Author name cluster

Haoran Jiang

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.

4 papers

1 author row

AAAI Conference 2026 Conference Paper

Beyond Predictive Resampling: Learning Input-Agnostic Downsampling for Efficient Aligned Vision Recognition

Kai Zhao
Liting Ruan
Haoran Jiang
Xiaoqiang Zhu
Xianchao Zhang
Dan Zeng

Images are typically sampled on a uniform grid,despite their non-uniform information distribution—some regions are rich in content while others are not. The mismatch leads to inefficient computation allocation in deep learning models. To address this, recent studies have proposed predictive downsampling methodsthat adaptively downsample images based on predicted per-pixel importance, allocating more pixels to informative areas. However,these methods require high-resolution processing to accurately estimate importance, which undermines their efficiency:the prediction itself must process the full-resolution image,consuming most of the computational budget. This high-resolution importance prediction is necessary because each input may differ significantly in structure and content. In this paper, we take a different approach and introduce a learn-to-downsample paradigmtailored for aligned vision recognition tasks, such as face recognition and palmprint recognition, where input alignment ensures consistent spatial structure across images. This alignment ensures structural consistency across images, allowing a shared, input-agnostic downsampling template applicable to all inputs. Furthermore, instead of relying on implicit importance maps, we introduce a flow-based representation that explicitly models the spatial warping from the original image to the downsampled version. The flow representation is not only more efficient but also more controllable: we regularize the flow using its Jacobian determinant to precisely control the sampling density and coverage,enabling interpretable and tunable sampling patterns. Extensive experiments on two aligned recognition tasks, face and palmprint recognition, demonstrate that our method substantially reduces computational cost with minimal accuracy degradation, achieving a significantly better performance-efficiency trade-off than existing predictive downsampling methods.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

ForgerySleuth: Empowering Multimodal Large Language Models for Image Manipulation Detection

Zhihao Sun
Haoran Jiang
Haoran Chen
Yixin Cao
Xipeng Qiu
Zuxuan Wu
Yu-Gang Jiang

Multimodal large language models have unlocked new possibilities for various multimodal tasks. However, their potential in image manipulation detection remains unexplored. When directly applied to the IMD task, M-LLMs often produce reasoning texts that suffer from hallucinations and overthinking. To address this, we propose ForgerySleuth, which leverages M-LLMs to perform comprehensive clue fusion and generate segmentation outputs indicating specific regions that are tampered with. Moreover, we construct the ForgeryAnalysis dataset through the Chain-of-Clues prompt, which includes analysis and reasoning text to upgrade the image manipulation detection task. A data engine is also introduced to build a larger-scale dataset for the pre-training phase. Our extensive experiments demonstrate the effectiveness of ForgeryAnalysis and show that ForgerySleuth significantly outperforms existing methods in generalization, robustness, and explainability.

PDF Details

YNIMG Journal 2025 Journal Article

Subjective value-weights on benefit and risk in human neurocomputation changes between conservative and risky decision-making

Sijia Liu
Shuang Li
Haoran Jiang
Lixing Yin
Yu Xu
Zhiyuan Liu
Xiuyan Guo

The substantial variability in people's risky decision-making constitutes a compelling and interesting topic. It is particularly fascinating to note that even when confronted with identical circumstances, the same individual tends to exhibit variability in their risk decisions, oscillating between a propensity for heightened risk-taking and a more cautious approach. The current study investigated human computational neural mechanisms of risky and conservative decision-making in sequential risk-taking tasks through integrative analysis of dynamic-updating model parameters and EEG signatures of decision processes. The model revealed that, during risky decision-making, subjective benefit values exerted a stronger influence, whereas subjective risk values dominated conservative decisions. Emotional factors, particularly regret-related emotion, primarily modulated conservative decisions rather than risky decisions. By applying time-resolved multivariate pattern analyses to EEG data and identifying the peak decoding accuracy as a marker of stage completion, we dissociated valuation from the selection stage in decision-making. The peak decoding accuracy during the valuation stage demonstrated higher and more stable in risky decision-making compared to conservative decision-making. Further analysis suggested that peak decoding accuracy in risky decision-making may reflect a relatively balanced consideration between risk and benefit values. Notably, emotional factors had less impact on the selection stage of risky decisions, but significantly affected the selection stage of conservative decisions. These findings elucidate the adaptability and dynamic architecture of neurocomputation across risky and conservative decisions.

Details DOI

AAAI Conference 2024 Conference Paper

Navigating Real-World Partial Label Learning: Unveiling Fine-Grained Images with Attributes

Haoran Jiang
Zhihao Sun
YingJie Tian

Partial label learning (PLL), a significant research area, addresses the challenge of annotating each sample with a candidate label set containing the true label when obtaining accurate labels is infeasible. However, existing PLL methods often rely on generic datasets like CIFAR, where annotators can readily differentiate candidate labels and are unlikely to confuse, making it less realistic for real-world partial label applications. In response, our research focuses on a rarely studied problem, PLL on fine-grained images with attributes. And we propose a novel framework called Shared to Learn, Distinct to Disambiguate (SoDisam). Within the candidate label set, the categories may exhibit numerous shared attribute features, posing a challenge in accurately distinguishing them. Rather than perceiving it as an impediment, we capitalize on these shared attributes as definitive sources of supervision. This insight guides us to learn attribute space visual representation to focus on the information from these shared attributes. Moreover, we introduce an attribute attention mechanism tailored to harness the remaining distinct attributes. This mechanism directs the originally holistic feature towards specific regions, capturing corresponding discriminative features. In addition, a dynamic disambiguation module is introduced, continuously adjusting the two aforementioned mechanisms and achieve the final disambiguation process. Extensive experiments demonstrate the effectiveness of our approach on fine-grained partial label datasets. The proposed SoDisam framework not only addresses the challenges associated with fine-grained partial label learning but also provides a more realistic representation of real-world partial label scenarios.

PDF Details DOI