatially varying noise. Then, in light of the structural consistency of the cell volume, a cross-plane global-propagation SR module propagates high-resolution details from the XY plane into adjacent regions in the XZ and YZ planes, progressively enhancing resolution across the entire 3D cell volume. Experimental results on 10 in vivo cellular dataset demonstrate high improvements in both denoising and super-resolution, with axial resolution enhanced from ~ 430 nm to ~ 90 nm.

Yu Tian, Chenwei Wang

We investigate the problem of wireless beam tracking on mmWave bands with the assistance of camera images. In particular, based on the user's beam indices used and camera images taken in the trajectory, we predict the optimal beam indices in the next few time spots. To resolve this problem, we first reformulate the "ViWi" dataset in [1] to get rid of the image repetition problem. Then we develop a deep learning approach and investigate various model components to achieve the best performance. Finally, we explore whether, when, and how to use the image for better beam prediction. To answer this question, we split the dataset into three clusters -- (LOS, light NLOS, serious NLOS)-like -- based on the standard deviation of the beam sequence. With experiments we demonstrate that using the image indeed helps beam tracking especially when the user is in serious NLOS, and the solution relies on carefully-designed dataset for training a model. Generally speaking, including NLOS-like data for training a model does not benefit beam tracking of the user in LOS, but including light NLOS-like data for training a model benefits beam tracking of the user in serious NLOS.

Yuan Wang, Chenwei Wang, Yinan Ling et al.

For short distance traveling in crowded urban areas, bike share services are becoming popular owing to the flexibility and convenience. To expand the service coverage, one of the key tasks is to seek new service ports, which requires to well understand the underlying features of the existing service ports. In this paper, we propose a new model, named for Efficient and Semantic Location Embedding (ESLE), which carries both geospatial and semantic information of the geo-locations. To generate ESLE, we first train a multi-label model with a deep Convolutional Neural Network (CNN) by feeding the static map-tile images and then extract location embedding vectors from the model. Compared to most recent relevant literature, ESLE is not only much cheaper in computation, but also easier to interpret via a systematic semantic analysis. Finally, we apply ESLE to seek new service ports for NTT DOCOMO's bike share services operated in Japan. The initial results demonstrate the effectiveness of ESLE, and provide a few insights that might be difficult to discover by using the conventional approaches.