BYBingyao Yu

Bingyao Yu

*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


Bingyao Yu has a total of 23 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Scale-adaptive multi-predator network for camouflaged object detection

    by Bingyao Yu, Wenzhao Zheng, Jiwen Lu

    In this paper, we propose a scale-adaptive multi-predator (SAMP) network for camouflaged object detection (COD), which aims to segment objects that have successfully concealed themselves by blending into the surrounding environment. Despite the challenging nature of distinguishing objects from a highly similar background, most existing works solve COD as a pixel-level binary classification problem and use a single classifier to identify the target object, analogous to deploying one predator to prey the target animal. Inspired by the high effectiveness of group predation (e.g., wolves), we propose to simultaneously employ a group of diverse “predators” to seek out the target object. To this end, we reformulate COD as a point-to-set matching problem and classify each pixel based on its distance with a set of dynamic query embeddings. Furthermore, we employ a confidence-based query selection method to enable each query to adaptively focus on different scales of the image for better identification of the camouflaged object. Extensive experiments on the CHAMELEON, CAMO, and COD10K datasets verify the effectiveness of the proposed method.


  • Toward Generalizable Forgery Detection and Reasoning

    by Yueying Gao, Dongliang Chang, Bingyao Yu, Haotian Qin, Muxi Diao, Lei Chen, Kongming Liang, Zhanyu Ma

    Accurate and interpretable detection of AI-generated images is essential for mitigating risks associated with AI misuse. However, the substantial domain gap among generative models makes it challenging to develop a generalizable forgery detection model. Moreover, since every pixel in an AI-generated image is synthesized, traditional saliency-based forgery explanation methods are not well suited for this task. To address these challenges, we formulate detection and explanation as a unified Forgery Detection and Reasoning task (FDR-Task)1, leveraging Multi-Modal Large Language Models (MLLMs) to provide accurate detection through reliable reasoning over forgery attributes. To facilitate this task, we introduce the Multi-Modal Forgery Reasoning dataset (MMFR-Dataset), a large-scale dataset containing 120K images across 10 generative models, with 378K reasoning annotations on forgery attributes, enabling comprehensive evaluation of the FDR-Task. Furthermore, we propose FakeReasoning, a forgery detection and reasoning framework with three key components: 1) a dual-branch visual encoder that integrates CLIP and DINO to capture both high-level semantics and low-level artifacts; 2) a Forgery-Aware Feature Fusion Module that leverages DINO’s attention attention maps and cross-attention mechanisms to guide MLLMs toward forgery-related clues; 3) a Classification Probability Mapper that couples language modeling and forgery detection, enhancing overall performance. Experiments across multiple generative models demonstrate that FakeReasoning not only achieves robust generalization but also outperforms state-of-the-art methods on both detection and reasoning tasks.


  • AdaParse: Personalized Fingerprinting for Visual Generative Model Reverse Engineering

    by Yu Zheng, Zhuoxun Li, Bingyao Yu, Jie Zhou, Jiwen Lu

    In this paper, we propose a hyperparameter-specialized adaptive fingerprinting framework named AdaParse for model reverse engineering, which aims at predicting hyperparameters of interest in generative models from the given AI-generated images. Existing methods rely on a single coarse model fingerprint that is originally designed for model-level attribution, which makes it difficult to distinguish fine-grained traces corresponding to different hyperparameter configurations in a multitude of generative models. To address this, our AdaParse dynamically responds to instance-level variations by estimating hyperparameter-specific fingerprints via personalizing estimation networks tailored for each input image. Specifically, our approach simultaneously learns two-branch hypernetworks that balance instance-aware and model-agnostic prior knowledge for fingerprint generation. To enable efficient network personalization, we further propose a Broadcasted Fusion module that transforms condensed feature codes into adaptive parameters through factorized weight generation with enhanced representative capacity. Extensive experiments on the large-scale public dataset across 123 generative models demonstrate that our approach outperforms previous state-of-the-art methods. Code available at https://github.com/lizhuoxun/AdaParse/.

  • Open Access

    WhiADD: Semantic-Acoustic Fusion for Robust Audio Deepfake Detection

    by Jianqiao Cui, Bingyao Yu, Qihao Wang, Fei Meng, Jiwen Lu


  • Discrepancy-Aware Meta-Learning for Zero-Shot Face Manipulation Detection

    by Bingyao Yu, Xiu Li, Wanhua Li, Jie Zhou, Jiwen Lu

    In this paper, we propose a discrepancy-aware meta-learning approach for zero-shot face manipulation detection, which aims to learn a discriminative model maximizing the generalization to unseen face manipulation attacks with the guidance of the discrepancy map. Unlike existing face manipulation detection methods that usually present algorithmic solutions to the known face manipulation attacks, where the same types of attacks are used to train and test the models, we define the detection of face manipulation as a zero-shot problem. We formulate the learning of the model as a meta-learning process and generate zero-shot face manipulation tasks for the model to learn the meta-knowledge shared by diversified attacks. We utilize the discrepancy map to keep the model focused on generalized optimization directions during the meta-learning process. We further incorporate a center loss to better guide the model to explore more effective meta-knowledge. Experimental results on the widely used face manipulation datasets demonstrate that our proposed approach achieves very competitive performance under the zero-shot setting.


  • Salience-Aware Face Presentation Attack Detection via Deep Reinforcement Learning

    by Bingyao Yu, Jiwen Lu, Xiu Li, Jie Zhou

    In this paper, we propose a salience-aware face presentation attack detection (SAFPAD) approach, which takes advantage of deep reinforcement learning to exploit the salient local part information in face images. Most existing deep face presentation attack detection approaches extract features from the entire image or several fixed regions. However, the discriminative information beneficial for presentation attack detection is unevenly distributed in the image due to the illumination and presentation attack instrument variation, so treating all regions equally fails to highlight the most discriminative information which is important for more accurate and robust face presentation attack detection. To address this, we propose to identify the discriminative salient parts using deep reinforcement learning and focus on them to alleviate the adverse effects of redundant information in the face images. We fuse the high-level features and the local features which guide the policy network to exploit discriminative patches and assist the classification network to predict more accurate results. We jointly train the SAFPAD model with deep reinforcement learning to generate salient locations. Extensive experiments on five public datasets demonstrate that our approach achieves very competitive performance due to the concentrated employment of salient local information.