DLDongliang Luo

Dongliang Luo

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Dongliang Luo has a total of 28 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    TokBench: Evaluating Your Visual Tokenizer before Visual Generation

    by Junfeng Wu, Dongliang Luo, Weizhi Zhao, Zhihao Xie, Yuanhao Wang, Junyi Li, Xudong Xie, Yuliang Liu, Xiang Bai

  • Open Access

    TokBench: Evaluating Your Visual Tokenizer before Visual Generation

    by Junfeng Wu, Dongliang Luo, Weizhi Zhao, Zhihao Xie, Yuanhao Wang, Junyi Li, Xudong Xie, Yuliang Liu, Xiang Bai

    In this work, we reveal the limitations of visual tokenizers and VAEs in preserving fine-grained features, and propose a benchmark to evaluate reconstruction performance for two challenging visual contents: text and face. Visual tokenizers and VAEs have significantly advanced visual generation and multimodal modeling by providing more efficient compressed or quantized image representations. However, while helping production models reduce computational burdens, the information loss from image compression fundamentally limits the upper bound of visual generation quality. To evaluate this upper bound, we focus on assessing reconstructed text and facial features since they typically: 1) exist at smaller scales, 2) contain dense and rich textures, 3) are prone to collapse, and 4) are highly sensitive to human vision. We first collect and curate a diverse set of clear text and face images from existing datasets. Unlike approaches using VLM models, we employ established OCR and face recognition models for evaluation, ensuring accuracy while maintaining an exceptionally lightweight assessment process requiring just 2GB memory and 4 minutes to complete. Using our benchmark, we analyze text and face reconstruction quality across various scales for different image tokenizers and VAEs. Our results show modern visual tokenizers still struggle to preserve fine-grained features, especially at smaller scales. We further extend this evaluation framework to video, conducting comprehensive analysis of video tokenizers. Additionally, we demonstrate that traditional metrics fail to accurately reflect reconstruction performance for faces and text, while our proposed metrics serve as an effective complement.

  • Toward real text manipulation detection: New dataset and new solution

    by Dongliang Luo, Yuliang Liu, Rui Yang, Xianjin Liu, Jishen Zeng, Yu Zhou, Xiang Bai


  • Open Access

    A Discrepancy Aware Framework for Robust Anomaly Detection

    by Yuxuan Cai, Dingkang Liang, Dongliang Luo, Xinwei He, Xin Yang, Xiang Bai

    Defect detection is a critical research area in artificial intelligence. Recently, synthetic data-based self-supervised learning has shown great potential on this task. Although many sophisticated synthesizing strategies exist, little research has been done to investigate the robustness of models when faced with different strategies. In this paper, we focus on this issue and find that existing methods are highly sensitive to them. To alleviate this issue, we present a Discrepancy Aware Framework (DAF), which demonstrates robust performance consistently with simple and cheap strategies across different anomaly detection benchmarks. We hypothesize that the high sensitivity to synthetic data of existing self-supervised methods arises from their heavy reliance on the visual appearance of synthetic data during decoding. In contrast, our method leverages an appearance-agnostic cue to guide the decoder in identifying defects, thereby alleviating its reliance on synthetic appearance. To this end, inspired by existing knowledge distillation methods, we employ a teacher-student network, which is trained based on synthesized outliers, to compute the discrepancy map as the cue. Extensive experiments on two challenging datasets prove the robustness of our method. Under the simple synthesis strategies, it outperforms existing methods by a large margin. Furthermore, it also achieves the state-of-the-art localization performance. Code is available at: https://github.com/caiyuxuan1120/DAF.

  • A Discrepancy Aware Framework for Robust Anomaly Detection

    by Yuxuan Cai, Dingkang Liang, Dongliang Luo, Xinwei He, Xin Yang, Xiang Bai

    Defect detection is a critical research area in artificial intelligence. Recently, synthetic data-based self-supervised learning has shown great potential on this task. Although many sophisticated synthesizing strategies exist, little research has been done to investigate the robustness of models when faced with different strategies. In this article, we focus on this issue and find that existing methods are highly sensitive to them. To alleviate this issue, we present a discrepancy aware framework (DAF), which demonstrates robust performance consistently with simple and cheap strategies across different anomaly detection benchmarks. We hypothesize that the high sensitivity to synthetic data of existing self-supervised methods arises from their heavy reliance on the visual appearance of synthetic data during decoding. In contrast, our method leverages an appearance-agnostic cue to guide the decoder in identifying defects, thereby alleviating its reliance on synthetic appearance. To this end, inspired by existing knowledge distillation methods, we employ a teacher-student network, which is trained based on synthesized outliers, to compute the discrepancy map as the cue. Extensive experiments on two challenging datasets prove the robustness of our method. Under the simple synthesis strategies, it outperforms existing methods by a large margin. Furthermore, it also achieves the state-of-the-art localization performance.


  • ICDAR 2023 Competition on Detecting Tampered Text in Images

    by Dongliang Luo, Yu Zhou, Rui Yang, Yuliang Liu, Xianjin Liu, Jishen Zeng, Enming Zhang, Biao Yang, Ziming Huang, Lianwen Jin, et al.


  • Prior Matching Operator in Self-Supervised Learning

    by Dongliang Luo, Jian Wang

    In self-supervised representation learning (SSL), contrastive learning has achieved remarkable successes in recent years. In contrastive learning, the augmented views of the same image are brought closer (i.e., positive pairs), while views from different images (i.e., negative pairs) are separated apart. To perform well, contrastive methods of ten rely on a large number of negative pairs, which is computationally demanding. Intuitively, the negative samples play a role to scatter the representation of samples in space, which guarantees the uniformity of the representation space, thus making it the key to avoiding representation collapse (i.e., constant features). In this work, we propose an interpretable method, in which prior distribution matching is applied to prevent representation collapse, while no negative pair is required. Empirical experiments show promising results of our method yielded by the priors of Gaussian, uniform, and spherical distribution on the CIFAR-10 and CIFAR-100 datasets.