Author name cluster

Jianlong Zhou

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

AAAI Conference 2026 Conference Paper

RcAE: Recursive Reconstruction Framework for Unsupervised Industrial Anomaly Detection

Rongcheng Wu
Hao Zhu
Shiying Zhang
Mingzhe Wang
Zhidong Li
Hui Li
Jianlong Zhou
Jiangtao Cui

Unsupervised industrial anomaly detection requires accurately identifying defects without labeled data. Traditional autoencoder-based methods often struggle with incomplete anomaly suppression and loss of fine details, as their single-pass decoding fails to effectively handle anomalies with varying severity and scale. We propose a recursive architecture for autoencoder (RcAE), which performs reconstruction iteratively to progressively suppress anomalies while refining normal structures. Unlike traditional single-pass models, this recursive design naturally produces a sequence of reconstructions, progressively exposing suppressed abnormal patterns. To leverage this reconstruction dynamics, we introduce a Cross Recursion Detection (CRD) module that tracks inconsistencies across recursion steps, enhancing detection of both subtle and large-scale anomalies. Additionally, we incorporate a Detail Preservation Network (DPN) to recover high-frequency textures typically lost during reconstruction. Extensive experiments demonstrate that our method significantly outperforms existing non-diffusion methods, and achieves performance on par with recent diffusion models with only 10% of their parameters and offering substantially faster inference. These results highlight the practicality and efficiency of our approach for real-world applications.

PDF Details DOI

ICLR Conference 2025 Conference Paper

Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations Interpretability

Zhiyu Zhu
Zhibo Jin
Jiayu Zhang 0001
Nan Yang
Jiahao Huang
Jianlong Zhou
Fang Chen 0001

The task of identifying multimodal image-text representations has garnered increasing attention, particularly with models such as CLIP (Contrastive Language-Image Pretraining), which demonstrate exceptional performance in learning complex associations between images and text. Despite these advancements, ensuring the interpretability of such models is paramount for their safe deployment in real-world applications, such as healthcare. While numerous interpretability methods have been developed for unimodal tasks, these approaches often fail to transfer effectively to multimodal contexts due to inherent differences in the representation structures. Bottleneck methods, well-established in information theory, have been applied to enhance CLIP's interpretability. However, they are often hindered by strong assumptions or intrinsic randomness. To overcome these challenges, we propose the Narrowing Information Bottleneck Theory, a novel framework that fundamentally redefines the traditional bottleneck approach. This theory is specifically designed to satisfy contemporary attribution axioms, providing a more robust and reliable solution for improving the interpretability of multimodal models. In our experiments, compared to state-of-the-art methods, our approach enhances image interpretability by an average of 9\%, text interpretability by an average of 58.83\%, and accelerates processing speed by 63.95\%. Our code is publicly accessible at https://github.com/LMBTough/NIB.

Details

ICML Conference 2025 Conference Paper

Splitting & Integrating: Out-of-Distribution Detection via Adversarial Gradient Attribution

Jiayu Zhang 0001
Xinyi Wang 0005
Zhibo Jin
Zhiyu Zhu
Jianlong Zhou
Fang Chen 0001
Huaming Chen

Out-of-distribution (OOD) detection is essential for enhancing the robustness and security of deep learning models in unknown and dynamic data environments. Gradient-based OOD detection methods, such as GAIA, analyse the explanation pattern representations of in-distribution (ID) and OOD samples by examining the sensitivity of model outputs w. r. t. model inputs, resulting in superior performance compared to traditional OOD detection methods. However, we argue that the non-zero gradient behaviors of OOD samples do not exhibit significant distinguishability, especially when ID samples are perturbed by random perturbations in high-dimensional spaces, which negatively impacts the accuracy of OOD detection. In this paper, we propose a novel OOD detection method called S & I based on layer S plitting and gradient I ntegration via Adversarial Gradient Attribution. Specifically, our approach involves splitting the model’s intermediate layers and iteratively updating adversarial examples layer-by-layer. We then integrate the attribution gradients from each intermediate layer along the attribution path from adversarial examples to the actual input, yielding true explanation pattern representations for both ID and OOD samples. Experiments demonstrate that our S & I algorithm achieves state-of-the-art results, with the average FPR95 of 29. 05% (ResNet34)/38. 61% (WRN40) and 37. 31% (BiT-S) on the CIFAR100 and ImageNet benchmarks, respectively. Our code is available at: https: //github. com/LMBTough/S-Ihttps: //github. com/LMBTough/S-I

Details

IS Journal 2024 Journal Article

Explaining Imitation Learning Through Frames

Boyuan Zheng
Jianlong Zhou
Chunjie Liu
Yiqiao Li
Fang Chen

As one of the prevalent methods to achieve automation systems, imitation learning (IL) presents a promising performance in a wide range of domains. However, despite the considerable improvement in policy performance, the corresponding research on the explainability of IL models is still limited. Inspired by the recent approaches in explainable AI, we proposed a model-agnostic explaining framework for IL models called Remove and Retrain via Randomized Input Sampling for Explanation (R2RISE). R2RISE aims to explain the importance of frames with respect to the overall policy performance. It iteratively retrains the black-box IL model from the randomized masked demonstrations and uses the conventional evaluation outcome environment returns as the coefficient to build an importance map. We also conducted experiments to investigate three major questions concerning frames’ importance equality, the effectiveness of the importance map, and connections in importance maps from different IL models. The result shows that R2RISE distinguishes important frames from the demonstrations effectively.

Details DOI

IS Journal 2023 Journal Article

Artificial Intelligence Ethics and Trust: From Principles to Practice

Fang Chen
Jianlong Zhou
Andreas Holzinger
Kenneth R. Fleischmann
Simone Stumpf

Despite the proliferation of ethical frameworks of artificial intelligence (AI) from different organizations such as government agencies, large corporations, and academic institutions, it is still a challenge to implement and operationalize ethical and legal frameworks for AI in practice due to its complexities. The implementation and operationalization involve different aspects in original theoretical and practical research on designing, developing, presenting, testing, and evaluating approaches, which are supported by advanced AI techniques and interdisciplinary research, in particular, social science, law, and cognitive science. This editorial provides an overview of the field of operationalization of AI ethics and trust, and highlights a few key topics covered in this special issue, i. e. , the current landscape of AI ethics implementation, trust and trustworthiness in AI, ethical framework for trust calibration, approaches to build morality in AI, implementation of AI ethics with a pattern-oriented engineering approach, and inclusive user studies.

Details DOI