Jie Zhao

Jie Zhao, Jingshu Zhang, Dongdong Li et al.

Unmanned aerial vehicles (UAV) have been widely used in various fields, and their invasion of security and privacy has aroused social concern. Several detection and tracking systems for UAVs have been introduced in recent years, but most of them are based on radio frequency, radar, and other media. We assume that the field of computer vision is mature enough to detect and track invading UAVs. Thus we propose a visible light mode dataset called Dalian University of Technology Anti-UAV dataset, DUT Anti-UAV for short. It contains a detection dataset with a total of 10,000 images and a tracking dataset with 20 videos that include short-term and long-term sequences. All frames and images are manually annotated precisely. We use this dataset to train several existing detection algorithms and evaluate the algorithms' performance. Several tracking methods are also tested on our tracking dataset. Furthermore, we propose a clear and simple tracking algorithm combined with detection that inherits the detector's high precision. Extensive experiments show that the tracking performance is improved considerably after fusing detection, thus providing a new attempt at UAV tracking using our dataset.The datasets and results are publicly available at: https://github.com/wangdongdut/DUT-Anti-UAV

Pengyu Zhang, Jie Zhao, Dong Wang et al.

With the popularity of multi-modal sensors, visible-thermal (RGB-T) object tracking is to achieve robust performance and wider application scenarios with the guidance of objects' temperature information. However, the lack of paired training samples is the main bottleneck for unlocking the power of RGB-T tracking. Since it is laborious to collect high-quality RGB-T sequences, recent benchmarks only provide test sequences. In this paper, we construct a large-scale benchmark with high diversity for visible-thermal UAV tracking (VTUAV), including 500 sequences with 1.7 million high-resolution (1920 $\times$ 1080 pixels) frame pairs. In addition, comprehensive applications (short-term tracking, long-term tracking and segmentation mask prediction) with diverse categories and scenes are considered for exhaustive evaluation. Moreover, we provide a coarse-to-fine attribute annotation, where frame-level attributes are provided to exploit the potential of challenge-specific trackers. In addition, we design a new RGB-T baseline, named Hierarchical Multi-modal Fusion Tracker (HMFT), which fuses RGB-T data in various levels. Numerous experiments on several datasets are conducted to reveal the effectiveness of HMFT and the complement of different fusion types. The project is available at here.

Hexin Dong, Zifan Chen, Mingze Yuan et al.

As one of the most challenging and practical segmentation tasks, open-world semantic segmentation requires the model to segment the anomaly regions in the images and incrementally learn to segment out-of-distribution (OOD) objects, especially under a few-shot condition. The current state-of-the-art (SOTA) method, Deep Metric Learning Network (DMLNet), relies on pixel-level metric learning, with which the identification of similar regions having different semantics is difficult. Therefore, we propose a method called region-aware metric learning (RAML), which first separates the regions of the images and generates region-aware features for further metric learning. RAML improves the integrity of the segmented anomaly regions. Moreover, we propose a novel meta-channel aggregation (MCA) module to further separate anomaly regions, forming high-quality sub-region candidates and thereby improving the model performance for OOD objects. To evaluate the proposed RAML, we have conducted extensive experiments and ablation studies on Lost And Found and Road Anomaly datasets for anomaly segmentation and the CityScapes dataset for incremental few-shot learning. The results show that the proposed RAML achieves SOTA performance in both stages of open world segmentation. Our code and appendix are available at https://github.com/czifan/RAML.

Zifan Chen, Jie Zhao, Hao Yu et al.

Accurate and efficient lumbar spine disease identification is crucial for clinical diagnosis. However, existing deep learning models with millions of parameters often fail to learn with only hundreds or dozens of medical images. These models also ignore the contextual relationship between adjacent objects, such as between vertebras and intervertebral discs. This work introduces a multi-scale context-guided network with coarse-to-fine localization and classification, named CCF-Net, for lumbar spine disease identification. Specifically, in learning, we divide the localization objective into two parallel tasks, coarse and fine, which are more straightforward and effectively reduce the number of parameters and computational cost. The experimental results show that the coarse-to-fine design presents the potential to achieve high performance with fewer parameters and data requirements. Moreover, the multi-scale context-guided module can significantly improve the performance by 6.45% and 5.51% with ResNet18 and ResNet50, respectively. Our code is available at https://github.com/czifan/CCFNet.pytorch.

Zhiyu Chen, Jie Zhao, Anjie Fang et al.

Conversational Question Answering (CQA) aims to answer questions contained within dialogues, which are not easily interpretable without context. Developing a model to rewrite conversational questions into self-contained ones is an emerging solution in industry settings as it allows using existing single-turn QA systems to avoid training a CQA model from scratch. Previous work trains rewriting models using human rewrites as supervision. However, such objectives are disconnected with QA models and therefore more human-like rewrites do not guarantee better QA performance. In this paper we propose using QA feedback to supervise the rewriting model with reinforcement learning. Experiments show that our approach can effectively improve QA performance over baselines for both extractive and retrieval QA. Furthermore, human evaluation shows that our method can generate more accurate and detailed rewrites when compared to human annotations.

Jie Zhao, Ziyu Guan, Wei Zhao et al.

Recent works considering professional legal-linguistic style (PLLS) texts have shown promising results on the charge prediction task. However, unprofessional users also show an increasing demand on such a prediction service. There is a clear domain discrepancy between PLLS texts and non-PLLS texts expressed by those laypersons, which degrades the current SOTA models' performance on non-PLLS texts. A key challenge is the scarcity of non-PLLS data for most charge classes. This paper proposes a novel few-shot domain adaptation (FSDA) method named Disentangled Legal Content for Charge Prediction (DLCCP). Compared with existing FSDA works, which solely perform instance-level alignment without considering the negative impact of text style information existing in latent features, DLCCP (1) disentangles the content and style representations for better domain-invariant legal content learning with carefully designed optimization goals for content and style spaces and, (2) employs the constitutive elements knowledge of charges to extract and align element-level and instance-level content representations simultaneously. We contribute the first publicly available non-PLLS dataset named NCCP for developing layperson-friendly charge prediction models. Experiments on NCCP show the superiority of our methods over competitive baselines.

Gao-Dong Liu, Wan-Lei Zhao, Jie Zhao

Deep metric learning aims to transform input data into an embedding space, where similar samples are close while dissimilar samples are far apart from each other. In practice, samples of new categories arrive incrementally, which requires the periodical augmentation of the learned model. The fine-tuning on the new categories usually leads to poor performance on the old, which is known as "catastrophic forgetting". Existing solutions either retrain the model from scratch or require the replay of old samples during the training. In this paper, a complete online deep metric learning framework is proposed based on mutual distillation for both one-task and multi-task scenarios. Different from the teacher-student framework, the proposed approach treats the old and new learning tasks with equal importance. No preference over the old or new knowledge is caused. In addition, a novel virtual feature estimation approach is proposed to recover the features assumed to be extracted by the old models. It allows the distillation between the new and the old models without the replay of old training samples or the holding of old models during the training. A comprehensive study shows the superior performance of our approach with the support of different backbones.

Zifan Chen, Xinyu Nan, Jiazheng Li et al.

Volumetric segmentation is important in medical imaging, but current methods face challenges like requiring lots of manual annotations and being tailored to specific tasks, which limits their versatility. General segmentation models used for natural images don't perform well with the unique features of medical images. There's a strong need for an adaptable approach that can effectively handle different 3D medical structures and imaging modalities. In this study, we present PAM (Propagating Anything Model), a segmentation approach that uses a 2D prompt, like a bounding box or sketch, to create a complete 3D segmentation of medical image volumes. PAM works by modeling relationships between slices, maintaining information flow across the 3D structure. It combines a CNN-based UNet for processing within slices and a Transformer-based attention module for propagating information between slices, leading to better generalizability across various imaging modalities. PAM significantly outperformed existing models like MedSAM and SegVol, with an average improvement of over 18.1% in dice similarity coefficient (DSC) across 44 medical datasets and various object types. It also showed stable performance despite prompt deviations and different propagation setups, and faster inference speeds compared to other models. PAM's one-view prompt design made it more efficient, reducing interaction time by about 63.6% compared to two-view prompts. Thanks to its focus on structural relationships, PAM handled unseen and complex objects well, showing a unique ability to generalize to new situations. PAM represents an advancement in medical image segmentation, effectively reducing the need for extensive manual work and specialized training. Its adaptability makes it a promising tool for more automated and reliable analysis in clinical settings.

Wei Chen, Jie Zhao, Wan-Lei Zhao et al.

The detection of 3D objects through a single perspective camera is a challenging issue. The anchor-free and keypoint-based models receive increasing attention recently due to their effectiveness and simplicity. However, most of these methods are vulnerable to occluded and truncated objects. In this paper, a single-stage monocular 3D object detection model is proposed. An instance-segmentation head is integrated into the model training, which allows the model to be aware of the visible shape of a target object. The detection largely avoids interference from irrelevant regions surrounding the target objects. In addition, we also reveal that the popular IoU-based evaluation metrics, which were originally designed for evaluating stereo or LiDAR-based detection methods, are insensitive to the improvement of monocular 3D object detection algorithms. A novel evaluation metric, namely average depth similarity (ADS) is proposed for the monocular 3D object detection models. Our method outperforms the baseline on both the popular and the proposed evaluation metrics while maintaining real-time efficiency.

Yan Gong, Jianli Lu, Yongsheng Gao et al.

Indoor semantic segmentation is fundamental to computer vision and robotics, supporting applications such as autonomous navigation, augmented reality, and smart environments. Although RGB-D fusion leverages complementary appearance and geometric cues, existing methods often depend on computationally intensive cross-attention mechanisms and insufficiently model intra- and inter-modal feature relationships, resulting in imprecise feature alignment and limited discriminative representation. To address these challenges, we propose DiffPixelFormer, a differential pixel-aware Transformer for RGB-D indoor scene segmentation that simultaneously enhances intra-modal representations and models inter-modal interactions. At its core, the Intra-Inter Modal Interaction Block (IIMIB) captures intra-modal long-range dependencies via self-attention and models inter-modal interactions with the Differential-Shared Inter-Modal (DSIM) module to disentangle modality-specific and shared cues, enabling fine-grained, pixel-level cross-modal alignment. Furthermore, a dynamic fusion strategy balances modality contributions and fully exploits RGB-D information according to scene characteristics. Extensive experiments on the SUN RGB-D and NYUDv2 benchmarks demonstrate that DiffPixelFormer-L achieves mIoU scores of 54.28% and 59.95%, outperforming DFormer-L by 1.78% and 2.75%, respectively. Code is available at https://github.com/gongyan1/DiffPixelFormer.

Jie Zhao, Ziyu Guan, Cai Xu et al.

Text style transfer (TST) aims to vary the style polarity of text while preserving the semantic content. Although recent advancements have demonstrated remarkable progress in short TST, it remains a relatively straightforward task with limited practical applications. The more comprehensive long TST task presents two challenges: (1) existing methods encounter difficulties in accurately evaluating content attributes in multiple words, leading to content degradation; (2) the conventional vanilla style classifier loss encounters obstacles in maintaining consistent style across multiple generated sentences. In this paper, we propose a novel method SC2, where a multilayer Joint Style-Content Weighed (JSCW) module and a Style Consistency loss are designed to address the two issues. The JSCW simultaneously assesses the amounts of style and content attributes within a token, aiming to acquire a lossless content representation and thereby enhancing content preservation. The multiple JSCW layers further progressively refine content representations. We design a style consistency loss to ensure the generated multiple sentences consistently reflect the target style polarity. Moreover, we incorporate a denoising non-autoregressive decoder to accelerate the training. We conduct plentiful experiments and the results show significant improvements of SC2 over competitive baselines. Our code: https://github.com/jiezhao6/SC2.

Ben Kang, Xin Chen, Jie Zhao et al.

Transformer-based visual trackers have demonstrated significant advancements due to their powerful modeling capabilities. However, their practicality is limited on resource-constrained devices because of their slow processing speeds. To address this challenge, we present HiT, a novel family of efficient tracking models that achieve high performance while maintaining fast operation across various devices. The core innovation of HiT lies in its Bridge Module, which connects lightweight transformers to the tracking framework, enhancing feature representation quality. Additionally, we introduce a dual-image position encoding approach to effectively encode spatial information. HiT achieves an impressive speed of 61 frames per second (fps) on the NVIDIA Jetson AGX platform, alongside a competitive AUC of 64.6% on the LaSOT benchmark, outperforming all previous efficient trackers.Building on HiT, we propose DyHiT, an efficient dynamic tracker that flexibly adapts to scene complexity by selecting routes with varying computational requirements. DyHiT uses search area features extracted by the backbone network and inputs them into an efficient dynamic router to classify tracking scenarios. Based on the classification, DyHiT applies a divide-and-conquer strategy, selecting appropriate routes to achieve a superior trade-off between accuracy and speed. The fastest version of DyHiT achieves 111 fps on NVIDIA Jetson AGX while maintaining an AUC of 62.4% on LaSOT.Furthermore, we introduce a training-free acceleration method based on the dynamic routing architecture of DyHiT. This method significantly improves the execution speed of various high-performance trackers without sacrificing accuracy. For instance, our acceleration method enables the state-of-the-art tracker SeqTrack-B256 to achieve a 2.68 times speedup on an NVIDIA GeForce RTX 2080 Ti GPU while maintaining the same AUC of 69.9% on the LaSOT.

Jie Zhao, Zhitong Xiong, Xiao Xiang Zhu

Due to its cloud-penetrating capability and independence from solar illumination, satellite Synthetic Aperture Radar (SAR) is the preferred data source for large-scale flood mapping, providing global coverage and including various land cover classes. However, most studies on large-scale SAR-derived flood mapping using deep learning algorithms have primarily focused on flooded open areas, utilizing available open-access datasets (e.g., Sen1Floods11) and with limited attention to urban floods. To address this gap, we introduce \textbf{UrbanSARFloods}, a floodwater dataset featuring pre-processed Sentinel-1 intensity data and interferometric coherence imagery acquired before and during flood events. It contains 8,879 $512\times 512$ chips covering 807,500 $km^2$ across 20 land cover classes and 5 continents, spanning 18 flood events. We used UrbanSARFloods to benchmark existing state-of-the-art convolutional neural networks (CNNs) for segmenting open and urban flood areas. Our findings indicate that prevalent approaches, including the Weighted Cross-Entropy (WCE) loss and the application of transfer learning with pretrained models, fall short in overcoming the obstacles posed by imbalanced data and the constraints of a small training dataset. Urban flood detection remains challenging. Future research should explore strategies for addressing imbalanced data challenges and investigate transfer learning's potential for SAR-based large-scale flood mapping. Besides, expanding this dataset to include additional flood events holds promise for enhancing its utility and contributing to advancements in flood mapping techniques.

Qinglu Min, Jie Zhao, Zhihao Zhang et al.

Deep learning has recently demonstrated its excellent performance on the task of multi-view stereo (MVS). However, loss functions applied for deep MVS are rarely studied. In this paper, we first analyze existing loss functions' properties for deep depth based MVS approaches. Regression based loss leads to inaccurate continuous results by computing mathematical expectation, while classification based loss outputs discretized depth values. To this end, we then propose a novel loss function, named adaptive Wasserstein loss, which is able to narrow down the difference between the true and predicted probability distributions of depth. Besides, a simple but effective offset module is introduced to better achieve sub-pixel prediction accuracy. Extensive experiments on different benchmarks, including DTU, Tanks and Temples and BlendedMVS, show that the proposed method with the adaptive Wasserstein loss and the offset module achieves state-of-the-art performance.

Zifan Chen, Jiazheng Li, Jie Zhao et al.

**Background:** Accurate 3D CT scan segmentation of gastric tumors is pivotal for diagnosis and treatment. The challenges lie in the irregular shapes, blurred boundaries of tumors, and the inefficiency of existing methods. **Purpose:** We conducted a study to introduce a model, utilizing human-guided knowledge and unique modules, to address the challenges of 3D tumor segmentation. **Methods:** We developed the PropNet framework, propagating radiologists' knowledge from 2D annotations to the entire 3D space. This model consists of a proposing stage for coarse segmentation and a refining stage for improved segmentation, using two-way branches for enhanced performance and an up-down strategy for efficiency. **Results:** With 98 patient scans for training and 30 for validation, our method achieves a significant agreement with manual annotation (Dice of 0.803) and improves efficiency. The performance is comparable in different scenarios and with various radiologists' annotations (Dice between 0.785 and 0.803). Moreover, the model shows improved prognostic prediction performance (C-index of 0.620 vs. 0.576) on an independent validation set of 42 patients with advanced gastric cancer. **Conclusions:** Our model generates accurate tumor segmentation efficiently and stably, improving prognostic performance and reducing high-throughput image reading workload. This model can accelerate the quantitative analysis of gastric tumors and enhance downstream task performance.

Ruiqi Sun, Siwei Ye, Jie Zhao et al.

The inherent diversity of computation types within the deep neural network (DNN) models often requires a variety of specialized units in hardware processors, which limits computational efficiency, increasing both inference latency and power consumption, especially when the hardware processor needs to support and execute different neural networks. In this study, we introduce NeuralMatrix, which elastically transforms the computations of entire DNNs into linear matrix operations. This transformation allows seamless execution of various DNN models all with matrix operations and paves the way for running versatile DNN models with a single General Matrix Multiplication (GEMM) accelerator.Extensive experiments with both CNN and transformer-based models demonstrate the potential of NeuralMatrix to accurately and efficiently execute a wide range of DNN models, achieving 2.17-38.72 times computation efficiency (i.e., throughput per power) compared to CPUs, GPUs, and SoC platforms. This level of efficiency is usually only attainable with the accelerator designed for a specific neural network.

Chunyuan Zhang, Chao Liu, Qi Song et al.

The echo state network (ESN) is a special type of recurrent neural networks for processing the time-series dataset. However, limited by the strong correlation among sequential samples of the agent, ESN-based policy control algorithms are difficult to use the recursive least squares (RLS) algorithm to update the ESN's parameters. To solve this problem, we propose two novel policy control algorithms, ESNRLS-Q and ESNRLS-Sarsa. Firstly, to reduce the correlation of training samples, we use the leaky integrator ESN and the mini-batch learning mode. Secondly, to make RLS suitable for training ESN in mini-batch mode, we present a new mean-approximation method for updating the RLS correlation matrix. Thirdly, to prevent ESN from over-fitting, we use the L1 regularization technique. Lastly, to prevent the target state-action value from overestimation, we employ the Mellowmax method. Simulation results show that our algorithms have good convergence performance.

Hexin Dong, Fei Yu, Jie Zhao et al.

This paper proposes an unsupervised cross-modality domain adaptation approach based on pixel alignment and self-training. Pixel alignment transfers ceT1 scans to hrT2 modality, helping to reduce domain shift in the training segmentation model. Self-training adapts the decision boundary of the segmentation network to fit the distribution of hrT2 scans. Experiment results show that PAST has outperformed the non-UDA baseline significantly, and it received rank-2 on CrossMoDA validation phase Leaderboard with a mean Dice score of 0.8395.

Mo Zhang, Fei Yu, Jie Zhao et al.

Blood vessel segmentation is crucial for many diagnostic and research applications. In recent years, CNN-based models have leaded to breakthroughs in the task of segmentation, however, such methods usually lose high-frequency information like object boundaries and subtle structures, which are vital to vessel segmentation. To tackle this issue, we propose Boundary Enhancement and Feature Denoising (BEFD) module to facilitate the network ability of extracting boundary information in semantic segmentation, which can be integrated into arbitrary encoder-decoder architecture in an end-to-end way. By introducing Sobel edge detector, the network is able to acquire additional edge prior, thus enhancing boundary in an unsupervised manner for medical image segmentation. In addition, we also utilize a denoising block to reduce the noise hidden in the low-level features. Experimental results on retinal vessel dataset and angiocarpy dataset demonstrate the superior performance of the new BEFD module.

Jie Zhao, Lei Dai, Mo Zhang et al.

Automated cervical nucleus segmentation based on deep learning can effectively improve the quantitative analysis of cervical cancer. However, accurate nuclei segmentation is still challenging. The classic U-net has not achieved satisfactory results on this task, because it mixes the information of different scales that affect each other, which limits the segmentation accuracy of the model. To solve this problem, we propose a progressive growing U-net (PGU-net+) model, which uses two paradigms to extract image features at different scales in a more independent way. First, we add residual modules between different scales of U-net, which enforces the model to learn the approximate shape of the annotation in the coarser scale, and to learn the residual between the annotation and the approximate shape in the finer scale. Second, we start to train the model with the coarsest part and then progressively add finer part to the training until the full model is included. When we train a finer part, we will reduce the learning rate of the previous coarser part, which further ensures that the model independently extracts information from different scales. We conduct several comparative experiments on the Herlev dataset. The experimental results show that the PGU-net+ has superior accuracy than the previous state-of-the-art methods on cervical nuclei segmentation.

Jie Zhao, Xin Jiang, Xiaoman Wang et al.

In industry assembly lines, parts feeding machines are widely employed as the prologue of the whole procedure. They play the role of sorting the parts randomly placed in bins to the state with specified pose. With the help of the parts feeding machines, the subsequent assembly processes by robot arm can always start from the same condition. Thus it is expected that function of parting feeding machine and the robotic assembly can be integrated with one robot arm. This scheme can provide great flexibility and can also contribute to reduce the cost. The difficulties involved in this scheme lie in the fact that in the part feeding phase, the pose of the part after grasping may be not proper for the subsequent assembly. Sometimes it can not even guarantee a stable grasp. In this paper, we proposed a method to integrate parts feeding and assembly within one robot arm. This proposal utilizes a specially designed gripper tip mounted on the jaws of a two-fingered gripper. With the modified gripper, in-hand manipulation of the grasped object is realized, which can ensure the control of the orientation and offset position of the grasped object. The proposal in this paper is verified by a simulated assembly in which a robot arm completed the assembly process including parts picking from bin and a subsequent peg-in-hole assembly.

Fei Yu, Jie Zhao, Yanjun Gong et al.

Segmenting coronary arteries is challenging, as classic unsupervised methods fail to produce satisfactory results and modern supervised learning (deep learning) requires manual annotation which is often time-consuming and can some time be infeasible. To solve this problem, we propose a knowledge transfer based shape-consistent generative adversarial network (SC-GAN), which is an annotation-free approach that uses the knowledge from publicly available annotated fundus dataset to segment coronary arteries. The proposed network is trained in an end-to-end fashion, generating and segmenting synthetic images that maintain the background of coronary angiography and preserve the vascular structures of retinal vessels and coronary arteries. We train and evaluate the proposed model on a dataset of 1092 digital subtraction angiography images, and experiments demonstrate the supreme accuracy of the proposed method on coronary arteries segmentation.

Mo Zhang, Jie Zhao, Xiang Li et al.

Extracting multi-scale information is key to semantic segmentation. However, the classic convolutional neural networks (CNNs) encounter difficulties in achieving multi-scale information extraction: expanding convolutional kernel incurs the high computational cost and using maximum pooling sacrifices image information. The recently developed dilated convolution solves these problems, but with the limitation that the dilation rates are fixed and therefore the receptive field cannot fit for all objects with different sizes in the image. We propose an adaptivescale convolutional neural network (ASCNet), which introduces a 3-layer convolution structure in the end-to-end training, to adaptively learn an appropriate dilation rate for each pixel in the image. Such pixel-level dilation rates produce optimal receptive fields so that the information of objects with different sizes can be extracted at the corresponding scale. We compare the segmentation results using the classic CNN, the dilated CNN and the proposed ASCNet on two types of medical images (The Herlev dataset and SCD RBC dataset). The experimental results show that ASCNet achieves the highest accuracy. Moreover, the automatically generated dilation rates are positively correlated to the sizes of the objects, confirming the effectiveness of the proposed method.

Wenjia Wang, Junxuan Chen, Jie Zhao et al.

The identification of pulmonary lobes is of great importance in disease diagnosis and treatment. A few lung diseases have regional disorders at lobar level. Thus, an accurate segmentation of pulmonary lobes is necessary. In this work, we propose an automated segmentation of pulmonary lobes using coordination-guided deep neural networks from chest CT images. We first employ an automated lung segmentation to extract the lung area from CT image, then exploit volumetric convolutional neural network (V-net) for segmenting the pulmonary lobes. To reduce the misclassification of different lobes, we therefore adopt coordination-guided convolutional layers (CoordConvs) that generate additional feature maps of the positional information of pulmonary lobes. The proposed model is trained and evaluated on a few publicly available datasets and has achieved the state-of-the-art accuracy with a mean Dice coefficient index of 0.947 $\pm$ 0.044.

Jie Zhao, Quanzheng Li, Xiang Li et al.

Pap smear testing has been widely used for detecting cervical cancers based on the morphology properties of cell nuclei in microscopic image. An accurate nuclei segmentation could thus improve the success rate of cervical cancer screening. In this work, a method of automated cervical nuclei segmentation using Deformable Multipath Ensemble Model (D-MEM) is proposed. The approach adopts a U-shaped convolutional network as a backbone network, in which dense blocks are used to transfer feature information more effectively. To increase the flexibility of the model, we then use deformable convolution to deal with different nuclei irregular shapes and sizes. To reduce the predictive bias, we further construct multiple networks with different settings, which form an ensemble model. The proposed segmentation framework has achieved state-of-the-art accuracy on Herlev dataset with Zijdenbos similarity index (ZSI) of 0.933, and has the potential to be extended for solving other medical image segmentation tasks.