Author name cluster

Cheng Peng

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.

14 papers

2 author rows

AAAI Conference 2026 Conference Paper

Dual Graph Disambiguation for Multi-Instance Partial-Label Learning

Zhen Zhu
Kai Tang
Songhe Feng
Yixuan Tang
Haobo Wang
Gengyu Lyu
Cheng Peng
Yining Sun

In multi-instance partial label learning (MIPL), each sample is a bag of multiple instances linked to a candidate label set containing one true and multiple false labels, yielding inexact supervision in both instance features and label space. However, existing works adopt decoupled approaches that focus exclusively on either instance-level feature fusion or label-level disambiguation, failing to fully exploit the intrinsic dependencies between these two spaces. To overcome this limitation, graph-based methods are widely recognized as a powerful paradigm in weakly supervised learning, yet their success hinges on reliable features—precisely what MIPL lacks due to instance-level noise. To bridge this gap, we propose DualG, a novel framework that simultaneously addresses feature learning and label disambiguation through dual-level graph propagation. Specifically, we construct dual relevance graphs at both the bag and instance levels. At the bag level, we build a similarity graph based on fused feature representations; at the instance level, we employ attention scores to filter out irrelevant instances and construct a reliable instance-level relevance graph. These complementary graphs enable our joint label disambiguation framework to simultaneously address inexact supervision signals in both instance space and label space. Experimental results on five benchmark datasets demonstrate that DualG outperforms existing MIPL and partial label learning methods, validating its effectiveness and superiority.

PDF Details DOI

EAAI Journal 2026 Journal Article

Structure-based curriculum learning ultrasound gallbladder image classification network

Xintao Mu
Shengbiao Yang
Jing Zhuo
Yang Li
Jia Wang
Cheng Peng
Xin Wang

Gallbladder cancer (GBC) is one of the most prevalent malignant tumors in the digestive system worldwide. Typically diagnosed at advanced stages, early detection is crucial for improving patient survival rates. Ultrasound imaging has emerged as an effective screening modality due to its noninvasive nature, real time capability, and cost-effectiveness. However, the considerable variations in lesion size, complex textural patterns, and substantial noise interference in GBC ultrasound images pose significant challenges for deep learning model training and inference. To address these challenges, this study proposes a novel two-stage deep learning framework for GBC classification. The first stage involves a comprehensive evaluation of mainstream object detection models, incorporating a newly developed gallbladder coverage ratio metric along with conventional evaluation criteria to select the optimal region-of-interest (ROI) detection network for precise gallbladder localization, thereby minimizing background noise and artifact interference. The second stage introduces an innovative curriculum learning strategy combining Relative Total Variation (RTV) and Visual Acuity (VA), which enhances classification performance in noisy environments by suppressing textural details while emphasizing structural information. Experimental results demonstrate that compared to state-of-the-art (SOTA) classification networks, our proposed method achieves minimum improvements in accuracy, specificity, and sensitivity of 1. 3%, 10. 7%, and 6. 0%, respectively.

Details DOI

EAAI Journal 2025 Journal Article

A novel facial expression recognition method based on cross direction attention network

Cheng Peng
Guodong Li
Likang Lin
Bowen Zhang
Kun Zou
Sio Long Lo
Ah Chung Tsoi

Facial expression recognition (FER) is an area of growing interest in computer vision research. This paper extends the framework provided by the ‘Distract your Attention Network’ (DAN) which consists of multiple parallel branches, each branch composes of a spatial attention (SA) module followed by a channel attention (CA) module, and then these multiple branches are fused together before being passed into a classifier module. The spatial attention module of DAN has an internal channel dimension of 1, while our proposed Cross Directional Attention Network (CDAN)-I and CDAN-II contain respectively an internal channel dimension of 512 (same as the channel dimension of the input), and internal channel dimension of 1024 (double that of the channel dimension of the input). These increases in internal channel dimension allow extraction of more features, before they are being made to conform with the input channel dimension. Despite these seemingly simple modifications from that of DAN, both CDAN-I and CDAN-II are found to outperform those of DAN, a state-of-the-art FER method, on four popular FER benchmark datasets: RAF-DB (Real world Affective Face-database), AffectNet-7 (AffectNet with Seven Categories) AffectNet-8 ( AffectNet with Eight Categories), and CK+ (Cohn–Kanada Extended). Moreover, we make use of three statistical indexes for clustering analysis, and verified that the CDAN-I and CDAN-II modules have been able to increase the inter-cluster distances, and decrease the intra-cluster distances, when compared with those obtained by the backbone ResNet-18 network (Residual Network with 18 Layers), thus providing a quantitative analysis technique in this area.

Details DOI

AAMAS Conference 2025 Conference Paper

Group-fair Facility Location Games with Externalities

Minming Li
Cheng Peng
Ying Wang
Houyu Zhou

We study facility location games with externalities where agents are located on a real line and divided into groups. The cost of an agent is affected by the facility location and their group members. The goal is to design mechanisms to locate a facility to approximately optimize group-fair objectives while eliciting the agents’ locations truthfully. We consider two types of group interactions: competitive and collaborative, and two group-fair objectives, minimizing the maximum total group cost and minimizing the maximum average group cost. For each scenario, we analyze classic mechanisms, presenting their approximation ratios, and introduce new mechanisms that achieve improved approximation ratios. Additionally, we establish tight lower bounds for each setting, demonstrating that our mechanisms are the best possible.

PDF

NeurIPS Conference 2025 Conference Paper

MS-GS: Multi-Appearance Sparse-View 3D Gaussian Splatting in the Wild

Deming Li
Kaiwen Jiang
Yutao Tang
Ravi Ramamoorthi
Rama Chellappa
Cheng Peng

In-the-wild photo collections often contain limited volumes of imagery and exhibit multiple appearances, e. g. , taken at different times of day or seasons, posing significant challenges to scene reconstruction and novel view synthesis. Although recent adaptations of Neural Radiance Field (NeRF) and 3D Gaussian Splatting (3DGS) have improved in these areas, they tend to oversmooth and are prone to overfitting. In this paper, we present MS-GS, a novel framework designed with \textbf{M}ulti-appearance capabilities in \textbf{S}parse-view scenarios using 3D\textbf{GS}. To address the lack of support due to sparse initializations, our approach is built on the geometric priors elicited from monocular depth estimations. The key lies in extracting and utilizing local semantic regions with a Structure-from-Motion (SfM) points anchored algorithm for reliable alignment and geometry cues. Then, to introduce multi-view constraints, we propose a series of geometry-guided supervision steps at virtual views in pixel and feature levels to encourage 3D consistency and reduce overfitting. We also introduce a dataset and an in-the-wild experiment setting to set up more realistic benchmarks. We demonstrate that MS-GS achieves photorealistic renderings under various challenging sparse-view and multi-appearance conditions, and outperforms existing approaches significantly across different datasets.

PDF Details

AAAI Conference 2024 Conference Paper

CARAT: Contrastive Feature Reconstruction and Aggregation for Multi-Modal Multi-Label Emotion Recognition

Cheng Peng
Ke Chen
Lidan Shou
Gang Chen

Multi-modal multi-label emotion recognition (MMER) aims to identify relevant emotions from multiple modalities. The challenge of MMER is how to effectively capture discriminative features for multiple labels from heterogeneous data. Recent studies are mainly devoted to exploring various fusion strategies to integrate multi-modal information into a unified representation for all labels. However, such a learning scheme not only overlooks the specificity of each modality but also fails to capture individual discriminative features for different labels. Moreover, dependencies of labels and modalities cannot be effectively modeled. To address these issues, this paper presents ContrAstive feature Reconstruction and AggregaTion (CARAT) for the MMER task. Specifically, we devise a reconstruction-based fusion mechanism to better model fine-grained modality-to-label dependencies by contrastively learning modal-separated and label-specific features. To further exploit the modality complementarity, we introduce a shuffle-based aggregation strategy to enrich co-occurrence collaboration among labels. Experiments on two benchmark datasets CMU-MOSEI and M3ED demonstrate the effectiveness of CARAT over state-of-the-art methods. Code is available at https://github.com/chengzju/CARAT.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

LP-3DGS: Learning to Prune 3D Gaussian Splatting

Zhaoliang Zhang
Tianchen Song
Yongjae Lee
Li Yang
Cheng Peng
Rama Chellappa
Deliang Fan

Recently, 3D Gaussian Splatting (3DGS) has become one of the mainstream methodologies for novel view synthesis (NVS) due to its high quality and fast rendering speed. However, as a point-based scene representation, 3DGS potentially generates a large number of Gaussians to fit the scene, leading to high memory usage. Improvements that have been proposed require either an empirical pre-set pruning ratio or importance score threshold to prune the point cloud. Such hyperparameters require multiple rounds of training to optimize and achieve the maximum pruning ratio while maintaining the rendering quality for each scene. In this work, we propose learning-to-prune 3DGS (LP-3DGS), where a trainable binary mask is applied to the importance score to automatically find a favorable pruning ratio. Instead of using the traditional straight-through estimator (STE) method to approximate the binary mask gradient, we redesign the masking function to leverage the Gumbel-Sigmoid method, making it differentiable and compatible with the existing training process of 3DGS. Extensive experiments have shown that LP-3DGS consistently achieves a good balance between efficiency and high quality.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Variational Hybrid-Attention Framework for Multi-Label Few-Shot Aspect Category Detection

Cheng Peng
Ke Chen
Lidan Shou
Gang Chen

Multi-label few-shot aspect category detection (FS-ACD) is a challenging sentiment analysis task, which aims to learn a multi-label learning paradigm with limited training data. The difficulty of this task is how to use limited data to generalize effective discriminative representations for different categories. Nowadays, all advanced FS-ACD works utilize the prototypical network to learn label prototypes to represent different aspects. However, such point-based estimation methods are inherently noise-susceptible and bias-vulnerable. To this end, this paper proposes a novel Variational Hybrid-Attention Framework (VHAF) for the FS-ACD task. Specifically, to alleviate the data noise, we adopt a hybrid-attention mechanism to generate more discriminative aspect-specific embeddings. Then, based on these embeddings, we introduce the variational distribution inference to obtain the aspect-specific distribution as a more robust aspect representation, which can eliminate the scarce data bias for better inference. Moreover, we further leverage an adaptive threshold estimation to help VHAF better identify multiple relevant aspects. Extensive experiments on three datasets demonstrate the effectiveness of our VHAF over other state-of-the-art methods. Code is available at https://github.com/chengzju/VHAF.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

NIS3D: A Completely Annotated Benchmark for Dense 3D Nuclei Image Segmentation

Wei Zheng
Cheng Peng
Zeyuan Hou
Boyu Lyu
Mengfan Wang
Xuelong Mi
Shuoxuan Qiao
Yinan Wan

3D segmentation of nuclei images is a fundamental task for many biological studies. Despite the rapid advances of large-volume 3D imaging acquisition methods and the emergence of sophisticated algorithms to segment the nuclei in recent years, a benchmark with all cells completely annotated is still missing, making it hard to accurately assess and further improve the performance of the algorithms. The existing nuclei segmentation benchmarks either worked on 2D only or annotated a small number of 3D cells, perhaps due to the high cost of 3D annotation for large-scale data. To fulfill the critical need, we constructed NIS3D, a 3D, high cell density, large-volume, and completely annotated Nuclei Image Segmentation benchmark, assisted by our newly designed semi-automatic annotation software. NIS3D provides more than 22, 000 cells across multiple most-used species in this area. Each cell is labeled by three independent annotators, so we can measure the variability of each annotation. A confidence score is computed for each cell, allowing more nuanced testing and performance comparison. A comprehensive review on the methods of segmenting 3D dense nuclei was conducted. The benchmark was used to evaluate the performance of several selected state-of-the-art segmentation algorithms. The best of current methods is still far away from human-level accuracy, corroborating the necessity of generating such a benchmark. The testing results also demonstrated the strength and weakness of each method and pointed out the directions of further methodological development. The dataset can be downloaded here: https: //github. com/yu-lab-vt/NIS3D.

PDF Details

AAAI Conference 2023 Conference Paper

PDRF: Progressively Deblurring Radiance Field for Fast Scene Reconstruction from Blurry Images

Cheng Peng
Rama Chellappa

We present Progressively Deblurring Radiance Field (PDRF), a novel approach to efficiently reconstruct high quality radiance fields from blurry images. While current State-of-The-Art (SoTA) scene reconstruction methods achieve photo-realistic renderings from clean source views, their performances suffer when the source views are affected by blur, which is commonly observed in the wild. Previous deblurring methods either do not account for 3D geometry, or are computationally intense. To addresses these issues, PDRF uses a progressively deblurring scheme for radiance field modeling, which can accurately model blur with 3D scene context. PDRF further uses an efficient importance sampling scheme that results in fast scene optimization. We perform extensive experiments and show that PDRF is 15X faster than previous SoTA while achieving better performance on both synthetic and real scenes.

PDF Details DOI

AAAI Conference 2021 Conference Paper

XraySyn: Realistic View Synthesis From a Single Radiograph Through CT Priors

Cheng Peng
Haofu Liao
Gina Wong
Jiebo Luo
S. Kevin Zhou
Rama Chellappa

A radiograph visualizes the internal anatomy of a patient through the use of X-ray, which projects 3D information onto a 2D plane. Hence, radiograph analysis naturally requires physicians to relate their prior knowledge about 3D human anatomy to 2D radiographs. Synthesizing novel radiographic views in a small range can assist physicians in interpreting anatomy more reliably; however, radiograph view synthesis is heavily ill-posed, lacking in paired data, and lacking in differentiable operations to leverage learning-based approaches. To address these problems, we use Computed Tomography (CT) for radiograph simulation and design a differentiable projection algorithm, which enables us to achieve geometrically consistent transformations between the radiography and CT domains. Our method, XraySyn, can synthesize novel views on real radiographs through a combination of realistic simulation and finetuning on real radiographs. To the best of our knowledge, this is the first work on radiograph view synthesis. We show that by gaining an understanding of radiography in 3D space, our method can be applied to radiograph bone extraction and suppression without requiring groundtruth bone labels.

PDF Details

AAAI Conference 2020 Conference Paper

Idle Time Optimization for Target Assignment and Path Finding in Sortation Centers

Ngai Meng Kou
Cheng Peng
Hang Ma
T. K. Satish Kumar
Sven Koenig

In this paper, we study the one-shot and lifelong versions of the Target Assignment and Path Finding problem in automated sortation centers, where each agent needs to constantly assign itself a sorting station, move to its assigned station without colliding with obstacles or other agents, wait in the queue of that station to obtain a parcel for delivery, and then deliver the parcel to a sorting bin. The throughput of such centers is largely determined by the total idle time of all stations since their queues can frequently become empty. To address this problem, we ﬁrst formalize and study the oneshot version that assigns stations to a set of agents and ﬁnds collision-free paths for the agents to their assigned stations. We present efﬁcient algorithms for this task based on a novel min-cost max-ﬂow formulation that minimizes the total idle time of all stations in a ﬁxed time window. We then demonstrate how our algorithms for solving the one-shot problem can be applied to solving the lifelong problem as well. Experimentally, we believe to be the ﬁrst researchers to consider real-world automated sortation centers using an industrial simulator with realistic data and a kinodynamic model of real robots. On this simulator, we showcase the beneﬁts of our algorithms by demonstrating their efﬁciency and effectiveness for up to 350 agents.

PDF Details

ICRA Conference 2020 Conference Paper

Map As the Hidden Sensor: Fast Odometry-Based Global Localization

Cheng Peng
David Weikersdorfer

Accurate and robust global localization is essential to robotics applications. We propose a novel global localization method that employs the map traversability as a hidden observation. The resulting map-corrected odometry localization is able to provide an accurate belief tensor of the robot state. Our method can be used for blind robots in dark or highly reflective areas. In contrast to odometry drift in the long-term, our method using only odometry and the map converges in long-term. Our method can also be integrated with other sensors to boost the localization performance. The algorithm does not have any initial state assumption and tracks all possible robot states at all times. Therefore, our method is global and is robust in the event of ambiguous observations. We parallel each step of our algorithm such that it can be performed in real-time (up to ~300 Hz) using GPU. We validate our algorithm in different publicly available floor-plans and show that it is able to converge to the ground truth fast while being robust to ambiguities.

Details

AAMAS Conference 2019 Conference Paper

Multi-agent Path Planning with Non-constant Velocity Motion

Ngai Meng Kou
Cheng Peng
Xiaowei Yan
Zhiyuan Yang
Heng Liu
Kai Zhou
Haibing Zhao
Lijun Zhu

Multi-agent path planning has wide application in fields such as robotics, transportation, logistics, computer games, etc. . To formulate the multi-agent path finding as a concisely discretized problem, most of the previous works did not construct a detailed motion model of each agent. While many elegant algorithms were proposed in the literature, a method to efficiently plan the paths for multi agents with non-constant velocity is still lacking. In this paper, we propose two methods CRISE and COB to extend the existing algorithms for non-constant velocity motion path planning.

PDF