Author name cluster

Xin Deng

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

Burst Image Quality Assessment: A New Benchmark and Unified Framework for Multiple Downstream Tasks

Xiaoye Liang
Lai Jiang
Minglang Qiao
Yichen Guo
Yue Zhang
Xin Deng
Shengxi Li
Yufan Liu

In recent years, the development of burst imaging technology has improved the capture and processing capabilities of visual data, enabling a wide range of applications. However, the redundancy in burst images leads to the increased storage and transmission demands, as well as reduced efficiency of downstream tasks. To address this, we propose a new task of Burst Image Quality Assessment (BuIQA), to evaluate the task-driven quality of each frame within a burst sequence, providing reasonable cues for burst image selection. Specifically, we establish the first benchmark dataset for BuIQA, consisting of 7,346 burst sequences with 45,827 images and 191,572 annotated quality scores for multiple downstream scenarios. Inspired by the data analysis, a unified BuIQA framework is proposed to achieve an efficient adaption for BuIQA under diverse downstream scenarios. Specifically, a task-driven prompt generation network is developed with heterogeneous knowledge distillation, to learn the priors of the downstream task. Then, the task-aware quality assessment network is introduced to assess the burst image quality based on the task prompt. Extensive experiments across 10 downstream scenarios demonstrate the impressive BuIQA performance of the proposed approach, outperforming the state-of-the-art. Furthermore, it can achieve 0.33 dB PSNR improvement in the downstream tasks of denoising and super-resolution, by applying our approach to select the high-quality burst frames.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Training-Free ANN-to-SNN Conversion for High-Performance Spiking Transformers

Jingya Wang
Xin Deng
Wenjie Wei
Dehao Zhang
Shuai Wang
Qian Sun
Jieyuan Zhang
Hanwen Liu

Leveraging the event-driven paradigm, Spiking Neural Networks (SNNs) offer a promising approach for constructing energy-efficient Transformer architectures. Compared to directly trained Spiking Transformers, ANN-to-SNN conversion methods bypass the high training costs. However, existing methods still suffer from notable limitations, failing to effectively handle nonlinear operations in Transformer architectures and requiring additional fine-tuning processes for pre-trained ANNs. To address these issues, we propose a high-performance and training-free ANN-to-SNN conversion framework tailored for Transformer architectures. Specifically, we introduce a Multi-basis Exponential Decay (MBE) neuron, which employs an exponential decay strategy and multi-basis encoding method to efficiently approximate various nonlinear operations. It removes the requirement for weight modifications in pre-trained ANNs. Extensive experiments across diverse tasks (CV, NLU, NLG) and mainstream Transformer architectures (ViT, RoBERTa, GPT-2) demonstrate that our method achieves near-lossless conversion accuracy with significantly lower latency. This provides a promising pathway for the efficient and scalable deployment of Spiking Transformers in real-world applications.

PDF Details DOI

EAAI Journal 2025 Journal Article

Damage and energy dissipation prediction and multi-objective optimization design of latticed concrete-filled steel tube column-composite box girder joints based on extreme gradient boosting

Zhi Huang
Xin Deng
Juan Chen
Xiang Li
Lizhong Jiang
Yohchia Frank Chen
Yuner Huang
Lin Chen

To optimize joint performance, a finite element (FE) model is developed based on low-cycle reciprocating load tests of latticed concrete-filled steel tubular (CFST) column-composite box girder joints. The FE-predicted hysteresis curves are compared with test results to verify model accuracy, and a data set is established accordingly. Extreme Gradient Boosting (XGBoost) algorithm is used for training and prediction, and compared with the traditional machine learning (ML) algorithm, the superiority of the XGBoost algorithm is manifested. The XGBoost algorithm is then used to predict the damage and energy values of the joint under more different parameter combinations, with the largest ratio of damage value to energy dissipation value selected as the optimal combination of the joints within the variation range of the six parameters. The results show that the FE model correlates well with the test results and can therefore be used to generate a data set. The prediction accuracy of XGBoost algorithm has high accuracy of more than 99 % in predicting damage and energy dissipation values and can thus be used for joint prediction research. Compared with other ML algorithms, XGBoost has the best prediction performance and superiority. Within the variation range of the six parameters, the ratio of damage value to energy dissipation value is the largest when the concrete strength, longitudinal bar diameter, concrete slab thickness, box girder strength, axial compression ratio, and transverse stiffener strength are respectively 30 Mega Pascal (MPa), 12 mm (mm), 90 mm, 390 MPa, 0. 3, and 455 MPa.

Details DOI

NeurIPS Conference 2024 Conference Paper

Causal Context Adjustment Loss for Learned Image Compression

Minghao Han
Shiyin Jiang
Shengxi Li
Xin Deng
Mai Xu
Ce Zhu
Shuhang Gu

In recent years, learned image compression (LIC) technologies have surpassed conventional methods notably in terms of rate-distortion (RD) performance. Most present learned techniques are VAE-based with an autoregressive entropy model, which obviously promotes the RD performance by utilizing the decoded causal context. However, extant methods are highly dependent on the fixed hand-crafted causal context. The question of how to guide the auto-encoder to generate a more effective causal context benefit for the autoregressive entropy models is worth exploring. In this paper, we make the first attempt in investigating the way to explicitly adjust the causal context with our proposed Causal Context Adjustment loss (CCA-loss). By imposing the CCA-loss, we enable the neural network to spontaneously adjust important information into the early stage of the autoregressive entropy model. Furthermore, as transformer technology develops remarkably, variants of which have been adopted by many state-of-the-art (SOTA) LIC techniques. The existing computing devices have not adapted the calculation of the attention mechanism well, which leads to a burden on computation quantity and inference latency. To overcome it, we establish a convolutional neural network (CNN) image compression model and adopt the unevenly channel-wise grouped strategy for high efficiency. Ultimately, the proposed CNN-based LIC network trained with our Causal Context Adjustment loss attains a great trade-off between inference latency and rate-distortion performance.

PDF Details DOI