Geng Chen

Geng Chen, Si-Jie Liu, Yu-Jia Sun et al.

Camouflaged object detection (COD) aims to identify the objects that conceal themselves in natural scenes. Accurate COD suffers from a number of challenges associated with low boundary contrast and the large variation of object appearances, e.g., object size and shape. To address these challenges, we propose a novel Context-aware Cross-level Fusion Network (C2F-Net), which fuses context-aware cross-level features for accurately identifying camouflaged objects. Specifically, we compute informative attention coefficients from multi-level features with our Attention-induced Cross-level Fusion Module (ACFM), which further integrates the features under the guidance of attention coefficients. We then propose a Dual-branch Global Context Module (DGCM) to refine the fused features for informative feature representations by exploiting rich global context information. Multiple ACFMs and DGCMs are integrated in a cascaded manner for generating a coarse prediction from high-level features. The coarse prediction acts as an attention map to refine the low-level features before passing them to our Camouflage Inference Module (CIM) to generate the final prediction. We perform extensive experiments on three widely used benchmark datasets and compare C2F-Net with state-of-the-art (SOTA) models. The results show that C2F-Net is an effective COD model and outperforms SOTA models remarkably. Further, an evaluation on polyp segmentation datasets demonstrates the promising potentials of our C2F-Net in COD downstream applications. Our code is publicly available at: https://github.com/Ben57882/C2FNet-TSCVT.

Tao Zhou, Yizhe Zhang, Geng Chen et al.

Precise polyp segmentation is vital for the early diagnosis and prevention of colorectal cancer (CRC) in clinical practice. However, due to scale variation and blurry polyp boundaries, it is still a challenging task to achieve satisfactory segmentation performance with different scales and shapes. In this study, we present a novel Edge-aware Feature Aggregation Network (EFA-Net) for polyp segmentation, which can fully make use of cross-level and multi-scale features to enhance the performance of polyp segmentation. Specifically, we first present an Edge-aware Guidance Module (EGM) to combine the low-level features with the high-level features to learn an edge-enhanced feature, which is incorporated into each decoder unit using a layer-by-layer strategy. Besides, a Scale-aware Convolution Module (SCM) is proposed to learn scale-aware features by using dilated convolutions with different ratios, in order to effectively deal with scale variation. Further, a Cross-level Fusion Module (CFM) is proposed to effectively integrate the cross-level features, which can exploit the local and global contextual information. Finally, the outputs of CFMs are adaptively weighted by using the learned edge-aware feature, which are then used to produce multiple side-out segmentation maps. Experimental results on five widely adopted colonoscopy datasets show that our EFA-Net outperforms state-of-the-art polyp segmentation methods in terms of generalization and effectiveness. Our implementation code and segmentation maps will be publicly at https://github.com/taozh2017/EFANet.

Ge-Peng Ji, Guobao Xiao, Yu-Cheng Chou et al.

We present the first comprehensive video polyp segmentation (VPS) study in the deep learning era. Over the years, developments in VPS are not moving forward with ease due to the lack of large-scale fine-grained segmentation annotations. To address this issue, we first introduce a high-quality frame-by-frame annotated VPS dataset, named SUN-SEG, which contains 158,690 colonoscopy frames from the well-known SUN-database. We provide additional annotations with diverse types, i.e., attribute, object mask, boundary, scribble, and polygon. Second, we design a simple but efficient baseline, dubbed PNS+, consisting of a global encoder, a local encoder, and normalized self-attention (NS) blocks. The global and local encoders receive an anchor frame and multiple successive frames to extract long-term and short-term spatial-temporal representations, which are then progressively updated by two NS blocks. Extensive experiments show that PNS+ achieves the best performance and real-time inference speed (170fps), making it a promising solution for the VPS task. Third, we extensively evaluate 13 representative polyp/object segmentation models on our SUN-SEG dataset and provide attribute-based comparisons. Finally, we discuss several open issues and suggest possible research directions for the VPS community.

Wentao Zhu, Yuan Jin, Gege Ma et al.

The accurate diagnosis on pathological subtypes for lung cancer is of significant importance for the follow-up treatments and prognosis managements. In this paper, we propose self-generating hybrid feature network (SGHF-Net) for accurately classifying lung cancer subtypes on computed tomography (CT) images. Inspired by studies stating that cross-scale associations exist in the image patterns between the same case's CT images and its pathological images, we innovatively developed a pathological feature synthetic module (PFSM), which quantitatively maps cross-modality associations through deep neural networks, to derive the "gold standard" information contained in the corresponding pathological images from CT images. Additionally, we designed a radiological feature extraction module (RFEM) to directly acquire CT image information and integrated it with the pathological priors under an effective feature fusion framework, enabling the entire classification model to generate more indicative and specific pathologically related features and eventually output more accurate predictions. The superiority of the proposed model lies in its ability to self-generate hybrid features that contain multi-modality image information based on a single-modality input. To evaluate the effectiveness, adaptability, and generalization ability of our model, we performed extensive experiments on a large-scale multi-center dataset (i.e., 829 cases from three hospitals) to compare our model and a series of state-of-the-art (SOTA) classification models. The experimental results demonstrated the superiority of our model for lung cancer subtypes classification with significant accuracy improvements in terms of accuracy (ACC), area under the curve (AUC), and F1 score.

Sijun Dong, Yuwei Zhu, Geng Chen et al.

With the widespread application of remote sensing technology in environmental monitoring, the demand for efficient and accurate remote sensing image change detection (CD) for natural environments is growing. We propose a novel deep learning framework named EfficientCD, specifically designed for remote sensing image change detection. The framework employs EfficientNet as its backbone network for feature extraction. To enhance the information exchange between bi-temporal image feature maps, we have designed a new Feature Pyramid Network module targeted at remote sensing change detection, named ChangeFPN. Additionally, to make full use of the multi-level feature maps in the decoding stage, we have developed a layer-by-layer feature upsampling module combined with Euclidean distance to improve feature fusion and reconstruction during the decoding stage. The EfficientCD has been experimentally validated on four remote sensing datasets: LEVIR-CD, SYSU-CD, CLCD, and WHUCD. The experimental results demonstrate that EfficientCD exhibits outstanding performance in change detection accuracy. The code and pretrained models will be released at https://github.com/dyzy41/mmrscd.

Geng Chen, Wendong Zhang, Han Lu et al.

Predictive learning ideally builds the world model of physical processes in one or more given environments. Typical setups assume that we can collect data from all environments at all times. In practice, however, different prediction tasks may arrive sequentially so that the environments may change persistently throughout the training procedure. Can we develop predictive learning algorithms that can deal with more realistic, non-stationary physical environments? In this paper, we study a new continual learning problem in the context of video prediction, and observe that most existing methods suffer from severe catastrophic forgetting in this setup. To tackle this problem, we propose the continual predictive learning (CPL) approach, which learns a mixture world model via predictive experience replay and performs test-time adaptation with non-parametric task inference. We construct two new benchmarks based on RoboNet and KTH, in which different tasks correspond to different physical robotic environments or human actions. Our approach is shown to effectively mitigate forgetting and remarkably outperform the naïve combinations of previous art in video prediction and continual learning.

Ryan Punamiya, Simar Kareer, Zeyi Liu et al.

Robot learning increasingly depends on large and diverse data, yet robot data collection remains expensive and difficult to scale. Egocentric human data offer a promising alternative by capturing rich manipulation behavior across everyday environments. However, existing human datasets are often limited in scope, difficult to extend, and fragmented across institutions. We introduce EgoVerse, a collaborative platform for human data-driven robot learning that unifies data collection, processing, and access under a shared framework, enabling contributions from individual researchers, academic labs, and industry partners. The current release includes 1,362 hours (80k episodes) of human demonstrations spanning 1,965 tasks, 240 scenes, and 2,087 unique demonstrators, with standardized formats, manipulation-relevant annotations, and tooling for downstream learning. Beyond the dataset, we conduct a large-scale study of human-to-robot transfer with experiments replicated across multiple labs, tasks, and robot embodiments under shared protocols. We find that policy performance generally improves with increased human data, but that effective scaling depends on alignment between human data and robot learning objectives. Together, the dataset, platform, and study establish a foundation for reproducible progress in human data-driven robot learning. Videos and additional information can be found at https://egoverse.ai/

Shijie Huang, Xukun Zhang, Zhiming Cui et al.

Accurate tissue segmentation of thick-slice fetal brain magnetic resonance (MR) scans is crucial for both reconstruction of isotropic brain MR volumes and the quantification of fetal brain development. However, this task is challenging due to the use of thick-slice scans in clinically-acquired fetal brain data. To address this issue, we propose to leverage high-quality isotropic fetal brain MR volumes (and also their corresponding annotations) as guidance for segmentation of thick-slice scans. Due to existence of significant domain gap between high-quality isotropic volume (i.e., source data) and thick-slice scans (i.e., target data), we employ a domain adaptation technique to achieve the associated knowledge transfer (from high-quality <source> volumes to thick-slice <target> scans). Specifically, we first register the available high-quality isotropic fetal brain MR volumes across different gestational weeks to construct longitudinally-complete source data. To capture domain-invariant information, we then perform Fourier decomposition to extract image content and style codes. Finally, we propose a novel Cycle-Consistent Domain Adaptation Network (C2DA-Net) to efficiently transfer the knowledge learned from high-quality isotropic volumes for accurate tissue segmentation of thick-slice scans. Our C2DA-Net can fully utilize a small set of annotated isotropic volumes to guide tissue segmentation on unannotated thick-slice scans. Extensive experiments on a large-scale dataset of 372 clinically acquired thick-slice MR scans demonstrate that our C2DA-Net achieves much better performance than cutting-edge methods quantitatively and qualitatively.

Yinghui Xing, Dexuan Kong, Shizhou Zhang et al.

Camouflaged object detection (COD), aiming to segment camouflaged objects which exhibit similar patterns with the background, is a challenging task. Most existing works are dedicated to establishing specialized modules to identify camouflaged objects with complete and fine details, while the boundary can not be well located for the lack of object-related semantics. In this paper, we propose a novel ``pre-train, adapt and detect" paradigm to detect camouflaged objects. By introducing a large pre-trained model, abundant knowledge learned from massive multi-modal data can be directly transferred to COD. A lightweight parallel adapter is inserted to adjust the features suitable for the downstream COD task. Extensive experiments on four challenging benchmark datasets demonstrate that our method outperforms existing state-of-the-art COD models by large margins. Moreover, we design a multi-task learning scheme for tuning the adapter to exploit the shareable knowledge across different semantic classes. Comprehensive experimental results showed that the generalization ability of our model can be substantially improved with multi-task adapter initialization on source tasks and multi-task adaptation on target tasks.

Minting Pan, Wendong Zhang, Geng Chen et al.

Learning physical dynamics in a series of non-stationary environments is a challenging but essential task for model-based reinforcement learning (MBRL) with visual inputs. It requires the agent to consistently adapt to novel tasks without forgetting previous knowledge. In this paper, we present a new continual learning approach for visual dynamics modeling and explore its efficacy in visual control. The key assumption is that an ideal world model can provide a non-forgetting environment simulator, which enables the agent to optimize the policy in a multi-task learning manner based on the imagined trajectories from the world model. To this end, we first introduce the life-long world model, which learns task-specific latent dynamics using a mixture of Gaussians and incorporates generative experience replay to mitigate catastrophic forgetting. Then, we further address the value estimation challenge for previous tasks with the exploratory-conservative behavior learning approach. Our model remarkably outperforms the straightforward combinations of existing continual learning and visual RL algorithms on DeepMind Control Suite and Meta-World benchmarks with continual visual control tasks.

Yuan Jin, Gege Ma, Geng Chen et al.

The accurate diagnosis of pathological subtypes of lung cancer is of paramount importance for follow-up treatments and prognosis managements. Assessment methods utilizing deep learning technologies have introduced novel approaches for clinical diagnosis. However, the majority of existing models rely solely on single-modality image input, leading to limited diagnostic accuracy. To this end, we propose a novel deep learning network designed to accurately classify lung cancer subtype with multi-dimensional and multi-modality images, i.e., CT and pathological images. The strength of the proposed model lies in its ability to dynamically process both paired CT-pathological image sets as well as independent CT image sets, and consequently optimize the pathology-related feature extractions from CT images. This adaptive learning approach enhances the flexibility in processing multi-dimensional and multi-modality datasets and results in performance elevating in the model testing phase. We also develop a contrastive constraint module, which quantitatively maps the cross-modality associations through network training, and thereby helps to explore the "gold standard" pathological information from the corresponding CT scans. To evaluate the effectiveness, adaptability, and generalization ability of our model, we conducted extensive experiments on a large-scale multi-center dataset and compared our model with a series of state-of-the-art classification models. The experimental results demonstrated the superiority of our model for lung cancer subtype classification, showcasing significant improvements in accuracy metrics such as ACC, AUC, and F1-score.

Yanqing Kang, Di Zhu, Haiyang Zhang et al.

Studying influential nodes (I-nodes) in brain networks is of great significance in the field of brain imaging. Most existing studies consider brain connectivity hubs as I-nodes. However, this approach relies heavily on prior knowledge from graph theory, which may overlook the intrinsic characteristics of the brain network, especially when its architecture is not fully understood. In contrast, self-supervised deep learning can learn meaningful representations directly from the data. This approach enables the exploration of I-nodes for brain networks, which is also lacking in current studies. This paper proposes a Self-Supervised Graph Reconstruction framework based on Graph-Transformer (SSGR-GT) to identify I-nodes, which has three main characteristics. First, as a self-supervised model, SSGR-GT extracts the importance of brain nodes to the reconstruction. Second, SSGR-GT uses Graph-Transformer, which is well-suited for extracting features from brain graphs, combining both local and global characteristics. Third, multimodal analysis of I-nodes uses graph-based fusion technology, combining functional and structural brain information. The I-nodes we obtained are distributed in critical areas such as the superior frontal lobe, lateral parietal lobe, and lateral occipital lobe, with a total of 56 identified across different experiments. These I-nodes are involved in more brain networks than other regions, have longer fiber connections, and occupy more central positions in structural connectivity. They also exhibit strong connectivity and high node efficiency in both functional and structural networks. Furthermore, there is a significant overlap between the I-nodes and both the structural and functional rich-club. These findings enhance our understanding of the I-nodes within the brain network, and provide new insights for future research in further understanding the brain working mechanisms.

Geng Chen, Junqing Yang, Xiaozhou Pu et al.

Accurate segmentation of polyps from colonoscopy videos is of great significance to polyp treatment and early prevention of colorectal cancer. However, it is challenging due to the difficulties associated with modelling long-range spatio-temporal relationships within a colonoscopy video. In this paper, we address this challenging task with a novel Mixture-Attention Siamese Transformer (MAST), which explicitly models the long-range spatio-temporal relationships with a mixture-attention mechanism for accurate polyp segmentation. Specifically, we first construct a Siamese transformer architecture to jointly encode paired video frames for their feature representations. We then design a mixture-attention module to exploit the intra-frame and inter-frame correlations, enhancing the features with rich spatio-temporal relationships. Finally, the enhanced features are fed to two parallel decoders for predicting the segmentation maps. To the best of our knowledge, our MAST is the first transformer model dedicated to video polyp segmentation. Extensive experiments on the large-scale SUN-SEG benchmark demonstrate the superior performance of MAST in comparison with the cutting-edge competitors. Our code is publicly available at https://github.com/Junqing-Yang/MAST.

Yanggang Xu, Jirong Zha, Weijie Hong et al.

In disaster scenarios, establishing robust emergency communication networks is critical, and unmanned aerial vehicles (UAVs) offer a promising solution to rapidly restore connectivity. However, organizing UAVs to form multi-hop networks in large-scale dynamic environments presents significant challenges, including limitations in algorithmic scalability and the vast exploration space required for coordinated decision-making. To address these issues, we propose MRLMN, a novel framework that integrates multi-agent reinforcement learning (MARL) and large language models (LLMs) to jointly optimize UAV agents toward achieving optimal networking performance. The framework incorporates a grouping strategy with reward decomposition to enhance algorithmic scalability and balance decision-making across UAVs. In addition, behavioral constraints are applied to selected key UAVs to improve the robustness of the network. Furthermore, the framework integrates LLM agents, leveraging knowledge distillation to transfer their high-level decision-making capabilities to MARL agents. This enhances both the efficiency of exploration and the overall training process. In the distillation module, a Hungarian algorithm-based matching scheme is applied to align the decision outputs of the LLM and MARL agents and define the distillation loss. Extensive simulation results validate the effectiveness of our approach, demonstrating significant improvements in network performance over the MAPPO baseline and other comparison methods, including enhanced coverage and communication quality.

Sijun Dong, Fangcheng Zuo, Geng Chen et al.

Change detection in remote sensing imagery is a critical technique for Earth observation, primarily focusing on pixel-level segmentation of change regions between bi-temporal images. The essence of pixel-level change detection lies in determining whether corresponding pixels in bi-temporal images have changed. In deep learning, the spatial and channel dimensions of feature maps represent different information from the original images. In this study, we found that in change detection tasks, difference information can be computed not only from the spatial dimension of bi-temporal features but also from the channel dimension. Therefore, we designed the Channel-Spatial Difference Weighting (CSDW) module as an aggregation-distribution mechanism for bi-temporal features in change detection. This module enhances the sensitivity of the change detection model to difference features. Additionally, bi-temporal images share the same geographic location and exhibit strong inter-image correlations. To construct the correlation between bi-temporal images, we designed a decoding structure based on the Layer-Exchange (LE) method to enhance the interaction of bi-temporal features. Comprehensive experiments on the CLCD, PX-CLCD, LEVIR-CD, and S2Looking datasets demonstrate that the proposed LENet model significantly improves change detection performance. The code and pre-trained models will be available at: https://github.com/dyzy41/lenet.

Jirong Zha, Yuxuan Fan, Tianyu Zhang et al.

Multimodal Large Language Models (MLLMs) have shown promise in single-agent vision tasks, yet benchmarks for evaluating multi-agent collaborative perception remain scarce. This gap is critical, as multi-drone systems provide enhanced coverage, robustness, and collaboration compared to single-sensor setups. Existing multi-image benchmarks mainly target basic perception tasks using high-quality single-agent images, thus failing to evaluate MLLMs in more complex, egocentric collaborative scenarios, especially under real-world degraded perception conditions.To address these challenges, we introduce AirCopBench, the first comprehensive benchmark designed to evaluate MLLMs in embodied aerial collaborative perception under challenging perceptual conditions. AirCopBench includes 14.6k+ questions derived from both simulator and real-world data, spanning four key task dimensions: Scene Understanding, Object Understanding, Perception Assessment, and Collaborative Decision, across 14 task types. We construct the benchmark using data from challenging degraded-perception scenarios with annotated collaborative events, generating large-scale questions through model-, rule-, and human-based methods under rigorous quality control. Evaluations on 40 MLLMs show significant performance gaps in collaborative perception tasks, with the best model trailing humans by 24.38% on average and exhibiting inconsistent results across tasks. Fine-tuning experiments further confirm the feasibility of sim-to-real transfer in aerial collaborative perception and reasoning.

Sijun Dong, Yuxuan Hu, LiBo Wang et al.

To tackle the prevalence of pseudo changes, the scarcity of labeled samples, and the difficulty of cross-domain generalization in multi-temporal and multi-source remote sensing imagery, we propose PeftCD, a change detection framework built upon Vision Foundation Models (VFMs) with Parameter-Efficient Fine-Tuning (PEFT). At its core, PeftCD employs a weight-sharing Siamese encoder derived from a VFM, into which LoRA and Adapter modules are seamlessly integrated. This design enables highly efficient task adaptation by training only a minimal set of additional parameters. To fully unlock the potential of VFMs, we investigate two leading backbones: the Segment Anything Model v2 (SAM2), renowned for its strong segmentation priors, and DINOv3, a state-of-the-art self-supervised representation learner. The framework is complemented by a deliberately lightweight decoder, ensuring the focus remains on the powerful feature representations from the backbones. Extensive experiments demonstrate that PeftCD achieves state-of-the-art performance across multiple public datasets, including SYSU-CD (IoU 73.81%), WHUCD (92.05%), MSRSCD (64.07%), MLCD (76.89%), CDD (97.01%), S2Looking (52.25%) and LEVIR-CD (85.62%), with notably precise boundary delineation and strong suppression of pseudo-changes. In summary, PeftCD presents an optimal balance of accuracy, efficiency, and generalization. It offers a powerful and scalable paradigm for adapting large-scale VFMs to real-world remote sensing change detection applications. The code and pretrained models will be released at https://github.com/dyzy41/PeftCD.

Ruiqi Wu, Yuang Yao, Tengfei Ma et al.

Multimodal large language models (MLLMs) have recently demonstrated remarkable reasoning abilities with reinforcement learning paradigm. Although several multimodal reasoning models have been explored in the medical domain, most of them focus exclusively on basic reasoning, which refers to shallow inference based on visual feature matching. However, real-world clinical diagnosis extends beyond basic reasoning, demanding reasoning processes that integrate heterogeneous clinical information (such as chief complaints and medical history) with multimodal medical imaging data. To bridge this gap, we introduce MM-Retinal-Reason, the first ophthalmic multimodal dataset with the full spectrum of perception and reasoning. It encompasses both basic reasoning tasks and complex reasoning tasks, aiming to enhance visual-centric fundamental reasoning capabilities and emulate realistic clinical thinking patterns. Building upon MM-Retinal-Reason, we propose OphthaReason, the first ophthalmology-specific multimodal reasoning model with step-by-step reasoning traces. To enable flexible adaptation to both basic and complex reasoning tasks, we specifically design a novel method called Uncertainty-Aware Dynamic Thinking (UADT), which estimates sample-level uncertainty via entropy and dynamically modulates the model's exploration depth using a shaped advantage mechanism. Comprehensive experiments demonstrate that our model achieves state-of-the-art performance on both basic and complex reasoning tasks, outperforming general-purpose MLLMs, medical MLLMs, RL-based medical MLLMs, and ophthalmic MLLMs by at least 24.92\%, 15.00\%, 21.20\%, and 17.66\%. Project Page: \href{https://github.com/lxirich/OphthaReason}{link}.

Yuxin Xie, Tao Zhou, Yi Zhou et al.

Weakly-supervised medical image segmentation is a challenging task that aims to reduce the annotation cost while keep the segmentation performance. In this paper, we present a novel framework, SimTxtSeg, that leverages simple text cues to generate high-quality pseudo-labels and study the cross-modal fusion in training segmentation models, simultaneously. Our contribution consists of two key components: an effective Textual-to-Visual Cue Converter that produces visual prompts from text prompts on medical images, and a text-guided segmentation model with Text-Vision Hybrid Attention that fuses text and image features. We evaluate our framework on two medical image segmentation tasks: colonic polyp segmentation and MRI brain tumor segmentation, and achieve consistent state-of-the-art performance. Source code is available at: https://github.com/xyx1024/SimTxtSeg.

Tao Zhou, Deng-Ping Fan, Geng Chen et al.

Salient object detection (SOD) on RGB and depth images has attracted more and more research interests, due to its effectiveness and the fact that depth cues can now be conveniently captured. Existing RGB-D SOD models usually adopt different fusion strategies to learn a shared representation from the two modalities (\ie, RGB and depth), while few methods explicitly consider how to preserve modality-specific characteristics. In this study, we propose a novel framework, termed SPNet} (Specificity-preserving network), which benefits SOD performance by exploring both the shared information and modality-specific properties (\eg, specificity). Specifically, we propose to adopt two modality-specific networks and a shared learning network to generate individual and shared saliency prediction maps, respectively. To effectively fuse cross-modal features in the shared learning network, we propose a cross-enhanced integration module (CIM) and then propagate the fused feature to the next layer for integrating cross-level information. Moreover, to capture rich complementary multi-modal information for boosting the SOD performance, we propose a multi-modal feature aggregation (MFA) module to integrate the modality-specific features from each individual decoder into the shared decoder. By using a skip connection, the hierarchical features between the encoder and decoder layers can be fully combined. Extensive experiments demonstrate that our~\ours~outperforms cutting-edge approaches on six popular RGB-D SOD and three camouflaged object detection benchmarks. The project is publicly available at: https://github.com/taozh2017/SPNet.

Yujia Sun, Geng Chen, Tao Zhou et al.

Camouflaged object detection (COD) is a challenging task due to the low boundary contrast between the object and its surroundings. In addition, the appearance of camouflaged objects varies significantly, e.g., object size and shape, aggravating the difficulties of accurate COD. In this paper, we propose a novel Context-aware Cross-level Fusion Network (C2F-Net) to address the challenging COD task. Specifically, we propose an Attention-induced Cross-level Fusion Module (ACFM) to integrate the multi-level features with informative attention coefficients. The fused features are then fed to the proposed Dual-branch Global Context Module (DGCM), which yields multi-scale feature representations for exploiting rich global context information. In C2F-Net, the two modules are conducted on high-level features using a cascaded manner. Extensive experiments on three widely used benchmark datasets demonstrate that our C2F-Net is an effective COD model and outperforms state-of-the-art models remarkably. Our code is publicly available at: https://github.com/thograce/C2FNet.

Yi Zhang, Geng Chen, Qian Chen et al.

We propose a novel Synergistic Attention Network (SA-Net) to address the light field salient object detection by establishing a synergistic effect between multi-modal features with advanced attention mechanisms. Our SA-Net exploits the rich information of focal stacks via 3D convolutional neural networks, decodes the high-level features of multi-modal light field data with two cascaded synergistic attention modules, and predicts the saliency map using an effective feature fusion module in a progressive manner. Extensive experiments on three widely-used benchmark datasets show that our SA-Net outperforms 28 state-of-the-art models, sufficiently demonstrating its effectiveness and superiority. Our code is available at https://github.com/PanoAsh/SA-Net.

Chun-Mei Feng, Zhanyuan Yang, Geng Chen et al.

Magnetic resonance (MR) image acquisition is an inherently prolonged process, whose acceleration by obtaining multiple undersampled images simultaneously through parallel imaging has always been the subject of research. In this paper, we propose the Dual-Octave Convolution (Dual-OctConv), which is capable of learning multi-scale spatial-frequency features from both real and imaginary components, for fast parallel MR image reconstruction. By reformulating the complex operations using octave convolutions, our model shows a strong ability to capture richer representations of MR images, while at the same time greatly reducing the spatial redundancy. More specifically, the input feature maps and convolutional kernels are first split into two components (i.e., real and imaginary), which are then divided into four groups according to their spatial frequencies. Then, our Dual-OctConv conducts intra-group information updating and inter-group information exchange to aggregate the contextual information across different groups. Our framework provides two appealing benefits: (i) it encourages interactions between real and imaginary components at various spatial frequencies to achieve richer representational capacity, and (ii) it enlarges the receptive field by learning multiple spatial-frequency features of both the real and imaginary components. We evaluate the performance of the proposed model on the acceleration of multi-coil MR image reconstruction. Extensive experiments are conducted on an {in vivo} knee dataset under different undersampling patterns and acceleration factors. The experimental results demonstrate the superiority of our model in accelerated parallel MR image reconstruction. Our code is available at: github.com/chunmeifeng/Dual-OctConv.

Rujia Yang, Geng Chen, Chuan Wen et al.

Following its success in natural language processing and computer vision, foundation models that are pre-trained on large-scale multi-task datasets have also shown great potential in robotics. However, most existing robot foundation models rely solely on 2D image observations, ignoring 3D geometric information, which is essential for robots to perceive and reason about the 3D world. In this paper, we introduce FP3, a first large-scale 3D foundation policy model for robotic manipulation. FP3 builds on a scalable diffusion transformer architecture and is pre-trained on 60k trajectories with point cloud observations. With the model design and diverse pre-training data, FP3 can be efficiently fine-tuned for downstream tasks while exhibiting strong generalization capabilities. Experiments on real robots demonstrate that with only 80 demonstrations, FP3 is able to learn a new task with over 90% success rates in novel environments with unseen objects, significantly surpassing existing robot foundation models.

Tong Zhang, Boyuan Zheng, Ruiqian Nai et al.

The human body demonstrates exceptional motor capabilities-such as standing steadily on one foot or performing a high kick with the leg raised over 1.5 meters-both requiring precise balance control. While recent research on humanoid control has leveraged reinforcement learning to track human motions for skill acquisition, applying this paradigm to balance-intensive tasks remains challenging. In this work, we identify three key obstacles: instability from reference motion errors, learning difficulties due to morphological mismatch, and the sim-to-real gap caused by sensor noise and unmodeled dynamics. To address these challenges, we propose HuB (Humanoid Balance), a unified framework that integrates reference motion refinement, balance-aware policy learning, and sim-to-real robustness training, with each component targeting a specific challenge. We validate our approach on the Unitree G1 humanoid robot across challenging quasi-static balance tasks, including extreme single-legged poses such as Swallow Balance and Bruce Lee's Kick. Our policy remains stable even under strong physical disturbances-such as a forceful soccer strike-while baseline methods consistently fail to complete these tasks. Project website: https://hub-robot.github.io

Isabella Liu, An-Chieh Cheng, Rui Yan et al.

Long-horizon manipulation remains challenging for vision-language-action (VLA) policies: real tasks are multi-step, progress-dependent, and brittle to compounding execution errors. We present LoHo-Manip, a modular framework that scales short-horizon VLA execution to long-horizon instruction following via a dedicated task-management VLM. The manager is decoupled from the executor and is invoked in a receding-horizon manner: given the current observation, it predicts a progress-aware remaining plan that combines (i) a subtask sequence with an explicit done + remaining split as lightweight language memory, and (ii) a visual trace -- a compact 2D keypoint trajectory prompt specifying where to go and what to approach next. The executor VLA is adapted to condition on the rendered trace, thereby turning long-horizon decision-making into repeated local control by following the trace. Crucially, predicting the remaining plan at each step yields an implicit closed loop: failed steps persist in subsequent outputs, and traces update accordingly, enabling automatic continuation and replanning without hand-crafted recovery logic or brittle visual-history buffers. Extensive experiments spanning embodied planning, long-horizon reasoning, trajectory prediction, and end-to-end manipulation in simulation and on a real Franka robot demonstrate strong gains in long-horizon success, robustness, and out-of-distribution generalization. Project page: https://www.liuisabella.com/LoHoManip

Xiongyi Cai, Ri-Zhao Qiu, Geng Chen et al.

Egocentric videos are a valuable and scalable data source to learn manipulation policies. However, due to significant data heterogeneity, most existing approaches utilize human data for simple pre-training, which does not unlock its full potential. This paper first provides a scalable recipe for collecting and using egocentric data by categorizing human data into two categories: in-the-wild and on-task alongside with systematic analysis on how to use the data. We first curate a dataset, PHSD, which contains over 1,000 hours of diverse in-the-wild egocentric data and over 20 hours of on-task data directly aligned to the target manipulation tasks. This enables learning a large egocentric language-conditioned flow matching policy, Human0. With domain adaptation techniques, Human0 minimizes the gap between humans and humanoids. Empirically, we show Human0 achieves several novel properties from scaling human data, including language following of instructions from only human data, few-shot learning, and improved robustness using on-task data. Project website: https://xiongyicai.github.io/In-N-On/

Chengbo Yuan, Geng Chen, Li Yi et al.

Egocentric videos provide valuable insights into human interactions with the physical world, which has sparked growing interest in the computer vision and robotics communities. A critical challenge in fully understanding the geometry and dynamics of egocentric videos is dense scene reconstruction. However, the lack of high-quality labeled datasets in this field has hindered the effectiveness of current supervised learning methods. In this work, we aim to address this issue by exploring an self-supervised dynamic scene reconstruction approach. We introduce EgoMono4D, a novel model that unifies the estimation of multiple variables necessary for Egocentric Monocular 4D reconstruction, including camera intrinsic, camera poses, and video depth, all within a fast feed-forward framework. Starting from pretrained single-frame depth and intrinsic estimation model, we extend it with camera poses estimation and align multi-frame results on large-scale unlabeled egocentric videos. We evaluate EgoMono4D in both in-domain and zero-shot generalization settings, achieving superior performance in dense pointclouds sequence reconstruction compared to all baselines. EgoMono4D represents the first attempt to apply self-supervised learning for pointclouds sequence reconstruction to the label-scarce egocentric field, enabling fast, dense, and generalizable reconstruction. The interactable visualization, code and trained models are released https://egomono4d.github.io/

Weiyu Liu, Geng Chen, Joy Hsu et al.

This paper presents a framework for learning state and action abstractions in sequential decision-making domains. Our framework, planning abstraction from language (PARL), utilizes language-annotated demonstrations to automatically discover a symbolic and abstract action space and induce a latent state abstraction based on it. PARL consists of three stages: 1) recovering object-level and action concepts, 2) learning state abstractions, abstract action feasibility, and transition models, and 3) applying low-level policies for abstract actions. During inference, given the task description, PARL first makes abstract action plans using the latent transition and feasibility functions, then refines the high-level plan using low-level policies. PARL generalizes across scenarios involving novel object instances and environments, unseen concept compositions, and tasks that require longer planning horizons than settings it is trained on.

Geng Chen, Qingyue Wang, Islem Rekik

A connectional brain template (CBT) is a holistic representation of a population of multi-view brain connectivity graphs, encoding shared patterns and normalizing typical variations across individuals. The federation of CBT learning allows for an inclusive estimation of the representative center of multi-domain brain connectivity datasets in a fully data-preserving manner. However, existing methods overlook the non-independent and identically distributed (non-IDD) issue stemming from multidomain brain connectivity heterogeneity, in which data domains are drawn from different hospitals and imaging modalities. To overcome this limitation, we unprecedentedly propose a metadata-driven federated learning framework, called MetaFedCBT, for cross-domain CBT learning. Given the data drawn from a specific domain (i.e., hospital), our model aims to learn metadata in a fully supervised manner by introducing a local client-based regressor network. The generated meta-data is forced to meet the statistical attributes (e.g., mean) of other domains, while preserving their privacy. Our supervised meta-data generation approach boosts the unsupervised learning of a more centered, representative, and holistic CBT of a particular brain state across diverse domains. As the federated learning progresses over multiple rounds, the learned metadata and associated generated connectivities are continuously updated to better approximate the target domain information. MetaFedCBT overcomes the non-IID issue of existing methods by generating informative brain connectivities for privacy-preserving holistic CBT learning with guidance using metadata. Extensive experiments on multi-view morphological brain networks of normal and patient subjects demonstrate that our MetaFedCBT is a superior federated CBT learning model and significantly advances the state-of-the-art performance.

Chun-Mei Feng, Yunlu Yan, Geng Chen et al.

Accelerated multi-modal magnetic resonance (MR) imaging is a new and effective solution for fast MR imaging, providing superior performance in restoring the target modality from its undersampled counterpart with guidance from an auxiliary modality. However, existing works simply combine the auxiliary modality as prior information, lacking in-depth investigations on the potential mechanisms for fusing different modalities. Further, they usually rely on the convolutional neural networks (CNNs), which is limited by the intrinsic locality in capturing the long-distance dependency. To this end, we propose a multi-modal transformer (MTrans), which is capable of transferring multi-scale features from the target modality to the auxiliary modality, for accelerated MR imaging. To capture deep multi-modal information, our MTrans utilizes an improved multi-head attention mechanism, named cross attention module, which absorbs features from the auxiliary modality that contribute to the target modality. Our framework provides three appealing benefits: (i) Our MTrans use an improved transformers for multi-modal MR imaging, affording more global information compared with existing CNN-based methods. (ii) A new cross attention module is proposed to exploit the useful information in each modality at different scales. The small patch in the target modality aims to keep more fine details, the large patch in the auxiliary modality aims to obtain high-level context features from the larger region and supplement the target modality effectively. (iii) We evaluate MTrans with various accelerated multi-modal MR imaging tasks, e.g., MR image reconstruction and super-resolution, where MTrans outperforms state-of-the-art methods on fastMRI and real-world clinical datasets.

Ge-Peng Ji, Yu-Cheng Chou, Deng-Ping Fan et al.

Existing video polyp segmentation (VPS) models typically employ convolutional neural networks (CNNs) to extract features. However, due to their limited receptive fields, CNNs can not fully exploit the global temporal and spatial information in successive video frames, resulting in false-positive segmentation results. In this paper, we propose the novel PNS-Net (Progressively Normalized Self-attention Network), which can efficiently learn representations from polyp videos with real-time speed (~140fps) on a single RTX 2080 GPU and no post-processing. Our PNS-Net is based solely on a basic normalized self-attention block, equipping with recurrence and CNNs entirely. Experiments on challenging VPS datasets demonstrate that the proposed PNS-Net achieves state-of-the-art performance. We also conduct extensive experiments to study the effectiveness of the channel split, soft-attention, and progressive learning strategy. We find that our PNS-Net works well under different settings, making it a promising solution to the VPS task.

Hong-Bo Bi, Zi-Qi Liu, Kang Wang et al.

Saliency detection based on the complementary information from RGB images and depth maps has recently gained great popularity. In this paper, we propose Complementary Attention and Adaptive Integration Network (CAAI-Net), a novel RGB-D saliency detection model that integrates complementary attention based feature concentration and adaptive cross-modal feature fusion into a unified framework for accurate saliency detection. Specifically, we propose a context-aware complementary attention (CCA) module, which consists of a feature interaction component, a complementary attention component, and a global-context component. The CCA module first utilizes the feature interaction component to extract rich local context features. The resulting features are then fed into the complementary attention component, which employs the complementary attention generated from adjacent levels to guide the attention at the current layer so that the mutual background disturbances are suppressed and the network focuses more on the areas with salient objects. Finally, we utilize a specially-designed adaptive feature integration (AFI) module, which sufficiently considers the low-quality issue of depth maps, to aggregate the RGB and depth features in an adaptive manner. Extensive experiments on six challenging benchmark datasets demonstrate that CAAI-Net is an effective saliency detection model and outperforms nine state-of-the-art models in terms of four widely-used metrics. In addition, extensive ablation studies confirm the effectiveness of the proposed CCA and AFI modules.

Geng Chen, Xinrui Chen, Bo Dong et al.

Camouflaged object detection (COD), which aims to identify the objects that conceal themselves into the surroundings, has recently drawn increasing research efforts in the field of computer vision. In practice, the success of deep learning based COD is mainly determined by two key factors, including (i) A significantly large receptive field, which provides rich context information, and (ii) An effective fusion strategy, which aggregates the rich multi-level features for accurate COD. Motivated by these observations, in this paper, we propose a novel deep learning based COD approach, which integrates the large receptive field and effective feature fusion into a unified framework. Specifically, we first extract multi-level features from a backbone network. The resulting features are then fed to the proposed dual-branch mixture convolution modules, each of which utilizes multiple asymmetric convolutional layers and two dilated convolutional layers to extract rich context features from a large receptive field. Finally, we fuse the features using specially-designed multilevel interactive fusion modules, each of which employs an attention mechanism along with feature interaction for effective feature fusion. Our method detects camouflaged objects with an effective fusion strategy, which aggregates the rich context information from a large receptive field. All of these designs meet the requirements of COD well, allowing the accurate detection of camouflaged objects. Extensive experiments on widely-used benchmark datasets demonstrate that our method is capable of accurately detecting camouflaged objects and outperforms the state-of-the-art methods.

Geng Chen, Peirong Guo

In recent years, crowd counting, a technique for predicting the number of people in an image, becomes a challenging task in computer vision. In this paper, we propose a cross-column feature fusion network to solve the problem of information redundancy in columns. We introduce the Information Fusion Module (IFM) which provides a channel for information flow to help different columns to obtain significant information from another column. Through this channel, different columns exchange information with each other and extract useful features from the other column to enhance key information. Hence, there is no need for columns to pay attention to all areas in the image. Each column can be responsible for different regions, thereby reducing the burden of each column. In experiments, the generalizability of our model is more robust and the results of transferring between different datasets acheive the comparable results with the state-of-the-art models.

Deng-Ping Fan, Ge-Peng Ji, Tao Zhou et al.

Colonoscopy is an effective technique for detecting colorectal polyps, which are highly related to colorectal cancer. In clinical practice, segmenting polyps from colonoscopy images is of great importance since it provides valuable information for diagnosis and surgery. However, accurate polyp segmentation is a challenging task, for two major reasons: (i) the same type of polyps has a diversity of size, color and texture; and (ii) the boundary between a polyp and its surrounding mucosa is not sharp. To address these challenges, we propose a parallel reverse attention network (PraNet) for accurate polyp segmentation in colonoscopy images. Specifically, we first aggregate the features in high-level layers using a parallel partial decoder (PPD). Based on the combined feature, we then generate a global map as the initial guidance area for the following components. In addition, we mine the boundary cues using a reverse attention (RA) module, which is able to establish the relationship between areas and boundary cues. Thanks to the recurrent cooperation mechanism between areas and boundaries, our PraNet is capable of calibrating any misaligned predictions, improving the segmentation accuracy. Quantitative and qualitative evaluations on five challenging datasets across six metrics show that our PraNet improves the segmentation accuracy significantly, and presents a number of advantages in terms of generalizability, and real-time segmentation efficiency.

Deng-Ping Fan, Tao Zhou, Ge-Peng Ji et al.

Coronavirus Disease 2019 (COVID-19) spread globally in early 2020, causing the world to face an existential health crisis. Automated detection of lung infections from computed tomography (CT) images offers a great potential to augment the traditional healthcare strategy for tackling COVID-19. However, segmenting infected regions from CT slices faces several challenges, including high variation in infection characteristics, and low intensity contrast between infections and normal tissues. Further, collecting a large amount of data is impractical within a short time period, inhibiting the training of a deep model. To address these challenges, a novel COVID-19 Lung Infection Segmentation Deep Network (Inf-Net) is proposed to automatically identify infected regions from chest CT slices. In our Inf-Net, a parallel partial decoder is used to aggregate the high-level features and generate a global map. Then, the implicit reverse attention and explicit edge-attention are utilized to model the boundaries and enhance the representations. Moreover, to alleviate the shortage of labeled data, we present a semi-supervised segmentation framework based on a randomly selected propagation strategy, which only requires a few labeled images and leverages primarily unlabeled data. Our semi-supervised framework can improve the learning ability and achieve a higher performance. Extensive experiments on our COVID-SemiSeg and real CT volumes demonstrate that the proposed Inf-Net outperforms most cutting-edge segmentation models and advances the state-of-the-art performance.

Yoonmi Hong, Wei-Tang Chang, Geng Chen et al.

Diffusion MRI (dMRI) is a unique imaging technique for in vivo characterization of tissue microstructure and white matter pathways. However, its relatively long acquisition time implies greater motion artifacts when imaging, for example, infants and Parkinson's disease patients. To accelerate dMRI acquisition, we propose in this paper (i) a diffusion encoding scheme, called Slice-Interleaved Diffusion Encoding (SIDE), that interleaves each diffusion-weighted (DW) image volume with slices that are encoded with different diffusion gradients, essentially allowing the slice-undersampling of image volume associated with each diffusion gradient to significantly reduce acquisition time, and (ii) a method based on deep learning for effective reconstruction of DW images from the highly slice-undersampled data. Evaluation based on the Human Connectome Project (HCP) dataset indicates that our method can achieve a high acceleration factor of up to 6 with minimal information loss. Evaluation using dMRI data acquired with SIDE acquisition demonstrates that it is possible to accelerate the acquisition by as much as 50 folds when combined with multi-band imaging.

Tao Zhou, Huazhu Fu, Geng Chen et al.

Magnetic resonance imaging (MRI) is a widely used neuroimaging technique that can provide images of different contrasts (i.e., modalities). Fusing this multi-modal data has proven particularly effective for boosting model performance in many tasks. However, due to poor data quality and frequent patient dropout, collecting all modalities for every patient remains a challenge. Medical image synthesis has been proposed as an effective solution to this, where any missing modalities are synthesized from the existing ones. In this paper, we propose a novel Hybrid-fusion Network (Hi-Net) for multi-modal MR image synthesis, which learns a mapping from multi-modal source images (i.e., existing modalities) to target images (i.e., missing modalities). In our Hi-Net, a modality-specific network is utilized to learn representations for each individual modality, and a fusion network is employed to learn the common latent representation of multi-modal data. Then, a multi-modal synthesis network is designed to densely combine the latent representation with hierarchical features from each modality, acting as a generator to synthesize the target images. Moreover, a layer-wise multi-modal fusion strategy is presented to effectively exploit the correlations among multiple modalities, in which a Mixed Fusion Block (MFB) is proposed to adaptively weight different fusion strategies (i.e., element-wise summation, product, and maximization). Extensive experiments demonstrate that the proposed model outperforms other state-of-the-art medical image synthesis methods.

Feihong Liu, Jun Feng, Geng Chen et al.

Parcellation of whole-brain tractography streamlines is an important step for tract-based analysis of brain white matter microstructure. Existing fiber parcellation approaches rely on accurate registration between an atlas and the tractograms of an individual, however, due to large individual differences, accurate registration is hard to guarantee in practice. To resolve this issue, we propose a novel deep learning method, called DeepBundle, for registration-free fiber parcellation. Our method utilizes graph convolution neural networks (GCNNs) to predict the parcellation label of each fiber tract. GCNNs are capable of extracting the geometric features of each fiber tract and harnessing the resulting features for accurate fiber parcellation and ultimately avoiding the use of atlases and any registration method. We evaluate DeepBundle using data from the Human Connectome Project. Experimental results demonstrate the advantages of DeepBundle and suggest that the geometric features extracted from each fiber tract can be used to effectively parcellate the fiber tracts.