Author name cluster

Gang Zhang

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.

10 papers

2 author rows

EAAI Journal 2026 Journal Article

Coupled data-driven and experience-informed neural networks for prediction of pile base resistance with consideration of data limitation

Kailiang Weng
Mincai Jia
Thanh T. Nguyen
Xingyuan Hu
Gang Zhang
Qingyuan Zeng

Recent advancements have witnessed the increasing integration of artificial intelligence (AI) methodologies into design and construction processes of various engineering matters. However, the purely data-based approaches are often overfitted to specific datasets without understanding of physics laws, resulting in data-driven models with limited out-of-distribution generalization capabilities and challenges in meeting the stringent requirements, especially when the reliable data is limited. To address these limitations, this study introduces a novel data-driven coupled with experience-informed approach. The proposed framework incorporates an Explicit Empirical Formula Network (EEFN) and an Implicit Empirical Information Network (IEIN), designed to enhance the model's generalization capability, particularly for predicting base resistance of pile. The EEFN generates predictions by identifying unknown parameters within empirical formulas and then subsequently substituting them into the respective equations. In contrast, the IEIN utilizes empirical information as prior knowledge to guide both the network and the loss function, enabling the direct calculation of prediction results that satisfy pile constraints across various stages. A comparative analysis of EEFN and IEIN against Backpropagation Neural Networks (BPNN) and Deep Operator Network (DeepOnet) was conducted using field load testing data from 37 high-rise building projects in Ho Chi Minh City, Vietnam, spanning from 2010 onward. The evaluation focused on the models' abilities to generalize both global patterns and individual characteristics beyond their training distributions. The results indicate that, when data is large enough, the IEIN exhibits superior generalization capabilities for global patterns, whereas the EEFN can significantly enhance the generalization of individual information, contingent upon the alignment between empirical equations and data. When data are limited, the IEIN outperforms alternative models in both generalization and robustness across domains. Consequently, the proposed model improves the use of experimental data and aligns with the inherent development principles of pile base resistance. This learning framework is particularly well suited for predicting pile base resistance in both long and super-long piles.

Details DOI

AAAI Conference 2025 Conference Paper

Interpretable Face Anti-Spoofing: Enhancing Generalization with Multimodal Large Language Models

Guosheng Zhang
Keyao Wang
Haixiao Yue
Ajian Liu
Gang Zhang
Kun Yao
Errui Ding
Jingdong Wang

Face Anti-Spoofing (FAS) is essential for ensuring the security and reliability of facial recognition systems. Most existing FAS methods are formulated as binary classification tasks, providing confidence scores without interpretation. They exhibit limited generalization in out-of-domain scenarios, such as new environments or unseen spoofing types. In this work, we introduce a multimodal large language model (MLLM) framework for FAS, termed Interpretable Face Anti-Spoofing (I-FAS), which transforms the FAS task into an interpretable visual question answering (VQA) paradigm. Specifically, we propose a Spoof-aware Captioning and Filtering (SCF) strategy to generate high-quality captions for FAS images, enriching the model's supervision with natural language interpretations. To mitigate the impact of noisy captions during training, we develop a Lopsided Language Model (L-LM) loss function that separates loss calculations for judgment and interpretation, prioritizing the optimization of the former. Furthermore, to enhance the model's perception of global visual features, we design a Globally Aware Connector (GAC) to align multi-level visual representations with the language model. Extensive experiments on standard and newly devised One to Eleven cross-domain benchmarks, comprising 12 public datasets, demonstrate that our method significantly outperforms state-of-the-art methods.

PDF Details DOI

ICRA Conference 2024 Conference Paper

End-to-end Semantic Segmentation Network for Low-Light Scenes

Hongmin Mu
Gang Zhang
MengChu Zhou
Zhengcai Cao

In the fields of robotic perception and computer vision, achieving accurate semantic segmentation of low-light or nighttime scenes is challenging. This is primarily due to the limited visibility of objects and the reduced texture and color contrasts among them. To address the issue of limited visibility, we propose a hierarchical gated convolution unit, which simultaneously expands the receptive field and restores edge texture. To address the issue of reduced texture among objects, we propose a dual closed-loop bipartite matching algorithm to establish a total loss function consisting of the unsupervised illumination enhancement loss and supervised intersection-over-union loss, thus enabling the joint minimization of both losses via the Hungarian algorithm. We thus achieve end-to-end training for a semantic segmentation network especially suitable for handling low-light scenes. Experimental results demonstrate that the proposed network surpasses existing methods on the Cityscapes dataset and notably outperforms state-of-the-art methods on both Dark Zurich and Nighttime Driving datasets.

Details

ICRA Conference 2024 Conference Paper

FastOcc: Accelerating 3D Occupancy Prediction by Fusing the 2D Bird's-Eye View and Perspective View

Jiawei Hou
Xiaoyan Li
Wenhao Guan
Gang Zhang
Di Feng
Yuheng Du
Xiangyang Xue 0001
Jian Pu

In autonomous driving, 3D occupancy prediction outputs voxel-wise status and semantic labels for more comprehensive understandings of 3D scenes compared with traditional perception tasks, such as 3D object detection and bird’s-eye view (BEV) semantic segmentation. Recent researchers have extensively explored various aspects of this task, including view transformation techniques, ground-truth label generation, and elaborate network design, aiming to achieve superior performance. However, the inference speed, crucial for running on an autonomous vehicle, is neglected. To this end, a new method, dubbed FastOcc, is proposed. By carefully analyzing the network effect and latency from four parts, including the input image resolution, image backbone, view transformation, and occupancy prediction head, it is found that the occupancy prediction head holds considerable potential for accelerating the model while keeping its accuracy. Targeted at improving this component, the time-consuming 3D convolution network is replaced with a novel residual-like architecture, where features are mainly digested by a lightweight 2D BEV convolution network and compensated by integrating the 3D voxel features interpolated from the original image features. Experiments on the Occ3D-nuScenes benchmark demonstrate that our FastOcc achieves state-of-the-art results with a fast inference speed.

Details

AAAI Conference 2024 Conference Paper

Multi-Domain Incremental Learning for Face Presentation Attack Detection

Keyao Wang
Guosheng Zhang
Haixiao Yue
Ajian Liu
Gang Zhang
Haocheng Feng
Junyu Han
Errui Ding

Previous face Presentation Attack Detection (PAD) methods aim to improve the effectiveness of cross-domain tasks. However, in real-world scenarios, the original training data of the pre-trained model is not available due to data privacy or other reasons. Under these constraints, general methods for fine-tuning single-target domain data may lose previously learned knowledge, leading to a catastrophic forgetting problem. To address these issues, we propose a multi-domain incremental learning (MDIL) method for PAD, which not only learns knowledge well from the new domain but also maintains the performance of previous domains stably. Specifically, we propose an adaptive domain-specific experts (ADE) framework based on the vision transformer to preserve the discriminability of previous domains. Furthermore, an asymmetric classifier is designed to keep the output distribution of different classifiers consistent, thereby improving the generalization ability. Extensive experiments show that our proposed method achieves state-of-the-art performance compared to prior methods of incremental learning. Excitingly, under more stringent setting conditions, our method approximates or even outperforms the DA/DG-based methods.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Octopus: A Multi-modal LLM with Parallel Recognition and Sequential Understanding

Chuyang Zhao
YuXin Song
Junru Chen
Kang Rong
Haocheng Feng
Gang Zhang
Shufan Ji
Jingdong Wang

A mainstream of Multi-modal Large Language Models (MLLMs) have two essential functions, i. e. , visual recognition (e. g. , grounding) and understanding (e. g. , visual question answering). Presently, all these MLLMs integrate visual recognition and understanding in a same sequential manner in the LLM head, i. e. , generating the response token-by-token for both recognition and understanding. We think unifying them in the same sequential manner is not optimal for two reasons: 1) parallel recognition is more efficient than sequential recognition and is actually prevailing in deep visual recognition, and 2) the recognition results can be integrated to help high-level cognition (while the current manner does not). Such motivated, this paper proposes a novel “parallel recognition → sequential understanding” framework for MLLMs. The bottom LLM layers are utilized for parallel recognition and the recognition results are relayed into the top LLM layers for sequential understanding. Specifically, parallel recognition in the bottom LLM layers is implemented via object queries, a popular mechanism in DEtection TRansformer, which we find to harmonize well with the LLM layers. Empirical studies show our MLLM named Octopus improves accuracy on popular MLLM tasks and is up to 5× faster on visual grounding tasks.

PDF Details DOI

IJCAI Conference 2023 Conference Paper

Dual Relation Knowledge Distillation for Object Detection

Zhen-Liang Ni
Fukui Yang
Shengzhao Wen
Gang Zhang

Knowledge distillation is an effective method for model compression. However, it is still a challenging topic to apply knowledge distillation to detection tasks. There are two key points resulting in poor distillation performance for detection tasks. One is the serious imbalance between foreground and background features, another one is that small object lacks enough feature representation. To solve the above issues, we propose a new distillation method named dual relation knowledge distillation (DRKD), including pixel-wise relation distillation and instance-wise relation distillation. The pixel-wise relation distillation embeds pixel-wise features in the graph space and applies graph convolution to capture the global pixel relation. By distilling the global pixel relation, the student detector can learn the relation between foreground and background features, and avoid the difficulty of distilling features directly for the feature imbalance issue. Besides, we find that instance-wise relation supplements valuable knowledge beyond independent features for small objects. Thus, the instance-wise relation distillation is designed, which calculates the similarity of different instances to obtain a relation matrix. More importantly, a relation filter module is designed to highlight valuable instance relations. The proposed dual relation knowledge distillation is general and can be easily applied for both one-stage and two-stage detectors. Our method achieves state-of-the-art performance, which improves Faster R-CNN based on ResNet50 from 38. 4% to 41. 6% mAP and improves RetinaNet based on ResNet50 from 37. 4% to 40. 3% mAP on COCO 2017.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Clouds

Gang Zhang
Chen Junnan
Guohuan Gao
Jianmin Li
Xiaolin Hu

3D object detection in point clouds is important for autonomous driving systems. A primary challenge in 3D object detection stems from the sparse distribution of points within the 3D scene. Existing high-performance methods typically employ 3D sparse convolutional neural networks with small kernels to extract features. To reduce computational costs, these methods resort to submanifold sparse convolutions, which prevent the information exchange among spatially disconnected features. Some recent approaches have attempted to address this problem by introducing large-kernel convolutions or self-attention mechanisms, but they either achieve limited accuracy improvements or incur excessive computational costs. We propose HEDNet, a hierarchical encoder-decoder network for 3D object detection, which leverages encoder-decoder blocks to capture long-range dependencies among features in the spatial space, particularly for large and distant objects. We conducted extensive experiments on the Waymo Open and nuScenes datasets. HEDNet achieved superior detection accuracy on both datasets than previous state-of-the-art methods with competitive efficiency. The code is available at https: //github. com/zhanggang001/HEDNet.

PDF Details

ICRA Conference 2022 Conference Paper

CPGNet: Cascade Point-Grid Fusion Network for Real-Time LiDAR Semantic Segmentation

Xiaoyan Li
Gang Zhang
Hongyu Pan
Zhenhua Wang

LiDAR semantic segmentation essential for advanced autonomous driving is required to be accurate, fast, and easy-deployed on mobile platforms. Previous point-based or sparse voxel-based methods are far away from real-time applications since time-consuming neighbor searching or sparse 3D convolution are employed. Recent 2D projection-based methods, including range view and multi-view fusion, can run in real time, but suffer from lower accuracy due to information loss during the 2 $D$ projection. Besides, to improve the performance, previous methods usually adopt test time augmentation (TTA), which further slows down the inference process. To achieve a better speed-accuracy trade-off, we propose Cascade Point-Grid Fusion Network (CPGNet), which ensures both effectiveness and efficiency mainly by the following two techniques: 1) the novel Point-Grid (PG) fusion block extracts semantic features mainly on the 2D projected grid for efficiency, while summarizes both 2D and 3D features on 3D point for minimal information loss; 2) the proposed transformation consistency loss narrows the gap between the single-time model inference and TTA. The experiments on the SemanticKITTI and nuScenes benchmarks demonstrate that the CPGNet without ensemble models or TTA is comparable with the state-of-the-art RPVNet, while it runs 4. 7 times faster.

Details

IJCAI Conference 2022 Conference Paper

PRNet: Point-Range Fusion Network for Real-Time LiDAR Semantic Segmentation

Xiaoyan Li
Gang Zhang
Tao Jiang
Xufen Cai
Zhenhua Wang

Accurate and real-time LiDAR semantic segmentation is necessary for advanced autonomous driving systems. To guarantee a fast inference speed, previous methods utilize the highly optimized 2D convolutions to extract features on the range view (RV), which is the most compact representation of the LiDAR point clouds. However, these methods often suffer from lower accuracy for two reasons: 1) the information loss during the projection from 3D points to the RV, 2) the semantic ambiguity when 3D points labels are assigned according to the RV predictions. In this work, we introduce an end-to-end point-range fusion network (PRNet) that extracts semantic features mainly on the RV and iteratively fuses the RV features back to the 3D points for the final prediction. Besides, a novel range view projection (RVP) operation is designed to alleviate the information loss during the projection to the RV, and a point-range convolution (PRConv) is proposed to automatically mitigate the semantic ambiguity during transmitting features from the RV back to 3D points. Experiments on the SemanticKITTI and nuScenes benchmarks demonstrate that the PRNet pushes the range-based methods to a new state-of-the-art, and achieves a better speed-accuracy trade-off.

PDF Details DOI