XPXi Peng

Xi Peng

*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


Xi Peng has a total of 81 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Medical AI Encodes a “Feeling of Error”: Verifying Cancer Segmentation via Internal Concepts

    by Mengmeng Ma, Yunxiang Peng, Tang Li, Lu Lin, Binsheng Zhao, Oguz Akin, Xi Peng

  • Open Access

    Beyond Accuracy: On the Effects of Fine-Tuning Towards Vision-Language Model’s Prediction Rationality

    by Qitong Wang, Tang Li, Kien X. Nguyen, Xi Peng

    Vision-Language Models (VLMs), such as CLIP, have already seen widespread applications. Researchers actively engage in further fine-tuning VLMs in safety-critical domains. In these domains, prediction rationality is crucial: the prediction should be correct and based on valid evidence. Yet, for VLMs, the impact of fine-tuning on prediction rationality is seldomly investigated. To study this problem, we proposed two new metrics called Prediction Trustworthiness and Inference Reliability. We conducted extensive experiments on various settings and observed some interesting phenomena. On the one hand, we found that the well-adopted fine-tuning methods led to more correct predictions based on invalid evidence. This potentially undermines the trustworthiness of correct predictions from fine-tuned VLMs. On the other hand, having identified valid evidence of target objects, fine-tuned VLMs were more likely to make correct predictions. Moreover, the findings are also consistent under distributional shifts and across various experimental settings. We hope our research offer fresh insights to VLM fine-tuning.


  • Open Access

    Interpretable Failure Detection with Human-Level Concepts

    by Kien X. Nguyen, Tang Li, Xi Peng

    Reliable failure detection holds paramount importance in safety-critical applications. Yet, neural networks are known to produce overconfident predictions for misclassified samples. As a result, it remains a problematic matter as existing confidence score functions rely on category-level signals, the logits, to detect failures. This research introduces an innovative strategy, leveraging human-level concepts for a dual purpose: to reliably detect when a model fails and to transparently interpret why. By integrating a nuanced array of signals for each category, our method enables a finer-grained assessment of the model's confidence. We present a simple yet highly effective approach based on the ordinal ranking of concept activation to the input image. Without bells and whistles, our method is able to significantly reduce the false positive rate across diverse real-world image classification benchmarks, specifically by 3.7% on ImageNet and 9.0% on EuroSAT.


  • Open Access

    Improving Representation Learning of Complex Critical Care Data with ICU-BERT

    by Ricardo Santos, André V. Carreiro, Xi Peng, Hugo Gamboa, Holger Fröhlich

    The multivariate, asynchronous nature of real-world clinical data, such as that generated in Intensive Care Units (ICUs), challenges traditional AI-based decision-support systems. These often assume data regularity and feature independence and frequently rely on limited data scopes and manual feature engineering. The potential of generative AI technologies has not yet been fully exploited to analyze clinical data. We introduce ICU-BERT, a transformer-based model pre-trained on the MIMIC-IV database using a multi-task scheme to learn robust representations of complex ICU data with minimal preprocessing. ICU-BERT employs a multi-token input strategy, incorporating dense embeddings from a biomedical Large Language Model to learn a generalizable representation of complex and multivariate ICU data. With an initial evaluation of five tasks and four additional ICU datasets, ICU-BERT results indicate that ICU-BERT either compares to or surpasses current performance benchmarks by leveraging fine-tuning. By integrating structured and unstructured data, ICU-BERT advances the use of foundational models in medical informatics, offering an adaptable solution for clinical decision support across diverse applications.

  • Open Access

    Adaptive Cascading Network for Continual Test-Time Adaptation

    by Kien X. Nguyen, Fengchun Qiao, Xi Peng

    We study the problem of continual test-time adaption where the goal is to adapt a source pre-trained model to a sequence of unlabelled target domains at test time. Existing methods on test-time training suffer from several limitations: (1) Mismatch between the feature extractor and classifier; (2) Interference between the main and self-supervised tasks; (3) Lack of the ability to quickly adapt to the current distribution. In light of these challenges, we propose a cascading paradigm that simultaneously updates the feature extractor and classifier at test time, mitigating the mismatch between them and enabling long-term model adaptation. The pre-training of our model is structured within a meta-learning framework, thereby minimizing the interference between the main and self-supervised tasks and encouraging fast adaptation in the presence of limited unlabelled data. Additionally, we introduce innovative evaluation metrics, average accuracy and forward transfer, to effectively measure the model's adaptation capabilities in dynamic, real-world scenarios. Extensive experiments and ablation studies demonstrate the superiority of our approach in a range of tasks including image classification, text classification, and speech recognition. Our code is publicly available at https://github.com/Nyquixt/CascadeTTA.


  • Open Access

    DEAL: Disentangle and Localize Concept-level Explanations for VLMs

    by Tang Li, Mengmeng Ma, Xi Peng

    Large pre-trained Vision-Language Models (VLMs) have become ubiquitous foundational components of other models and downstream tasks. Although powerful, our empirical results reveal that such models might not be able to identify fine-grained concepts. Specifically, the explanations of VLMs with respect to fine-grained concepts are entangled and mislocalized. To address this issue, we propose to DisEntAngle and Localize (DEAL) the concept-level explanations for VLMs without human annotations. The key idea is encouraging the concept-level explanations to be distinct while maintaining consistency with category-level explanations. We conduct extensive experiments and ablation studies on a wide range of benchmark datasets and vision-language models. Our empirical results demonstrate that the proposed method significantly improves the concept-level explanations of the model in terms of disentanglability and localizability. Surprisingly, the improved explainability alleviates the model's reliance on spurious correlations, which further benefits the prediction accuracy.

  • Adapting Wireless Network Configuration From Simulation to Reality via Deep Learning-Based Domain Adaptation

    by Junyang Shi, Aitian Ma, Xia Cheng, Mo Sha, Peng Xi

    Today, wireless mesh networks (WMNs) are deployed globally to support various applications, such as industrial automation, military operations, and smart energy. Significant efforts have been made in the literature to facilitate their deployments and optimize their performance. However, configuring a WMN well is challenging because the network configuration is a complex process, which involves theoretical computation, simulation, and field testing, among other tasks. Our study shows that the models for network configuration prediction learned from simulations may not work well in physical networks because of the simulation-to-reality gap. In this paper, we employ deep learning-based domain adaptation to close the gap and leverage a teacher-student neural network and a physical sampling method to transfer the network configuration knowledge learned from a simulated network to its corresponding physical network. Experimental results show that our method effectively closes the gap and increases the accuracy of predicting a good network configuration that allows the network to meet performance requirements from 30.10% to 70.24% by learning robust machine learning models from a large amount of inexpensive simulation data and a few costly field testing measurements.