Ping Huang

EAAI Journal 2025 Journal Article

A multi-scale feature fusion network based on semi-channel attention for seismic phase picking

• Shuguang Zhao
• Jiang Wang
• Ping Huang
• Fa Zhao
• Fudong Zhang
• Yadongyang Zhu

In the field of seismic data processing, deep learning technologies have been widely used for seismic phase picking. However, it is difficult to take full advantage of the features extracted at different stages in existing models. In this paper, a multi-scale feature fusion network was proposed for seismic phase picking to address this problem. In the stage of feature extraction, semi-channel attention is introduced. It improves the representation ability of the model by efficiently utilizing the feature information extracted from the encoder. In the stage of decoding, a channel compression module is designed to reduce the number of feature channels. It improves the receptive field of channels. Additionally, a multi-feature fusion module is presented to integrate features at multiple scales. It reduces the loss of useful information and improves the accuracy of phase picking. The effectiveness of our network is validated on Stanford earthquake dataset, where the picking errors for phase picking are 2 ms. The parameter of our network is only 52, 100. Compared with earthquake transformer, it has 42. 1% fewer time costs to process 12, 656 test samples on Graphics Processing Unit.

TMLR Journal 2025 Journal Article

Learning Deformable Body Interactions With Adaptive Spatial Tokenization

• Hao Wang
• Yu Liu
• Daniel Biggs
• Haoru Wang
• Jiandong Yu
• Ping Huang

Simulating interactions between deformable bodies is vital in fields like material science, mechanical design, and robotics. While learning-based methods with Graph Neural Networks (GNNs) are effective at solving complex physical systems, they encounter scalability issues when modeling deformable body interactions. To model interactions between objects, pairwise global edges have to be created dynamically, which is computationally intensive and impractical for large-scale meshes. To overcome these challenges, drawing on insights from geometric representations, we propose an Adaptive Spatial Tokenization (AST) method for efficient representation of physical states. By dividing the simulation space into a grid of cells and mapping unstructured meshes onto this structured grid, our approach naturally groups adjacent mesh nodes. We then apply a cross-attention module to map the sparse cells into a compact, fixed-length embedding, serving as tokens for the entire physical state. Self-attention modules are employed to predict the next state over these tokens in latent space. This framework leverages the efficiency of tokenization and the expressive power of attention mechanisms to achieve accurate and scalable simulation results. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art approaches in modeling deformable body interactions. Notably, it remains effective on large-scale simulations with meshes exceeding 100,000 nodes, where existing methods are hindered by computational limitations. Additionally, we contribute a novel large-scale dataset encompassing a wide range of deformable body interactions to support future research in this area.

NeurIPS Conference 2025 Conference Paper

StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant

• Haibo Wang
• Bo Feng
• Zhengfeng Lai
• Mingze Xu
• Shiyu Li
• Weifeng Ge
• Afshin Dehghan
• Meng Cao

We present StreamBridge, a simple yet effective framework that seamlessly transforms offline Video-LLMs into streaming-capable models. It addresses two fundamental challenges in adapting existing models into online scenarios: (1) limited capability for multi-turn real-time understanding, and (2) lack of proactive response mechanisms. Specifically, StreamBridge incorporates (1) a memory buffer combined with a round-decayed compression strategy, supporting long-context multi-turn interactions, and (2) a decoupled, lightweight activation model that can be effortlessly integrated into existing Video-LLMs, enabling continuous proactive responses. To further support StreamBridge, we construct Stream-IT, a large-scale dataset tailored for streaming video understanding, featuring interleaved video-text sequences and diverse instruction formats. Extensive experiments show that StreamBridge significantly improves the streaming understanding capabilities of offline Video-LLMs across various tasks, outperforming even proprietary models such as GPT-4o and Gemini 1. 5 Pro. Simultaneously, it achieves competitive or superior performance on standard video understanding benchmarks.

ICLR Conference 2024 Conference Paper

Efficient ConvBN Blocks for Transfer Learning and Beyond

• Kaichao You
• Guo Qin
• Anchang Bao
• Meng Cao
• Ping Huang
• Jiulong Shan
• Mingsheng Long

Convolution-BatchNorm (ConvBN) blocks are integral components in various computer vision tasks and other domains. A ConvBN block can operate in three modes: Train, Eval, and Deploy. While the Train mode is indispensable for training models from scratch, the Eval mode is suitable for transfer learning and beyond, and the Deploy mode is designed for the deployment of models. This paper focuses on the trade-off between stability and efficiency in ConvBN blocks: Deploy mode is efficient but suffers from training instability; Eval mode is widely used in transfer learning but lacks efficiency. To solve the dilemma, we theoretically reveal the reason behind the diminished training stability observed in the Deploy mode. Subsequently, we propose a novel Tune mode to bridge the gap between Eval mode and Deploy mode. The proposed Tune mode is as stable as Eval mode for transfer learning, and its computational efficiency closely matches that of the Deploy mode. Through extensive experiments in object detection, classification, and adversarial example generation across $5$ datasets and $12$ model architectures, we demonstrate that the proposed Tune mode retains the performance while significantly reducing GPU memory footprint and training time, thereby contributing efficient ConvBN blocks for transfer learning and beyond. Our method has been integrated into both PyTorch (general machine learning framework) and MMCV/MMEngine (computer vision framework). Practitioners just need one line of code to enjoy our efficient ConvBN blocks thanks to PyTorch's builtin machine learning compilers.

NeurIPS Conference 2024 Conference Paper

ODGEN: Domain-specific Object Detection Data Generation with Diffusion Models

• Jingyuan Zhu
• Shiyu Li
• Yuxuan Liu
• Jian Yuan
• Ping Huang
• Jiulong Shan
• Huimin Ma

Modern diffusion-based image generative models have made significant progress and become promising to enrich training data for the object detection task. However, the generation quality and the controllability for complex scenes containing multi-class objects and dense objects with occlusions remain limited. This paper presents ODGEN, a novel method to generate high-quality images conditioned on bounding boxes, thereby facilitating data synthesis for object detection. Given a domain-specific object detection dataset, we first fine-tune a pre-trained diffusion model on both cropped foreground objects and entire images to fit target distributions. Then we propose to control the diffusion model using synthesized visual prompts with spatial constraints and object-wise textual descriptions. ODGEN exhibits robustness in handling complex scenes and specific domains. Further, we design a dataset synthesis pipeline to evaluate ODGEN on 7 domain-specific benchmarks to demonstrate its effectiveness. Adding training data generated by ODGEN improves up to 25. 3% mAP@. 50: .95 with object detectors like YOLOv5 and YOLOv7, outperforming prior controllable generative methods. In addition, we design an evaluation protocol based on COCO-2014 to validate ODGEN in general domains and observe an advantage up to 5. 6% in mAP@. 50: .95 against existing methods.

ICLR Conference 2023 Conference Paper

RGI: robust GAN-inversion for mask-free image inpainting and unsupervised pixel-wise anomaly detection

• Shancong Mou
• Xiaoyi Gu
• Meng Cao
• Haoping Bai
• Ping Huang
• Jiulong Shan
• Jianjun Shi

Generative adversarial networks (GANs), trained on a large-scale image dataset, can be a good approximator of the natural image manifold. GAN-inversion, using a pre-trained generator as a deep generative prior, is a promising tool for image restoration under corruptions. However, the performance of GAN-inversion can be limited by a lack of robustness to unknown gross corruptions, i.e., the restored image might easily deviate from the ground truth. In this paper, we propose a Robust GAN-inversion (RGI) method with a provable robustness guarantee to achieve image restoration under unknown \textit{gross} corruptions, where a small fraction of pixels are completely corrupted. Under mild assumptions, we show that the restored image and the identified corrupted region mask converge asymptotically to the ground truth. Moreover, we extend RGI to Relaxed-RGI (R-RGI) for generator fine-tuning to mitigate the gap between the GAN learned manifold and the true image manifold while avoiding trivial overfitting to the corrupted input image, which further improves the image restoration and corrupted region mask identification performance. The proposed RGI/R-RGI method unifies two important applications with state-of-the-art (SOTA) performance: (i) mask-free semantic inpainting, where the corruptions are unknown missing regions, the restored background can be used to restore the missing content. (ii) unsupervised pixel-wise anomaly detection, where the corruptions are unknown anomalous regions, the retrieved mask can be used as the anomalous region’s segmentation mask.

ICLR Conference 2022 Conference Paper

Information Gain Propagation: a New Way to Graph Active Learning with Soft Labels

• Wentao Zhang 0001
• Yexin Wang
• Zhenbang You
• Meng Cao
• Ping Huang
• Jiulong Shan
• Zhi Yang 0001
• Bin Cui 0001

Graph Neural Networks (GNNs) have achieved great success in various tasks, but their performance highly relies on a large number of labeled nodes, which typically requires considerable human effort. GNN-based Active Learning (AL) methods are proposed to improve the labeling efficiency by selecting the most valuable nodes to label. Existing methods assume an oracle can correctly categorize all the selected nodes and thus just focus on the node selection. However, such an exact labeling task is costly, especially when the categorization is out of the domain of individual expert (oracle). The paper goes further, presenting a soft-label approach to AL on GNNs. Our key innovations are: i) relaxed queries where a domain expert (oracle) only judges the correctness of the predicted labels (a binary question) rather than identifying the exact class (a multi-class question), and ii) new criteria of maximizing information gain propagation for active learner with relaxed queries and soft labels. Empirical studies on public datasets demonstrate that our method significantly outperforms the state-of-the-art GNN-based AL methods in terms of both accuracy and labeling cost.

NeurIPS Conference 2021 Conference Paper

BatchQuant: Quantized-for-all Architecture Search with Robust Quantizer

• Haoping Bai
• Meng Cao
• Ping Huang
• Jiulong Shan

As the applications of deep learning models on edge devices increase at an accelerating pace, fast adaptation to various scenarios with varying resource constraints has become a crucial aspect of model deployment. As a result, model optimization strategies with adaptive configuration are becoming increasingly popular. While single-shot quantized neural architecture search enjoys flexibility in both model architecture and quantization policy, the combined search space comes with many challenges, including instability when training the weight-sharing supernet and difficulty in navigating the exponentially growing search space. Existing methods tend to either limit the architecture search space to a small set of options or limit the quantization policy search space to fixed precision policies. To this end, we propose BatchQuant, a robust quantizer formulation that allows fast and stable training of a compact, single-shot, mixed-precision, weight-sharing supernet. We employ BatchQuant to train a compact supernet (offering over $10^{76}$ quantized subnets) within substantially fewer GPU hours than previous methods. Our approach, Quantized-for-all (QFA), is the first to seamlessly extend one-shot weight-sharing NAS supernet to support subnets with arbitrary ultra-low bitwidth mixed-precision quantization policies without retraining. QFA opens up new possibilities in joint hardware-aware neural architecture search and quantization. We demonstrate the effectiveness of our method on ImageNet and achieve SOTA Top-1 accuracy under a low complexity constraint (<20 MFLOPs).

NeurIPS Conference 2021 Conference Paper

RIM: Reliable Influence-based Active Learning on Graphs

• Wentao Zhang
• Yexin Wang
• Zhenbang You
• Meng Cao
• Ping Huang
• Jiulong Shan
• Zhi Yang
• Bin Cui

Message passing is the core of most graph models such as Graph Convolutional Network (GCN) and Label Propagation (LP), which usually require a large number of clean labeled data to smooth out the neighborhood over the graph. However, the labeling process can be tedious, costly, and error-prone in practice. In this paper, we propose to unify active learning (AL) and message passing towards minimizing labeling costs, e. g. , making use of few and unreliable labels that can be obtained cheaply. We make two contributions towards that end. First, we open up a perspective by drawing a connection between AL enforcing message passing and social influence maximization, ensuring that the selected samples effectively improve the model performance. Second, we propose an extension to the influence model that incorporates an explicit quality factor to model label noise. In this way, we derive a fundamentally new AL selection criterion for GCN and LP--reliable influence maximization (RIM)--by considering quantity and quality of influence simultaneously. Empirical studies on public datasets show that RIM significantly outperforms current AL methods in terms of accuracy and efficiency.

AIIM Journal 2019 Journal Article

A novel Chinese herbal medicine clustering algorithm via artificial bee colony optimization

• Nan Han
• Shaojie Qiao
• Guan Yuan
• Ping Huang
• Dingxiang Liu
• Kun Yue

Traditional Chinese medicine (TCM) has become popular and been viewed as an effective clinical treatment across the world. Accordingly, there is an ever-increasing interest in performing data analysis over TCM data. Aiming to cope with the problem of excessively depending on empirical values when selecting cluster centers by traditional clustering algorithms, an improved artificial bee colony algorithm is proposed by which to automatically select cluster centers and apply it to aggregate Chinese herbal medicines. The proposed method integrates the following new techniques: (1) improving the artificial bee colony algorithm by applying a new searching strategy of neighbour nectar, (2) employing the improved artificial bee colony algorithm to optimize the parameters of the cutoff distance d c, the local density ρ i and the minimum distance δ i between the element i and any other element with higher density in the cluster algorithm by fast search and finding of density peaks (called DP algorithm) to find the optimal cluster centers, in order to clustering herbal medicines in an accurate fashion with the guarantee of runtime performance. Extensive experiments were conducted on the UCI benchmark datasets and the TCM datasets and the results verify the effectiveness of the proposed method by comparing it with classical clustering algorithms including K-means, K-mediods and DBSCAN in multiple evaluation metrics, that is, Silhouette Coefficient, Entropy, Purity, Precision, Recall and F1-Measure. The results show that the IABC-DP algorithm outperforms other approaches with good clustering quality and accuracy on the UCI and the TCM datasets as well. In addition, it can be found that the improved artificial bee colony algorithm can effectively reduce the number of iterations when compared to the traditional bee colony algorithm. In particular, the IABC-DP algorithm is applied to cluster multi-dimensional Chinese herbal medicines and the result shows that it outperforms other clustering algorithms in clustering Chinese herbal medicines, which can contribute to a larger effort targeted at advancing the study of discovering composition rules of traditional Chinese prescriptions.

AAAI Conference 2011 Conference Paper

Exact Phase Transitions and Approximate Algorithm of #CSP

• Ping Huang
• Minghao Yin
• Ke Xu