RDRuoxi Deng

Ruoxi Deng

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ruoxi Deng has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Advancing Semantic Edge Detection through Cross-Modal Knowledge Learning

    by Ruoxi Deng, Bin Yu, Jinxuan Lu, Caixia Zhou, Zhao-Min Chen, Jie Hu

    Semantic edge detection (SED) is pivotal for the precise demarcation of object boundaries, yet it faces ongoing challenges due to the prevalence of low-quality labels in current methods. In this paper, we present a novel solution to bolster SED through the encoding of both language and image data. Distinct from antecedent language-driven techniques, which predominantly utilize static elements such as dataset labels, our method taps into the dynamic language content that details the objects in each image and their interrelations. By encoding this varied input, we generate integrated features that utilize semantic insights to refine the high-level image features and the ultimate mask representations. This advancement improves the quality of these features and elevates SED performance. Experimental evaluation on benchmark datasets, including SBD and Cityscape, showcases the efficacy of our method, achieving leading ODS F-scores of 79.0 and 76.0, respectively. Our approach signifies a notable advancement in SED technology by seamlessly integrating multimodal textual information, embracing both static and dynamic aspects.

  • Modeling Label Correlations with Latent Context for Multi-label Recognition

    by Zhaomin Chen, Quan Cui, Ruoxi Deng, Jie Hu, Guodao Zhang


  • Open Access

    DIM: long-tailed object detection and instance segmentation via dynamic instance memory

    by Zhao-Min Chen, Xin Jin, Xiaoqin Zhang, Chaoqun Xia, Zhiyong Pan, Ruoxi Deng, Jie Hu, Heng Chen

    Object detection and instance segmentation have been successful on benchmarks with relatively balanced category distribution (e.g. MSCOCO). However, state-of-the-art object detection and segmentation methods still struggle to generalize on long-tailed datasets (e.g. LVIS), where a few classes (head classes) dominate the instance samples, while most classes (tailed classes) have only a few samples. To address this challenge, we propose a plug-and-play module within the Mask R-CNN framework called dynamic instance memory (DIM). Specifically, we augment Mask R-CNN with an auxiliary branch for training. It maintains a dynamic memory bank storing an instance-level prototype representation for each category, and shares the classifier with the existing instance branch. With a simple metric loss, the representations in DIM can be dynamically updated by the instance proposals in the mini-batch during training. Our DIM introduces a bias toward tailed classes to the classifier learning along with a class frequency reversed sampler, which learns generalizable representations from the original data distribution, complementing the existing instance branch. Comprehensive experiments on LVIS demonstrate the effectiveness of DIM, as well as the significant advantages of DIM over the baseline Mask R-CNN.