XMXiaoxiao Ma

Xiaoxiao Ma

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Xiaoxiao Ma has a total of 52 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    MAR-GRPO: Stabilized GRPO for AR-diffusion Hybrid Image Generation

    by Xiaoxiao Ma, Jiachen Lei, Tianfei Ren, Jie Huang, Siming Fu, Aiming Hao, Jiahong Wu, Xiangxiang Chu, Feng Zhao

  • Rein++: Efficient Generalization and Adaptation for Semantic Segmentation With Vision Foundation Models

    by Zhixiang Wei, Xiaoxiao Ma, Ruishen Yan, Tao Tu, Huaian Chen, Jinjin Zheng, Yi Jin, Enhong Chen

    Vision Foundation Models(VFMs) have achieved remarkable success in various computer vision tasks. However, their application to semantic segmentation is hindered by two significant challenges: (1) the disparity in data scale, as segmentation datasets are typically much smaller than those used for VFM pre-training, and (2) domain distribution shifts, where real-world segmentation scenarios are diverse and often underrepresented during pre-training. To overcome these limitations, we present Rein++, an efficient VFM-based segmentation framework that demonstrates superior generalization from limited data and enables effective adaptation to diverse unlabeled scenarios. Specifically, Rein++ comprises a domain generalization solution Rein G and a domain adaptation solution Rein-A. Rein-G introduces a set of trainable, instance-aware tokens that effectively refine the VFM's features for the segmentation task. This parameter efficient approach fine-tunes less than 1% of the backbone's parameters, enabling robust generalization. Building on the Rein-G, Rein-A performs unsupervised domain adaptation at both the instance and logit levels to mitigate domain shifts. In addition, it incorporates a semantic transfer module that leverages the class-agnostic capabilities of the segment anything model to enhance boundary details in the target domain. The integrated Rein++ pipeline first learns a generalizable model on a source domain (e.g., daytime scenes) and subsequently adapts it to diverse target domains (e.g., nighttime scenes) without any target labels. Comprehensive experiments demonstrate that Rein++ significantly outperforms state-of-the-art methods with efficient training, underscoring its roles an efficient, generalizable, and adaptive segmentation solution for VFMs, even for large models with billions of parameters. The code is available at https://github.com/wloves/Rein.


  • Masked Video Pretraining Advances Real-World Video Denoising

    by Yi Jin, Xiaoxiao Ma, Rui Zhang, Huaian Chen, Yuxuan Gu, Pengyang Ling, Enhong Chen

    Learning-based video denoisers have attained state-of-the-art (SOTA) performances on public evaluation benchmarks. Nevertheless, they typically encounter significant performance drops when applied to unseen real-world data, owing to inherent data discrepancies. To address this problem, this work delves into the model pretraining techniques and proposes masked central frame modeling (MCFM), a new video pretraining approach that significantly improves the generalization ability of the denoiser. This proposal stems from a key observation: pretraining denoiser by reconstructing intact videos from the corrupted sequences, where the central frames are masked at a suitable probability, contributes to achieving superior performance on real-world data. Building upon MCFM, we introduce a robust video denoiser, named MVDenoiser, which is firstly pretrained on massive available ordinary videos for general video modeling, and then finetuned on costful real-world noisy/clean video pairs for noisy-to-clean mapping. Additionally, beyond the denoising model, we further establish a new paired real-world noisy video dataset (RNVD) to facilitate cross-dataset evaluation of generalization ability. Extensive experiments conducted across different datasets demonstrate that the proposed method achieves superior performance compared to existing methods. Code and dataset are available at https://github.com/mxxx99/MVDenoiser .


  • Domain Adaptative Video Semantic Segmentation via Motion-Guided Domain Bridge

    by Wenchao Guan, Ben Wang, Xiaoxiao Ma, Junkang Dai, Chengfeng Kong, Lin Chen, Zhixiang Wei, Yi Jin, Huaian Chen

    Domain bridging aims to eliminate discrepancies across domains by establishing an intermediary domain, enabling gradual domain adaptation. However, in the realm of video segmentation, existing methods often yield inaccurate motion within this intermediary domain, especially when tackling complex temporal sequences involving both object and camera movements. To overcome this challenge, we introduce a Motion-guided Domain Bridge (MDBridge), which constructs an aligned video intermediary domain and strengthens motion awareness. Central to MDBridge is the Motion-Aligned Domain Bridge , which unifies the relative camera movements into a consistent ego-motion by leveraging depth and motion priors. Complementing this, the Motion Perception Module , which utilizes monocular and binocular vision to establish a spatial perception structure, is developed to capture and utilize aligned motion information. Notably, both motion and depth information are derived using a self-supervised depth estimation strategy, without the need for external depth ground truth, allowing us to directly integrate into existing tasks without extra annotation costs. These progressive steps collectively extract and leverage temporal information from complex temporal scenarios, ensuring smooth domain transition during video segmentation training. Extensive experiments validate the superiority of our approach over previous state-of-the-art methods.


  • Seed Optimization With Frozen Generator for Superior Zero-Shot Low-Light Image Enhancement

    by Yuxuan Gu, Yi Jin, Ben Wang, Zhixiang Wei, Xiaoxiao Ma, Haoxuan Wang, Pengyang Ling, Huaian Chen, Enhong Chen

    In this work, we observe that the generators, which are pre-trained on massive natural images, inherently hold the promising potential for superior low-light image enhancement against varying scenarios. Specifically, for the low-light image enhancement process of a single image, we introduce the pre-trained generators to restore the details and colors degraded by low-light conditions, thereby improving the visual effect. Taking one step further, we introduce a novel optimization strategy, which backpropagates the gradients to the input seeds rather than the parameters of the low-light image enhancement model, thus intactly retaining the generative knowledge learned from natural images and achieving faster convergence speed. Benefiting from the pre-trained knowledge and seed-optimization strategy, the low-light image enhancement model can significantly regularize the visibility and fidelity of the enhanced result, thus rapidly generating high-quality images without training on any low-light dataset. Extensive experiments on various benchmarks demonstrate the effectiveness of the proposed method, showing its potential advantages over numerous state-of-the-art methods both qualitatively and quantitatively.


  • Wheat-bran-based hierarchically porous biochar as electrode materials for supercapacitors

    by Sijing Zhang, Xiaoxiao Ma, Yile Du, Yutong Li, Jun Lin, Shuangli Chen


  • Open Access

    Automating Method Naming with Context-Aware Prompt-Tuning

    by Jie Zhu, Lingwei Li, Li Yang, Xiaoxiao Ma, Chun Zuo

    Method names are crucial to program comprehension and maintenance. Recently, many approaches have been proposed to automatically recommend method names and detect inconsistent names. Despite promising, their results are still sub-optimal considering the three following drawbacks: 1) These models are mostly trained from scratch, learning two different objectives simultaneously. The misalignment between two objectives will negatively affect training efficiency and model performance. 2) The enclosing class context is not fully exploited, making it difficult to learn the abstract function of the method. 3) Current method name consistency checking methods follow a generate-then-compare process, which restricts the accuracy as they highly rely on the quality of generated names and face difficulty measuring the semantic consistency. In this paper, we propose an approach named AUMENA to AUtomate MEthod NAming tasks with context-aware prompt-tuning. Unlike existing deep learning based approaches, our model first learns the contextualized representation(i.e., class attributes) of PL and NL through the pre-training model, then fully exploits the capacity and knowledge of large language model with prompt-tuning to precisely detect inconsistent method names and recommend more accurate names. To better identify semantically consistent names, we model the method name consistency checking task as a two-class classification problem, avoiding the limitation of previous similarity-based consistency checking approaches. The experimental results reflect that AUMENA scores 68.6%, 72.0%, 73.6%, 84.7% on four datasets of method name recommendation, surpassing the state-of-the-art baseline by 8.5%, 18.4%, 11.0%, 12.0%, respectively. And our approach scores 80.8% accuracy on method name consistency checking, reaching an 5.5% outperformance. All data and trained models are publicly available.

  • Relationships between patient-related attitudinal barriers, analgesic adherence and pain relief in Chinese cancer inpatients

    by Xiaoxiao Ma, Yuhan Lu, Hong Yang, Wenhua Yu, Xiaoting Hou, Renxiu Guo, Yun Wang, Yaru Zhang

    The purpose of this study was to evaluate patient-related attitudinal barriers and identify associated factors in Chinese cancer inpatients receiving opioids and to explore relationships between patient-related attitudinal barriers, analgesic adherence and pain relief.