Zhe Ma

AAAI Conference 2025 Conference Paper

Improving Transformer Based Line Segment Detection with Matched Predicting and Re-ranking

• Xin Tong
• Shi Peng
• Baojie Tian
• Yufei Guo
• Xuhui Huang
• Zhe Ma

Classical Transformer-based line segment detection methods have delivered impressive results. However, we observe that some accurately detected line segments are assigned low confidence scores during prediction, causing them to be ranked lower and potentially suppressed. Additionally, these models often require prolonged training periods to achieve strong performance, largely due to the necessity of bipartite matching. In this paper, we introduce RANK-LETR, a novel Transformer-based line segment detection method. Our approach leverages learnable geometric information to refine the ranking of predicted line segments by enhancing the confidence scores of high-quality predictions in a posterior verification step. We also propose a new line segment proposal method, wherein the feature point nearest to the centroid of the line segment directly predicts the location, significantly improving training efficiency and stability. Moreover, we introduce a line segment ranking loss to stabilize rankings during training, thereby enhancing the generalization capability of the model. Experimental results demonstrate that our method outperforms other Transformer-based and CNN-based approaches in prediction accuracy while requiring fewer training epochs than previous Transformer-based models.

NeurIPS Conference 2025 Conference Paper

LLM-PySC2: Starcraft II learning environment for Large Language Models

• Zongyuan Li
• Yanan Ni
• Runnan Qi
• Chang Lu
• Lumin Jiang
• Xu Xiaojie
• Xiangbei Liu
• Pengfei Li

The tremendous potential has been demonstrated by large language models (LLMs) in intelligent decision-making problems, with unprecedented capabilities shown across diverse applications ranging from gaming AI systems to complex strategic planning frameworks. However, the StarCraft II platform, which has been widely adopted for validating decision-making algorithms in the past decade, has not yet provided substantial support for this emerging domain. To address issues that LLMs cannot interface with the hundreds of actions of the pysc2 backend and the lack of native support for multi-agent (MA) collaboration, we propose the LLM-PySC2 environment. This is the first environment that offers LLMs the complete pysc2 action space with sufficient multi-modal information and game Wiki knowledge. With an asynchronous query architecture, the environment efficiently interacts with LLMs that maintain a constant latency regardless of the scale of the agents' population. In the experiments, we evaluated LLMs' decision-making performance in both the macro-decision and micro-operation scenarios, with traditional StarCraft II Multi-Agent Challenge (SMAC) tasks and a series of new proposed. Results indicate that LLMs possess the potential to achieve victories in complex scenarios but cannot constantly generate correct decisions, especially in the recovered pysc2 action space and MA settings. Without task-relevant instructions, the pre-trained models suffer from issues such as hallucinations and inefficient collaboration. Our findings suggest that StarCraft II still challenges in the era of large models, revealing that there is a lot to do to develop an advanced LLM decision-making system, and the proposed LLM-PySC2 environment will support future development of LLM-based decision-making solutions.

NeurIPS Conference 2025 Conference Paper

RANK++LETR: Learn to Rank and Optimize Candidates for Line Segment Detection

• Xin Tong
• Baojie Tian
• Yufei Guo
• Zhe Ma

It is observed that the confidence score may fail to reflect the predicting quality accurately in previous proposal-based line segment detection methods, since the scores and the line locations are predicted simultaneously. We find that the line segment detection performance can be further improved by learning-based line candidate ranking and optimizing strategy. To this end, we build a novel end-to-end line detecting model named RANK++LETR upon deformable DETR architecture, where the encoder is used to select the line candidates while the decoder is applied to rank and optimize these candidates. We design line-aware deformable attention (LADA) module in which attention positions are distributed in a long narrow area and can align well with the elongated geometry of line segments. Moreover, we innovatively apply ranking-based supervision in line segment detection task with the design of contiguous labels according to the detection quality. Experimental results demonstrate that our method outperforms previous SOTA methods in prediction accuracy and gets faster inferring speed than other Transformer-based methods.

AAAI Conference 2025 Conference Paper

Safe Planner: Empowering Safety Awareness in Large Pre-Trained Models for Robot Task Planning

• Siyuan Li
• Feifan Liu
• Lingfei Cui
• Jiani Lu
• Qinqin Xiao
• Xirui Yang
• Peng Liu
• Kewu Sun

Robot task planning is an important problem for autonomous robots in long-horizon challenging tasks. As large pre-trained models have demonstrated superior planning ability, recent research investigates utilizing large models to achieve autonomous planning for robots in diverse tasks. However, since the large models are pre-trained with Internet data and lack the knowledge of real task scenes, large models as planners may make unsafe decisions that hurt the robots and the surrounding environments. To solve this challenge, we propose a novel Safe Planner framework, which empowers safety awareness in large pre-trained models to accomplish safe and executable planning. In this framework, we develop a safety prediction module to guide the high-level large model planner, and this safety module trained in a simulator can be effectively transferred to real-world tasks. The proposed Safe Planner framework is evaluated on both simulated environments and real robots. The experiment results demonstrate that Safe Planner not only achieves state-of-the-art task success rates, but also substantially improves safety during task execution.

IROS Conference 2024 Conference Paper

A Context-Enhanced Full-Resolution Floor Plan Segmentation Network for Topological Semantic Mapping

• Zhengcai Cao
• Yiyang Sun
• Zhe Ma
• MengChu Zhou

Topological semantic maps provide a practical solution to enhance indoor navigation for the Partially Sighted or Visually Impaired (PSVI). Segmenting indoor floor plans and extracting boundaries are key to constructing these maps. The existing methods exhibit low accuracy in segmentation. To achieve desired high segmentation accuracy, we introduce a Context-Enhanced Full-Resolution Network (CEFRN) for floor plan segmentation. It is designed to harness the shallow detailed features and inter-category contextual dependencies inherent in floor plans. CEFRN integrates modified residual blocks to capture the low-stage full-resolution features while maintaining its compactness. A position attention module is employed to refine the deep-stage contextual information. We also propose a two-dimensional deep supervision method to merge features from both stages, which significantly boosts the feature representation ability of CEFRN. Finally, a practical topological semantic mapping method for PSVI indoor navigation is introduced. Experimental results demonstrate that CEFRN’s segmentation accuracy well exceeds the state-of-the-art methods’. It can be used to well support accurate topological semantic mapping.

NeurIPS Conference 2024 Conference Paper

AdaPKC: PeakConv with Adaptive Peak Receptive Field for Radar Semantic Segmentation

• Teng Li
• Liwen Zhang
• Youcheng Zhang
• Zijun Hu
• Pengcheng Pi
• Zongqing Lu
• Qingmin Liao
• Zhe Ma

Deep learning-based radar detection technology is receiving increasing attention in areas such as autonomous driving, UAV surveillance, and marine monitoring. Among recent efforts, PeakConv (PKC) provides a solution that can retain the peak response characteristics of radar signals and play the characteristics of deep convolution, thereby improving the effect of radar semantic segmentation (RSS). However, due to the use of a pre-set fixed peak receptive field sampling rule, PKC still has limitations in dealing with problems such as inconsistency of target frequency domain response broadening, non-homogeneous and time-varying characteristic of noise/clutter distribution. Therefore, this paper proposes an idea of adaptive peak receptive field, and upgrades PKC to AdaPKC based on this idea. Beyond that, a novel fine-tuning technology to further boost the performance of AdaPKC-based RSS networks is presented. Through experimental verification using various real-measured radar data (including publicly available low-cost millimeter-wave radar dataset for autonomous driving and self-collected Ku-band surveillance radar dataset), we found that the performance of AdaPKC-based models surpasses other SoTA methods in RSS tasks. The code is available at https: //github. com/lihua199710/AdaPKC.

AAAI Conference 2024 Conference Paper

Enhancing Representation of Spiking Neural Networks via Similarity-Sensitive Contrastive Learning

• Yuhan Zhang
• Xiaode Liu
• Yuanpei Chen
• Weihang Peng
• Yufei Guo
• Xuhui Huang
• Zhe Ma

Spiking neural networks (SNNs) have attracted intensive attention as a promising energy-efficient alternative to conventional artificial neural networks (ANNs) recently, which could transmit information in form of binary spikes rather than continuous activations thus the multiplication of activation and weight could be replaced by addition to save energy. However, the binary spike representation form will sacrifice the expression performance of SNNs and lead to accuracy degradation compared with ANNs. Considering improving feature representation is beneficial to training an accurate SNN model, this paper focuses on enhancing the feature representation of the SNN. To this end, we establish a similarity-sensitive contrastive learning framework, where SNN could capture significantly more information from its ANN counterpart to improve representation by Mutual Information (MI) maximization with layer-wise sensitivity to similarity. In specific, it enriches the SNN’s feature representation by pulling the positive pairs of SNN's and ANN's feature representation of each layer from the same input samples closer together while pushing the negative pairs from different samples further apart. Experimental results show that our method consistently outperforms the current state-of-the-art algorithms on both popular non-spiking static and neuromorphic datasets.

NeurIPS Conference 2024 Conference Paper

EnOF-SNN: Training Accurate Spiking Neural Networks via Enhancing the Output Feature

• Yufei Guo
• Weihang Peng
• Xiaode Liu
• Yuanpei Chen
• Yuhan Zhang
• Xin Tong
• Zhou Jie
• Zhe Ma

Spiking neural networks (SNNs) have gained more and more interest as one of the energy-efficient alternatives of conventional artificial neural networks (ANNs). They exchange 0/1 spikes for processing information, thus most of the multiplications in networks can be replaced by additions. However, binary spike feature maps will limit the expressiveness of the SNN and result in unsatisfactory performance compared with ANNs. It is shown that a rich output feature representation, i. e. , the feature vector before classifier) is beneficial to training an accurate model in ANNs for classification. We wonder if it also does for SNNs and how to improve the feature representation of the SNN. To this end, we materialize this idea in two special designed methods for SNNs. First, inspired by some ANN-SNN methods that directly copy-paste the weight parameters from trained ANN with light modification to homogeneous SNN can obtain a well-performed SNN, we use rich information of the weight parameters from the trained ANN counterpart to guide the feature representation learning of the SNN. In particular, we present the SNN's and ANN's feature representation from the same input to ANN's classifier to product SNN's and ANN's outputs respectively and then align the feature with the KL-divergence loss as in knowledge distillation methods, called L_ AF loss. It can be seen as a novel and effective knowledge distillation method specially designed for the SNN that comes from both the knowledge distillation and ANN-SNN methods. Various ablation study shows that the L_AF loss is more powerful than the vanilla knowledge distillation method. Second, we replace the last Leaky Integrate-and-Fire (LIF) activation layer as the ReLU activation layer to generate the output feature, thus a more powerful SNN with full-precision feature representation can be achieved but with only a little extra computation. Experimental results show that our method consistently outperforms the current state-of-the-art algorithms on both popular non-spiking static and neuromorphic datasets. We provide an extremely simple but effective way to train high-accuracy spiking neural networks.

NeurIPS Conference 2024 Conference Paper

Exploring Fixed Point in Image Editing: Theoretical Support and Convergence Optimization

• Chen Hang
• Zhe Ma
• Haoming Chen
• Xuwei Fang
• Weisheng Xie
• Faming Fang
• Guixu Zhang
• Hongbin Wang

In image editing, Denoising Diffusion Implicit Models (DDIM) inversion has become a widely adopted method and is extensively used in various image editing approaches. The core concept of DDIM inversion stems from the deterministic sampling technique of DDIM, which allows the DDIM process to be viewed as an Ordinary Differential Equation (ODE) process that is reversible. This enables the prediction of corresponding noise from a reference image, ensuring that the restored image from this noise remains consistent with the reference image. Image editing exploits this property by modifying the cross-attention between text and images to edit specific objects while preserving the remaining regions. However, in the DDIM inversion, using the $t-1$ time step to approximate the noise prediction at time step $t$ introduces errors between the restored image and the reference image. Recent approaches have modeled each step of the DDIM inversion process as finding a fixed-point problem of an implicit function. This approach significantly mitigates the error in the restored image but lacks theoretical support regarding the existence of such fixed points. Therefore, this paper focuses on the study of fixed points in DDIM inversion and provides theoretical support. Based on the obtained theoretical insights, we further optimize the loss function for the convergence of fixed points in the original DDIM inversion, improving the visual quality of the edited image. Finally, we extend the fixed-point based image editing to the application of unsupervised image dehazing, introducing a novel text-based approach for unsupervised dehazing.

AAAI Conference 2024 Conference Paper

Let All Be Whitened: Multi-Teacher Distillation for Efficient Visual Retrieval

• Zhe Ma
• Jianfeng Dong
• Shouling Ji
• Zhenguang Liu
• Xuhong Zhang
• Zonghui Wang
• Sifeng He
• Feng Qian

Visual retrieval aims to search for the most relevant visual items, e.g., images and videos, from a candidate gallery with a given query item. Accuracy and efficiency are two competing objectives in retrieval tasks. Instead of crafting a new method pursuing further improvement on accuracy, in this paper we propose a multi-teacher distillation framework Whiten-MTD, which is able to transfer knowledge from off-the-shelf pre-trained retrieval models to a lightweight student model for efficient visual retrieval. Furthermore, we discover that the similarities obtained by different retrieval models are diversified and incommensurable, which makes it challenging to jointly distill knowledge from multiple models. Therefore, we propose to whiten the output of teacher models before fusion, which enables effective multi-teacher distillation for retrieval models. Whiten-MTD is conceptually simple and practically effective. Extensive experiments on two landmark image retrieval datasets and one video retrieval dataset demonstrate the effectiveness of our proposed method, and its good balance of retrieval performance and efficiency. Our source code is released at https://github.com/Maryeon/whiten_mtd.

AAAI Conference 2024 Conference Paper

Robust Visual Imitation Learning with Inverse Dynamics Representations

• Siyuan Li
• Xun Wang
• Rongchang Zuo
• Kewu Sun
• Lingfei Cui
• Jishiyu Ding
• Peng Liu
• Zhe Ma

Imitation learning (IL) has achieved considerable success in solving complex sequential decision-making problems. However, current IL methods mainly assume that the environment for learning policies is the same as the environment for collecting expert datasets. Therefore, these methods may fail to work when there are slight differences between the learning and expert environments, especially for challenging problems with high-dimensional image observations. However, in real-world scenarios, it is rare to have the chance to collect expert trajectories precisely in the target learning environment. To address this challenge, we propose a novel robust imitation learning approach, where we develop an inverse dynamics state representation learning objective to align the expert environment and the learning environment. With the abstract state representation, we design an effective reward function, which thoroughly measures the similarity between behavior data and expert data not only element-wise, but also from the trajectory level. We conduct extensive experiments to evaluate the proposed approach under various visual perturbations and in diverse visual control tasks. Our approach can achieve a near-expert performance in most environments, and significantly outperforms the state-of-the-art visual IL methods and robust IL methods.

IJCAI Conference 2024 Conference Paper

SpecAR-Net: Spectrogram Analysis and Representation Network for Time Series

• Yi Dong
• Liwen Zhang
• Youcheng Zhang
• Shi Peng
• Wen Chen
• Zhe Ma

Representing temporal-structured samples is essential for effective time series analysis tasks. So far, recurrent networks, convolution networks and transformer-style models have been successively applied in temporal data representation, yielding notable results. However, most existing methods primarily focus on modeling and representing the variation patterns within time series in the time domain. As a highly abstracted information entity, 1D time series couples various patterns such as trends, seasonality, and dramatic changes (instantaneous high dynamic), it is difficult to exploit these highly coupled properties merely by analysis tools on purely time domain. To this end, we present Spectrogram Analysis and Representation Network (SpecAR-Net). SpecAR-Net aims at learning more comprehensive representations by modeling raw time series in both time and frequency domain, where an efficient joint extraction of time-frequency features is achieved through a group of learnable 2D multi-scale parallel complex convolution blocks. Experimental results show that the SpecAR-Net achieves excellent performance on 5 major downstream tasks i. e. , classification, anomaly detection, imputation, long- and short-term forecasting. Code and appendix are available at https: //github. com/Dongyi2go/SpecAR_Net.

NeurIPS Conference 2024 Conference Paper

Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks

• Yufei Guo
• Yuanpei Chen
• Zecheng Hao
• Weihang Peng
• Zhou Jie
• Yuhan Zhang
• Xiaode Liu
• Zhe Ma

The Spiking Neural Network (SNN) is a biologically inspired neural network infrastructure that has recently garnered significant attention. It utilizes binary spike activations to transmit information, thereby replacing multiplications with additions and resulting in high energy efficiency. However, training an SNN directly poses a challenge due to the undefined gradient of the firing spike process. Although prior works have employed various surrogate gradient training methods that use an alternative function to replace the firing process during back-propagation, these approaches ignore an intrinsic problem: gradient vanishing. To address this issue, we propose a shortcut back-propagation method in the paper, which advocates for transmitting the gradient directly from the loss to the shallow layers. This enables us to present the gradient to the shallow layers directly, thereby significantly mitigating the gradient vanishing problem. Additionally, this method does not introduce any burden during the inference phase. To strike a balance between final accuracy and ease of training, we also propose an evolutionary training framework and implement it by inducing a balance coefficient that dynamically changes with the training epoch, which further improves the network's performance. Extensive experiments conducted over static and dynamic datasets using several popular network structures reveal that our method consistently outperforms state-of-the-art methods.

NeurIPS Conference 2024 Conference Paper

TARSS-Net: Temporal-Aware Radar Semantic Segmentation Network

• Youcheng Zhang
• Liwen Zhang
• Zijun Hu
• Pengcheng Pi
• Teng Li
• Yuanpei Chen
• Shi Peng
• Zhe Ma

Radar signal interpretation plays a crucial role in remote detection and ranging. With the gradual display of the advantages of neural network technology in signal processing, learning-based radar signal interpretation is becoming a research hot-spot and made great progress. And since radar semantic segmentation (RSS) can provide more fine-grained target information, it has become a more concerned direction in this field. However, the temporal information, which is an important clue for analyzing radar data, has not been exploited sufficiently in present RSS frameworks. In this work, we propose a novel temporal information learning paradigm, i. e. , data-driven temporal information aggregation with learned target-history relations. Following this idea, a flexible learning module, called Temporal Relation-Aware Module (TRAM) is carefully designed. TRAM contains two main blocks: i) an encoder for capturing the target-history temporal relations (TH-TRE) and ii) a learnable temporal relation attentive pooling (TRAP) for aggregating temporal information. Based on TRAM, an end-to-end Temporal-Aware RSS Network (TARSS-Net) is presented, which has outstanding performance on publicly available and our collected real-measured datasets. Code and supplementary materials are available at https: //github. com/zlw9161/TARSS-Net.

AAAI Conference 2024 Conference Paper

Ternary Spike: Learning Ternary Spikes for Spiking Neural Networks

• Yufei Guo
• Yuanpei Chen
• Xiaode Liu
• Weihang Peng
• Yuhan Zhang
• Xuhui Huang
• Zhe Ma

The Spiking Neural Network (SNN), as one of the biologically inspired neural network infrastructures, has drawn increasing attention recently. It adopts binary spike activations to transmit information, thus the multiplications of activations and weights can be substituted by additions, which brings high energy efficiency. However, in the paper, we theoretically and experimentally prove that the binary spike activation map cannot carry enough information, thus causing information loss and resulting in accuracy decreasing. To handle the problem, we propose a ternary spike neuron to transmit information. The ternary spike neuron can also enjoy the event-driven and multiplication-free operation advantages of the binary spike neuron but will boost the information capacity. Furthermore, we also embed a trainable factor in the ternary spike neuron to learn the suitable spike amplitude, thus our SNN will adopt different spike amplitudes along layers, which can better suit the phenomenon that the membrane potential distributions are different along layers. To retain the efficiency of the vanilla ternary spike, the trainable ternary spike SNN will be converted to a standard one again via a re-parameterization technique in the inference. Extensive experiments with several popular network structures over static and dynamic datasets show that the ternary spike can consistently outperform state-of-the-art methods. Our code is open-sourced at https://github.com/yfguo91/Ternary-Spike.

NeurIPS Conference 2023 Conference Paper

Spiking PointNet: Spiking Neural Networks for Point Clouds

• Dayong Ren
• Zhe Ma
• Yuanpei Chen
• Weihang Peng
• Xiaode Liu
• Yuhan Zhang
• Yufei Guo

Recently, Spiking Neural Networks (SNNs), enjoying extreme energy efficiency, have drawn much research attention on 2D visual recognition and shown gradually increasing application potential. However, it still remains underexplored whether SNNs can be generalized to 3D recognition. To this end, we present Spiking PointNet in the paper, the first spiking neural model for efficient deep learning on point clouds. We discover that the two huge obstacles limiting the application of SNNs in point clouds are: the intrinsic optimization obstacle of SNNs that impedes the training of a big spiking model with large time steps, and the expensive memory and computation cost of PointNet that makes training a big spiking point model unrealistic. To solve the problems simultaneously, we present a trained-less but learning-more paradigm for Spiking PointNet with theoretical justifications and in-depth experimental analysis. In specific, our Spiking PointNet is trained with only a single time step but can obtain better performance with multiple time steps inference, compared to the one trained directly with multiple time steps. We conduct various experiments on ModelNet10, ModelNet40 to demonstrate the effectiveness of Sipiking PointNet. Notably, our Spiking PointNet even can outperform its ANN counterpart, which is rare in the SNN field thus providing a potential research direction for the following work. Moreover, Spiking PointNet shows impressive speedup and storage saving in the training phase. Our code is open-sourced at https: //github. com/DayongRen/Spiking-PointNet.

NeurIPS Conference 2022 Conference Paper

IM-Loss: Information Maximization Loss for Spiking Neural Networks

• Yufei Guo
• Yuanpei Chen
• Liwen Zhang
• Xiaode Liu
• Yinglei Wang
• Xuhui Huang
• Zhe Ma

Spiking Neural Network (SNN), recognized as a type of biologically plausible architecture, has recently drawn much research attention. It transmits information by $0/1$ spikes. This bio-mimetic mechanism of SNN demonstrates extreme energy efficiency since it avoids any multiplications on neuromorphic hardware. However, the forward-passing $0/1$ spike quantization will cause information loss and accuracy degradation. To deal with this problem, the Information maximization loss (IM-Loss) that aims at maximizing the information flow in the SNN is proposed in the paper. The IM-Loss not only enhances the information expressiveness of an SNN directly but also plays a part of the role of normalization without introducing any additional operations (\textit{e. g. }, bias and scaling) in the inference phase. Additionally, we introduce a novel differentiable spike activity estimation, Evolutionary Surrogate Gradients (ESG) in SNNs. By appointing automatic evolvable surrogate gradients for spike activity function, ESG can ensure sufficient model updates at the beginning and accurate gradients at the end of the training, resulting in both easy convergence and high task performance. Experimental results on both popular non-spiking static and neuromorphic datasets show that the SNN models trained by our method outperform the current state-of-the-art algorithms.

AAAI Conference 2020 Conference Paper

Fine-Grained Fashion Similarity Learning by Attribute-Specific Embedding Network

• Zhe Ma
• Jianfeng Dong
• Zhongzi Long
• Yao Zhang
• Yuan He
• Hui Xue
• Shouling Ji

This paper strives to learn fine-grained fashion similarity. In this similarity paradigm, one should pay more attention to the similarity in terms of a specific design/attribute among fashion items, which has potential values in many fashion related applications such as fashion copyright protection. To this end, we propose an Attribute-Specific Embedding Network (ASEN) to jointly learn multiple attributespecific embeddings in an end-to-end manner, thus measure the fine-grained similarity in the corresponding space. With two attention modules, i. e. , Attribute-aware Spatial Attention and Attribute-aware Channel Attention, ASEN is able to locate the related regions and capture the essential patterns under the guidance of the specified attribute, thus make the learned attribute-specific embeddings better reflect the fine-grained similarity. Extensive experiments on four fashion-related datasets show the effectiveness of ASEN for fine-grained fashion similarity learning and its potential for fashion reranking. Code and data are available at https: //github. com/Maryeon/asen.

IJCAI Conference 1995 Conference Paper

GR2—A Hybrid Knowledge-based System Using General Rules

• Zhe Ma
• Robert F. Harrison
• R. Lee Kennedy