Huafeng Liu

Mingyang Song, Haiyun Jiang, Shuming Shi et al.

The emergence of ChatGPT has recently garnered significant attention from the computational linguistics community. To demonstrate its capabilities as a keyphrase generator, we conduct a preliminary evaluation of ChatGPT for the keyphrase generation task. We evaluate its performance in various aspects, including keyphrase generation prompts, keyphrase generation diversity, and long document understanding. Our evaluation is based on six benchmark datasets, and we adopt the prompt suggested by OpenAI while extending it to six candidate prompts. We find that ChatGPT performs exceptionally well on all six candidate prompts, with minor performance differences observed across the datasets. Based on our findings, we conclude that ChatGPT has great potential for keyphrase generation. Moreover, we discover that ChatGPT still faces challenges when it comes to generating absent keyphrases. Meanwhile, in the final section, we also present some limitations and future expansions of this report.

Huafeng Liu, Pai Peng, Tao Chen et al.

Few-shot semantic segmentation is the task of learning to locate each pixel of the novel class in the query image with only a few annotated support images. The current correlation-based methods construct pair-wise feature correlations to establish the many-to-many matching because the typical prototype-based approaches cannot learn fine-grained correspondence relations. However, the existing methods still suffer from the noise contained in naive correlations and the lack of context semantic information in correlations. To alleviate these problems mentioned above, we propose a Feature-Enhanced Context-Aware Network (FECANet). Specifically, a feature enhancement module is proposed to suppress the matching noise caused by inter-class local similarity and enhance the intra-class relevance in the naive correlation. In addition, we propose a novel correlation reconstruction module that encodes extra correspondence relations between foreground and background and multi-scale context semantic features, significantly boosting the encoder to capture a reliable matching pattern. Experiments on PASCAL-$5^i$ and COCO-$20^i$ datasets demonstrate that our proposed FECANet leads to remarkable improvement compared to previous state-of-the-arts, demonstrating its effectiveness.

Rui Hu, Yunmei Chen, Kyungsang Kim et al.

Deep learning based PET image reconstruction methods have achieved promising results recently. However, most of these methods follow a supervised learning paradigm, which rely heavily on the availability of high-quality training labels. In particular, the long scanning time required and high radiation exposure associated with PET scans make obtaining this labels impractical. In this paper, we propose a dual-domain unsupervised PET image reconstruction method based on learned decent algorithm, which reconstructs high-quality PET images from sinograms without the need for image labels. Specifically, we unroll the proximal gradient method with a learnable l2,1 norm for PET image reconstruction problem. The training is unsupervised, using measurement domain loss based on deep image prior as well as image domain loss based on rotation equivariance property. The experimental results domonstrate the superior performance of proposed method compared with maximum likelihood expectation maximazation (MLEM), total-variation regularized EM (EM-TV) and deep image prior based method (DIP).

Chenxu Li, Rui Hu, Jianan Cui et al.

The integration of Time-of-Flight (TOF) information in the reconstruction process of Positron Emission Tomography (PET) yields improved image properties. However, implementing the cutting-edge model-based deep learning methods for TOF-PET reconstruction is challenging due to the substantial memory requirements. In this study, we present a novel model-based deep learning approach, LMPDNet, for TOF-PET reconstruction from list-mode data. We address the issue of real-time parallel computation of the projection matrix for list-mode data, and propose an iterative model-based module that utilizes a dedicated network model for list-mode data. Our experimental results indicate that the proposed LMPDNet outperforms traditional iteration-based TOF-PET list-mode reconstruction algorithms. Additionally, we compare the spatial and temporal consumption of list-mode data and sinogram data in model-based deep learning methods, demonstrating the superiority of list-mode data in model-based TOF-PET reconstruction.

Rui Hu, Jianan Cui, Chengjin Yu et al.

Dynamic positron emission tomography (dPET) image reconstruction is extremely challenging due to the limited counts received in individual frame. In this paper, we propose a spatial-temporal convolutional primal dual network (STPDnet) for dynamic PET image reconstruction. Both spatial and temporal correlations are encoded by 3D convolution operators. The physical projection of PET is embedded in the iterative learning process of the network, which provides the physical constraints and enhances interpretability. The experiments of real rat scan data have shown that the proposed method can achieve substantial noise reduction in both temporal and spatial domains and outperform the maximum likelihood expectation maximization (MLEM), spatial-temporal kernel method (KEM-ST), DeepPET and Learned Primal Dual (LPD).

Yihang Gao, Huafeng Liu, Michael K. Ng et al.

Wide applications of differentiable two-player sequential games (e.g., image generation by GANs) have raised much interest and attention of researchers to study efficient and fast algorithms. Most of the existing algorithms are developed based on nice properties of simultaneous games, i.e., convex-concave payoff functions, but are not applicable in solving sequential games with different settings. Some conventional gradient descent ascent algorithms theoretically and numerically fail to find the local Nash equilibrium of the simultaneous game or the local minimax (i.e., local Stackelberg equilibrium) of the sequential game. In this paper, we propose the HessianFR, an efficient Hessian-based Follow-the-Ridge algorithm with theoretical guarantees. Furthermore, the convergence of the stochastic algorithm and the approximation of Hessian inverse are exploited to improve algorithm efficiency. A series of experiments of training generative adversarial networks (GANs) have been conducted on both synthetic and real-world large-scale image datasets (e.g. MNIST, CIFAR-10 and CelebA). The experimental results demonstrate that the proposed HessianFR outperforms baselines in terms of convergence and image generation quality.

Jingren Hou, Hong Wang, Pengyu Xu et al.

Real-world scientific applications frequently encounter incomplete observational data due to sensor limitations, geographic constraints, or measurement costs. Although neural operators significantly advanced PDE solving in terms of computational efficiency and accuracy, their underlying assumption of fully-observed spatial inputs severely restricts applicability in real-world applications. We introduce the first systematic framework for learning neural operators from partial observation. We identify and formalize two fundamental obstacles: (i) the supervision gap in unobserved regions that prevents effective learning of physical correlations, and (ii) the dynamic spatial mismatch between incomplete inputs and complete solution fields. Specifically, our proposed Latent Autoregressive Neural Operator(LANO) introduces two novel components designed explicitly to address the core difficulties of partial observations: (i) a mask-to-predict training strategy that creates artificial supervision by strategically masking observed regions, and (ii) a Physics-Aware Latent Propagator that reconstructs solutions through boundary-first autoregressive generation in latent space. Additionally, we develop POBench-PDE, a dedicated and comprehensive benchmark designed specifically for evaluating neural operators under partial observation conditions across three PDE-governed tasks. LANO achieves state-of-the-art performance with 18--69$\%$ relative L2 error reduction across all benchmarks under patch-wise missingness with less than 50$\%$ missing rate, including real-world climate prediction. Our approach effectively addresses practical scenarios involving up to 75$\%$ missing rate, to some extent bridging the existing gap between idealized research settings and the complexities of real-world scientific computing.

Rui Hu, Chenxu Li, Kun Tian et al.

Time-of-flight (TOF) information provides more accurate location data for annihilation photons, thereby enhancing the quality of PET reconstruction images and reducing noise. List-mode reconstruction has a significant advantage in handling TOF information. However, current advanced TOF PET list-mode reconstruction algorithms still require improvements when dealing with low-count data. Deep learning algorithms have shown promising results in PET image reconstruction. Nevertheless, the incorporation of TOF information poses significant challenges related to the storage space required by deep learning methods, particularly for the advanced deep unrolled methods. In this study, we propose a deep unrolled primal dual network for TOF-PET list-mode reconstruction. The network is unrolled into multiple phases, with each phase comprising a dual network for list-mode domain updates and a primal network for image domain updates. We utilize CUDA for parallel acceleration and computation of the system matrix for TOF list-mode data, and we adopt a dynamic access strategy to mitigate memory consumption. Reconstructed images of different TOF resolutions and different count levels show that the proposed method outperforms the LM-OSEM, LM-EMTV, LM-SPDHG,LM-SPDHG-TV and FastPET method in both visually and quantitative analysis. These results demonstrate the potential application of deep unrolled methods for TOF-PET list-mode data and show better performance than current mainstream TOF-PET list-mode reconstruction algorithms, providing new insights for the application of deep learning methods in TOF list-mode data. The codes for this work are available at https://github.com/RickHH/LMPDnet

Huafeng Liu, Benjamin Dowdell, Todd Engelder et al.

Glioblastoma is one of the most aggressive and deadliest types of brain cancer, with low survival rates compared to other types of cancer. Analysis of Magnetic Resonance Imaging (MRI) scans is one of the most effective methods for the diagnosis and treatment of brain cancers such as glioblastoma. Accurate tumor segmentation in MRI images is often required for treatment planning and risk assessment of treatment methods. Here, we propose a novel pipeline, Brain Radiology Aided by Intelligent Neural NETworks (BRAINNET), which leverages MaskFormer, a vision transformer model, and generates robust tumor segmentation maks. We use an ensemble of nine predictions from three models separately trained on each of the three orthogonal 2D slice directions (axial, sagittal, and coronal) of a 3D brain MRI volume. We train and test our models on the publicly available UPenn-GBM dataset, consisting of 3D multi-parametric MRI (mpMRI) scans from 611 subjects. Using Dice coefficient (DC) and 95% Hausdorff distance (HD) for evaluation, our models achieved state-of-the-art results in segmenting all three different tumor regions -- tumor core (DC = 0.894, HD = 2.308), whole tumor (DC = 0.891, HD = 3.552), and enhancing tumor (DC = 0.812, HD = 1.608).

Gensheng Pei, Tao Chen, Xiruo Jiang et al.

Recently, the advancement of self-supervised learning techniques, like masked autoencoders (MAE), has greatly influenced visual representation learning for images and videos. Nevertheless, it is worth noting that the predominant approaches in existing masked image / video modeling rely excessively on resource-intensive vision transformers (ViTs) as the feature encoder. In this paper, we propose a new approach termed as \textbf{VideoMAC}, which combines video masked autoencoders with resource-friendly ConvNets. Specifically, VideoMAC employs symmetric masking on randomly sampled pairs of video frames. To prevent the issue of mask pattern dissipation, we utilize ConvNets which are implemented with sparse convolutional operators as encoders. Simultaneously, we present a simple yet effective masked video modeling (MVM) approach, a dual encoder architecture comprising an online encoder and an exponential moving average target encoder, aimed to facilitate inter-frame reconstruction consistency in videos. Additionally, we demonstrate that VideoMAC, empowering classical (ResNet) / modern (ConvNeXt) convolutional encoders to harness the benefits of MVM, outperforms ViT-based approaches on downstream tasks, including video object segmentation (+\textbf{5.2\%} / \textbf{6.4\%} $\mathcal{J}\&\mathcal{F}$), body part propagation (+\textbf{6.3\%} / \textbf{3.1\%} mIoU), and human pose tracking (+\textbf{10.2\%} / \textbf{11.1\%} PCK@0.1).

Huafeng Liu, Mengmeng Sheng, Zeren Sun et al.

Learning with noisy labels has gained increasing attention because the inevitable imperfect labels in real-world scenarios can substantially hurt the deep model performance. Recent studies tend to regard low-loss samples as clean ones and discard high-loss ones to alleviate the negative impact of noisy labels. However, real-world datasets contain not only noisy labels but also class imbalance. The imbalance issue is prone to causing failure in the loss-based sample selection since the under-learning of tail classes also leans to produce high losses. To this end, we propose a simple yet effective method to address noisy labels in imbalanced datasets. Specifically, we propose Class-Balance-based sample Selection (CBS) to prevent the tail class samples from being neglected during training. We propose Confidence-based Sample Augmentation (CSA) for the chosen clean samples to enhance their reliability in the training process. To exploit selected noisy samples, we resort to prediction history to rectify labels of noisy samples. Moreover, we introduce the Average Confidence Margin (ACM) metric to measure the quality of corrected labels by leveraging the model's evolving training dynamics, thereby ensuring that low-quality corrected noisy samples are appropriately masked out. Lastly, consistency regularization is imposed on filtered label-corrected noisy samples to boost model performance. Comprehensive experimental results on synthetic and real-world datasets demonstrate the effectiveness and superiority of our proposed method, especially in imbalanced scenarios. Comprehensive experimental results on synthetic and real-world datasets demonstrate the effectiveness and superiority of our proposed method, especially in imbalanced scenarios.

Rui Hu, Qian He, Gaofeng He et al.

Modeling and producing lifelike clothed human images has attracted researchers' attention from different areas for decades, with the complexity from highly articulated and structured content. Rendering algorithms decompose and simulate the imaging process of a camera, while are limited by the accuracy of modeled variables and the efficiency of computation. Generative models can produce impressively vivid human images, however still lacking in controllability and editability. This paper studies photorealism enhancement of rendered images, leveraging generative power from diffusion models on the controlled basis of rendering. We introduce a novel framework to translate rendered images into their realistic counterparts, which consists of two stages: Domain Knowledge Injection (DKI) and Realistic Image Generation (RIG). In DKI, we adopt positive (real) domain finetuning and negative (rendered) domain embedding to inject knowledge into a pretrained Text-to-image (T2I) diffusion model. In RIG, we generate the realistic image corresponding to the input rendered image, with a Texture-preserving Attention Control (TAC) to preserve fine-grained clothing textures, exploiting the decoupled features encoded in the UNet structure. Additionally, we introduce SynFashion dataset, featuring high-quality digital clothing images with diverse textures. Extensive experimental results demonstrate the superiority and effectiveness of our method in rendered-to-real image translation.

Ziqian Bi, Lu Chen, Junhao Song et al.

This study presents the first comprehensive evaluation of thinking budget mechanisms in medical reasoning tasks, revealing fundamental scaling laws between computational resources and reasoning quality. We systematically evaluated two major model families, Qwen3 (1.7B to 235B parameters) and DeepSeek-R1 (1.5B to 70B parameters), across 15 medical datasets spanning diverse specialties and difficulty levels. Through controlled experiments with thinking budgets ranging from zero to unlimited tokens, we establish logarithmic scaling relationships where accuracy improvements follow a predictable pattern with both thinking budget and model size. Our findings identify three distinct efficiency regimes: high-efficiency (0 to 256 tokens) suitable for real-time applications, balanced (256 to 512 tokens) offering optimal cost-performance tradeoffs for routine clinical support, and high-accuracy (above 512 tokens) justified only for critical diagnostic tasks. Notably, smaller models demonstrate disproportionately larger benefits from extended thinking, with 15 to 20% improvements compared to 5 to 10% for larger models, suggesting a complementary relationship where thinking budget provides greater relative benefits for capacity-constrained models. Domain-specific patterns emerge clearly, with neurology and gastroenterology requiring significantly deeper reasoning processes than cardiovascular or respiratory medicine. The consistency between Qwen3 native thinking budget API and our proposed truncation method for DeepSeek-R1 validates the generalizability of thinking budget concepts across architectures. These results establish thinking budget control as a critical mechanism for optimizing medical AI systems, enabling dynamic resource allocation aligned with clinical needs while maintaining the transparency essential for healthcare deployment.

Bin Huang, Kang Chen, Bingxuan Li et al.

Building large-scale foundation model for PET imaging is hindered by limited access to labeled data and insufficient computational resources. To overcome data scarcity and efficiency limitations, we propose ALL-PET, a low-resource, low-shot PET foundation model operating directly in projection domain. ALL-PET leverages a latent diffusion model (LDM) with three key innovations. First, we design a Radon mask augmentation strategy (RMAS) that generates over 200,000 structurally diverse training samples by projecting randomized image-domain masks into sinogram space, significantly improving generalization with minimal data. This is extended by a dynamic multi-mask (DMM) mechanism that varies mask quantity and distribution, enhancing data diversity without added model complexity. Second, we implement positive/negative mask constraints to embed strict geometric consistency, reducing parameter burden while preserving generation quality. Third, we introduce transparent medical attention (TMA), a parameter-free, geometry-driven mechanism that enhances lesion-related regions in raw projection data. Lesion-focused attention maps are derived from coarse segmentation, covering both hypermetabolic and hypometabolic areas, and projected into sinogram space for physically consistent guidance. The system supports clinician-defined ROI adjustments, ensuring flexible, interpretable, and task-adaptive emphasis aligned with PET acquisition physics. Experimental results show that ALL-PET achieves high-quality sinogram generation using only 500 samples, with performance comparable to models trained on larger datasets. ALL-PET generalizes across tasks including low-dose reconstruction, attenuation correction, delayed-frame prediction, and tracer separation, operating efficiently with memory use under 24GB.

Han Wang, Ruoyun He, Guoguang Lao et al.

Early identification of high-risk ICU patients is crucial for directing limited medical resources. We introduce ALFIA (Adaptive Layer Fusion with Intelligent Attention), a modular, attention-based architecture that jointly trains LoRA (Low-Rank Adaptation) adapters and an adaptive layer-weighting mechanism to fuse multi-layer semantic features from a BERT backbone. Trained on our rigorous cw-24 (CriticalWindow-24) benchmark, ALFIA surpasses state-of-the-art tabular classifiers in AUPRC while preserving a balanced precision-recall profile. The embeddings produced by ALFIA's fusion module, capturing both fine-grained clinical cues and high-level concepts, enable seamless pairing with GBDTs (CatBoost/LightGBM) as ALFIA-boost, and deep neuro networks as ALFIA-nn, yielding additional performance gains. Our experiments confirm ALFIA's superior early-warning performance, by operating directly on routine clinical text, it furnishes clinicians with a convenient yet robust tool for risk stratification and timely intervention in critical-care settings.

Jie Sun, Qian Xia, Chuanfu Sun et al.

Dynamic positron emission tomography (PET) images can reveal the distribution of tracers in the organism and the dynamic processes involved in biochemical reactions, and it is widely used in clinical practice. Despite the high effectiveness of dynamic PET imaging in studying the kinetics and metabolic processes of radiotracers. Pro-longed scan times can cause discomfort for both patients and medical personnel. This study proposes a dynamic frame prediction method for dynamic PET imaging, reduc-ing dynamic PET scanning time by applying a multi-module deep learning framework composed of reversible and irreversible modules. The network can predict kinetic parameter images based on the early frames of dynamic PET images, and then generate complete dynamic PET images. In validation experiments with simulated data, our network demonstrated good predictive performance for kinetic parameters and was able to reconstruct high-quality dynamic PET images. Additionally, in clinical data experiments, the network exhibited good generalization performance and attached that the proposed method has promising clinical application prospects.

Yubo Ye, Sumeet Vadhavkar, Xiajun Jiang et al.

Modern applications increasingly require unsupervised learning of latent dynamics from high-dimensional time-series. This presents a significant challenge of identifiability: many abstract latent representations may reconstruct observations, yet do they guarantee an adequate identification of the governing dynamics? This paper investigates this challenge from two angles: the use of physics inductive bias specific to the data being modeled, and a learn-to-identify strategy that separates forecasting objectives from the data used for the identification. We combine these two strategies in a novel framework for unsupervised meta-learning of hybrid latent dynamics (Meta-HyLaD) with: 1) a latent dynamic function that hybridize known mathematical expressions of prior physics with neural functions describing its unknown errors, and 2) a meta-learning formulation to learn to separately identify both components of the hybrid dynamics. Through extensive experiments on five physics and one biomedical systems, we provide strong evidence for the benefits of Meta-HyLaD to integrate rich prior knowledge while identifying their gap to observed data.

Huafeng Liu, Chuanyi Zhang, Yazhou Yao et al.

Labeling objects at a subordinate level typically requires expert knowledge, which is not always available when using random annotators. As such, learning directly from web images for fine-grained recognition has attracted broad attention. However, the presence of label noise and hard examples in web images are two obstacles for training robust fine-grained recognition models. Therefore, in this paper, we propose a novel approach for removing irrelevant samples from real-world web images during training, while employing useful hard examples to update the network. Thus, our approach can alleviate the harmful effects of irrelevant noisy web images and hard examples to achieve better performance. Extensive experiments on three commonly used fine-grained datasets demonstrate that our approach is far superior to current state-of-the-art web-supervised methods.

Jianan Cui, Kuang Gong, Paul Han et al.

Arterial spin labeling (ASL) magnetic resonance imaging (MRI) is a powerful imaging technology that can measure cerebral blood flow (CBF) quantitatively. However, since only a small portion of blood is labeled compared to the whole tissue volume, conventional ASL suffers from low signal-to-noise ratio (SNR), poor spatial resolution, and long acquisition time. In this paper, we proposed a super-resolution method based on a multi-scale generative adversarial network (GAN) through unsupervised training. The network only needs the low-resolution (LR) ASL image itself for training and the T1-weighted image as the anatomical prior. No training pairs or pre-training are needed. A low-pass filter guided item was added as an additional loss to suppress the noise interference from the LR ASL image. After the network was trained, the super-resolution (SR) image was generated by supplying the upsampled LR ASL image and corresponding T1-weighted image to the generator of the last layer. Performance of the proposed method was evaluated by comparing the peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) using normal-resolution (NR) ASL image (5.5 min acquisition) and high-resolution (HR) ASL image (44 min acquisition) as the ground truth. Compared to the nearest, linear, and spline interpolation methods, the proposed method recovers more detailed structure information, reduces the image noise visually, and achieves the highest PSNR and SSIM when using HR ASL image as the ground-truth.

Nuobei Xie, Kuang Gong, Ning Guo et al.

Patlak model is widely used in 18F-FDG dynamic positron emission tomography (PET) imaging, where the estimated parametric images reveal important biochemical and physiology information. Because of better noise modeling and more information extracted from raw sinogram, direct Patlak reconstruction gains its popularity over the indirect approach which utilizes reconstructed dynamic PET images alone. As the prerequisite of direct Patlak methods, raw data from dynamic PET are rarely stored in clinics and difficult to obtain. In addition, the direct reconstruction is time-consuming due to the bottleneck of multiple-frame reconstruction. All of these impede the clinical adoption of direct Patlak reconstruction.In this work, we proposed a data-driven framework which maps the dynamic PET images to the high-quality motion-corrected direct Patlak images through a convolutional neural network. For the patient motion during the long period of dynamic PET scan, we combined the correction with the backward/forward projection in direct reconstruction to better fit the statistical model. Results based on fifteen clinical 18F-FDG dynamic brain PET datasets demonstrates the superiority of the proposed framework over Gaussian, nonlocal mean and BM4D denoising, regarding the image bias and contrast-to-noise ratio.

Nuobei Xie, Kuang Gong, Ning Guo et al.

Positron emission tomography (PET) is widely used for clinical diagnosis. As PET suffers from low resolution and high noise, numerous efforts try to incorporate anatomical priors into PET image reconstruction, especially with the development of hybrid PET/CT and PET/MRI systems. In this work, we proposed a novel 3D structural convolutional sparse coding (CSC) concept for penalized-likelihood PET image reconstruction, named 3D PET-CSC. The proposed 3D PET-CSC takes advantage of the convolutional operation and manages to incorporate anatomical priors without the need of registration or supervised training. As 3D PET-CSC codes the whole 3D PET image, instead of patches, it alleviates the staircase artifacts commonly presented in traditional patch-based sparse coding methods. Moreover, we developed the residual-image and order-subset mechanisms to further reduce the computational cost and accelerate the convergence for the proposed 3D PET-CSC method. Experiments based on computer simulations and clinical datasets demonstrate the superiority of 3D PET-CSC compared with other reference methods.

Ming Li, Weiwei Zhang, Guang Yang et al.

Multi-view echocardiographic sequences segmentation is crucial for clinical diagnosis. However, this task is challenging due to limited labeled data, huge noise, and large gaps across views. Here we propose a recurrent aggregation learning method to tackle this challenging task. By pyramid ConvBlocks, multi-level and multi-scale features are extracted efficiently. Hierarchical ConvLSTMs next fuse these features and capture spatial-temporal information in multi-level and multi-scale space. We further introduce a double-branch aggregation mechanism for segmentation and classification which are mutually promoted by deep aggregation of multi-level and multi-scale features. The segmentation branch provides information to guide the classification while the classification branch affords multi-view regularization to refine segmentations and further lessen gaps across views. Our method is built as an end-to-end framework for segmentation and classification. Adequate experiments on our multi-view dataset (9000 labeled images) and the CAMUS dataset (1800 labeled images) corroborate that our method achieves not only superior segmentation and classification accuracy but also prominent temporal stability.

Huafeng Liu, Xiaofeng Han, Xiangrui Li et al.

Robust road detection is a key challenge in safe autonomous driving. Recently, with the rapid development of 3D sensors, more and more researchers are trying to fuse information across different sensors to improve the performance of road detection. Although many successful works have been achieved in this field, methods for data fusion under deep learning framework is still an open problem. In this paper, we propose a Siamese deep neural network based on FCN-8s to detect road region. Our method uses data collected from a monocular color camera and a Velodyne-64 LiDAR sensor. We project the LiDAR point clouds onto the image plane to generate LiDAR images and feed them into one of the branches of the network. The RGB images are fed into another branch of our proposed network. The feature maps that these two branches extract in multiple scales are fused before each pooling layer, via padding additional fusion layers. Extensive experimental results on public dataset KITTI ROAD demonstrate the effectiveness of our proposed approach.

Huafeng Liu, Yazhou Yao, Zeren Sun et al.

Robust road segmentation is a key challenge in self-driving research. Though many image-based methods have been studied and high performances in dataset evaluations have been reported, developing robust and reliable road segmentation is still a major challenge. Data fusion across different sensors to improve the performance of road segmentation is widely considered an important and irreplaceable solution. In this paper, we propose a novel structure to fuse image and LiDAR point cloud in an end-to-end semantic segmentation network, in which the fusion is performed at decoder stage instead of at, more commonly, encoder stage. During fusion, we improve the multi-scale LiDAR map generation to increase the precision of the multi-scale LiDAR map by introducing pyramid projection method. Additionally, we adapted the multi-path refinement network with our fusion strategy and improve the road prediction compared with transpose convolution with skip layers. Our approach has been tested on KITTI ROAD dataset and has competitive performance.