Yan Peng

Dan Zhang, Xi Zhou, Zi-Hao Wang et al.

Ship roll motion in high sea states has large amplitudes and nonlinear dynamics, and its prediction is significant for operability, safety, and survivability. This paper presents a novel data-driven methodology to provide a multi-step prediction of ship roll motions in high sea states. A hybrid neural network is proposed that combines long short-term memory (LSTM) and convolutional neural network (CNN) in parallel. The motivation is to extract the nonlinear dynamic characteristics and the hydrodynamic memory information through the advantage of CNN and LSTM, respectively. For the feature selection, the time histories of motion states and wave heights are selected to involve sufficient information. Taken a scaled KCS as the study object, the ship motions in sea state 7 irregular long-crested waves are simulated and used for the validation. The results show that at least one period of roll motion can be accurately predicted. Compared with the single LSTM and CNN methods, the proposed method has better performance in predicting the amplitude of roll angles. Besides, the comparison results also demonstrate that selecting motion states and wave heights as feature space improves the prediction accuracy, verifying the effectiveness of the proposed method.

Jinan Yu, Liyan Ma, Zhenglin Li et al.

Open-world object detection (OWOD) is a challenging problem that combines object detection with incremental learning and open-set learning. Compared to standard object detection, the OWOD setting is task to: 1) detect objects seen during training while identifying unseen classes, and 2) incrementally learn the knowledge of the identified unknown objects when the corresponding annotations is available. We propose a novel and efficient OWOD solution from a prototype perspective, which we call OCPL: Open-world object detection via discriminative Class Prototype Learning, which consists of a Proposal Embedding Aggregator (PEA), an Embedding Space Compressor (ESC) and a Cosine Similarity-based Classifier (CSC). All our proposed modules aim to learn the discriminative embeddings of known classes in the feature space to minimize the overlapping distributions of known and unknown classes, which is beneficial to differentiate known and unknown classes. Extensive experiments performed on PASCAL VOC and MS-COCO benchmark demonstrate the effectiveness of our proposed method.

Haoyang Li, Liang Wang, Chao Wang et al.

The Base-New Trade-off (BNT) problem universally exists during the optimization of CLIP-based prompt tuning, where continuous fine-tuning on base (target) classes leads to a simultaneous decrease of generalization ability on new (unseen) classes. Existing approaches attempt to regulate the prompt tuning process to balance BNT by appending constraints. However, imposed on the same target prompt, these constraints fail to fully avert the mutual exclusivity between the optimization directions for base and new. As a novel solution to this challenge, we propose the plug-and-play Dual-Prompt Collaboration (DPC) framework, the first that decoupling the optimization processes of base and new tasks at the prompt level. Specifically, we clone a learnable parallel prompt based on the backbone prompt, and introduce a variable Weighting-Decoupling framework to independently control the optimization directions of dual prompts specific to base or new tasks, thus avoiding the conflict in generalization. Meanwhile, we propose a Dynamic Hard Negative Optimizer, utilizing dual prompts to construct a more challenging optimization task on base classes for enhancement. For interpretability, we prove the feature channel invariance of the prompt vector during the optimization process, providing theoretical support for the Weighting-Decoupling of DPC. Extensive experiments on multiple backbones demonstrate that DPC can significantly improve base performance without introducing any external knowledge beyond the base classes, while maintaining generalization to new classes. Code is available at: https://github.com/JREion/DPC.

Jiacheng Sun, Jiaqi Lin, Wenlong Hu et al.

One of the bottlenecks for instance segmentation today lies in the conflicting requirements of high-resolution inputs and lightweight, real-time inference. To address this bottleneck, we present a Polygon Detection Transformer (Poly-DETR) to reformulate instance segmentation as sparse vertex regression via Polar Representation, thereby eliminating the reliance on dense pixel-wise mask prediction. Considering the box-to-polygon reference shift in Detection Transformers, we propose Polar Deformable Attention and Position-Aware Training Scheme to dynamically update supervision and focus attention on boundary cues. Compared with state-of-the-art polar-based methods, Poly-DETR achieves a 4.7 mAP improvement on MS COCO test-dev. Moreover, we construct a parallel mask-based counterpart to support a systematic comparison between polar and mask representations. Experimental results show that Poly-DETR is more lightweight in high-resolution scenarios, reducing memory consumption by almost half on Cityscapes dataset. Notably, on PanNuke (cell segmentation) and SpaceNet (building footprints) datasets, Poly-DETR surpasses its mask-based counterpart on all metrics, which validates its advantage on regular-shaped instances in domain-specific settings.

Haoyang Li, Liang Wang, Chao Wang et al.

For CLIP-based prompt tuning, introducing more data as additional knowledge for enhancing fine-tuning process is proved to be an effective approach. Existing data amplification strategies for prompt tuning typically rely on external knowledge (e.g., large language models or pre-structured knowledge bases), resulting in higher costs for data collection and processing, while generally ignoring further utilization of features in image modality. To address this, we propose Augmentation-driven Prompt Tuning (AugPT), a self-contained distillation-based prompt tuning approach using only internal augmentation on raw dataset to better exploit known features. Specifically, AugPT employs self-supervised augmentation on unlabeled images in the training set, and introduces a novel gating mechanism based on consensus test, reusing the pre-trained prompt tuning backbone model to spontaneously filter noisy samples, further enhancing the quality of augmented views. Extensive experiments validate that AugPT simultaneously enhances model performance and generalization capability without using appended external knowledge. The code of AugPT is available at: https://github.com/JREion/AugPT .

Linqi Ye, Rankun Li, Xiaowen Hu et al.

This paper introduces Unity RL Playground, an open-source reinforcement learning framework built on top of Unity ML-Agents. Unity RL Playground automates the process of training mobile robots to perform various locomotion tasks such as walking, running, and jumping in simulation, with the potential for seamless transfer to real hardware. Key features include one-click training for imported robot models, universal compatibility with diverse robot configurations, multi-mode motion learning capabilities, and extreme performance testing to aid in robot design optimization and morphological evolution. The attached video can be found at https://linqi-ye.github.io/video/iros25.mp4 and the code is coming soon.

Chengmeng Li, Junjie Wen, Yan Peng et al.

Vision-Language-Action (VLA) models excel at robotic tasks by leveraging large-scale 2D vision-language pretraining, but their reliance on RGB images limits spatial reasoning critical for real-world interaction. Retraining these models with 3D data is computationally prohibitive, while discarding existing 2D datasets wastes valuable resources. To bridge this gap, we propose PointVLA, a framework that enhances pre-trained VLAs with point cloud inputs without requiring retraining. Our method freezes the vanilla action expert and injects 3D features via a lightweight modular block. To identify the most effective way of integrating point cloud representations, we conduct a skip-block analysis to pinpoint less useful blocks in the vanilla action expert, ensuring that 3D features are injected only into these blocks--minimizing disruption to pre-trained representations. Extensive experiments demonstrate that PointVLA outperforms state-of-the-art 2D imitation learning methods, such as OpenVLA, Diffusion Policy and DexVLA, across both simulated and real-world robotic tasks. Specifically, we highlight several key advantages of PointVLA enabled by point cloud integration: (1) Few-shot multi-tasking, where PointVLA successfully performs four different tasks using only 20 demonstrations each; (2) Real-vs-photo discrimination, where PointVLA distinguishes real objects from their images, leveraging 3D world knowledge to improve safety and reliability; (3) Height adaptability, Unlike conventional 2D imitation learning methods, PointVLA enables robots to adapt to objects at varying table height that unseen in train data. Furthermore, PointVLA achieves strong performance in long-horizon tasks, such as picking and packing objects from a moving conveyor belt, showcasing its ability to generalize across complex, dynamic environments.

Yimin Sun, Chao Wang, Yan Peng

Visual question answering (VQA) is a fundamental and essential AI task, and VQA-based disaster scenario understanding is a hot research topic. For instance, we can ask questions about a disaster image by the VQA model and the answer can help identify whether anyone or anything is affected by the disaster. However, previous VQA models for disaster damage assessment have some shortcomings, such as limited candidate answer space, monotonous question types, and limited answering capability of existing models. In this paper, we propose a zero-shot VQA model named Zero-shot VQA for Flood Disaster Damage Assessment (ZFDDA). It is a VQA model for damage assessment without pre-training. Also, with flood disaster as the main research object, we build a Freestyle Flood Disaster Image Question Answering dataset (FFD-IQA) to evaluate our VQA model. This new dataset expands the question types to include free-form, multiple-choice, and yes-no questions. At the same time, we expand the size of the previous dataset to contain a total of 2,058 images and 22,422 question-meta ground truth pairs. Most importantly, our model uses well-designed chain of thought (CoT) demonstrations to unlock the potential of the large language model, allowing zero-shot VQA to show better performance in disaster scenarios. The experimental results show that the accuracy in answering complex questions is greatly improved with CoT prompts. Our study provides a research basis for subsequent research of VQA for other disaster scenarios.

Qixuan Li, Chao Wang, Zongjin He et al.

Text-to-3D asset generation has achieved significant optimization under the supervision of 2D diffusion priors. However, when dealing with compositional scenes, existing methods encounter several challenges: 1). failure to ensure that composite scene layouts comply with physical laws; 2). difficulty in accurately capturing the assets and relationships described in complex scene descriptions; 3). limited autonomous asset generation capabilities among layout approaches leveraging large language models (LLMs). To avoid these compromises, we propose a novel framework for compositional scene generation, PhiP-G, which seamlessly integrates generation techniques with layout guidance based on a world model. Leveraging LLM-based agents, PhiP-G analyzes the complex scene description to generate a scene graph, and integrating a multimodal 2D generation agent and a 3D Gaussian generation method for targeted assets creation. For the stage of layout, PhiP-G employs a physical pool with adhesion capabilities and a visual supervision agent, forming a world model for layout prediction and planning. Extensive experiments demonstrate that PhiP-G significantly enhances the generation quality and physical rationality of the compositional scenes. Notably, PhiP-G attains state-of-the-art (SOTA) performance in CLIP scores, achieves parity with the leading methods in generation quality as measured by the T$^3$Bench, and improves efficiency by 24x.

Chao Wang, Chunbai Zhang, Yongxiao Tian et al.

Visual reasoning refers to the task of solving questions about visual information. Current visual reasoning methods typically employ pre-trained vision-language model (VLM) strategies or deep neural network approaches. However, existing efforts are constrained by limited reasoning interpretability, while hindering by the phenomenon of underspecification in the question text. Additionally, the absence of fine-grained visual knowledge limits the precise understanding of subject behavior in visual reasoning tasks. To address these issues, we propose VIKSER (Visual Knowledge-Driven Self-Reinforcing Reasoning Framework). Specifically, VIKSER, trained using knowledge distilled from large language models, extracts fine-grained visual knowledge with the assistance of visual relationship detection techniques. Subsequently, VIKSER utilizes fine-grained visual knowledge to paraphrase the question with underspecification. Additionally, we design a novel prompting method called Chain-of-Evidence (CoE), which leverages the power of "evidence for reasoning" to endow VIKSER with interpretable reasoning capabilities. Meanwhile, the integration of self-reflection technology empowers VIKSER with the ability to learn and improve from its mistakes. Experiments conducted on widely used datasets demonstrate that VIKSER achieves new state-of-the-art (SOTA) results in relevant tasks. Moreover, VIKSER achieves performance on par with leading proprietary models, such as the latest ChatGPT-5.

Yimin Sun, Chao Wang, Yan Peng

The zero-shot performance of visual question answering (VQA) models relies heavily on prompts. For example, a zero-shot VQA for disaster scenarios could leverage well-designed Chain of Thought (CoT) prompts to stimulate the model's potential. However, using CoT prompts has some problems, such as causing an incorrect answer in the end due to the hallucination in the thought process. In this paper, we propose a zero-shot VQA named Flood Disaster VQA with Two-Stage Prompt (VQA-TSP). The model generates the thought process in the first stage and then uses the thought process to generate the final answer in the second stage. In particular, visual context is added in the second stage to relieve the hallucination problem that exists in the thought process. Experimental results show that our method exceeds the performance of state-of-the-art zero-shot VQA models for flood disaster scenarios in total. Our study provides a research basis for improving the performance of CoT-based zero-shot VQA.

Mingyuan Mao, Renrui Zhang, Honghui Zheng et al.

Transformers with remarkable global representation capacities achieve competitive results for visual tasks, but fail to consider high-level local pattern information in input images. In this paper, we present a generic Dual-stream Network (DS-Net) to fully explore the representation capacity of local and global pattern features for image classification. Our DS-Net can simultaneously calculate fine-grained and integrated features and efficiently fuse them. Specifically, we propose an Intra-scale Propagation module to process two different resolutions in each block and an Inter-Scale Alignment module to perform information interaction across features at dual scales. Besides, we also design a Dual-stream FPN (DS-FPN) to further enhance contextual information for downstream dense predictions. Without bells and whistles, the proposed DS-Net outperforms DeiT-Small by 2.4% in terms of top-1 accuracy on ImageNet-1k and achieves state-of-the-art performance over other Vision Transformers and ResNets. For object detection and instance segmentation, DS-Net-Small respectively outperforms ResNet-50 by 6.4% and 5.5% in terms of mAP on MSCOCO 2017, and surpasses the previous state-of-the-art scheme, which significantly demonstrates its potential to be a general backbone in vision tasks. The code will be released soon.

Yong Chen, Zhi-Gang Jia, Ya-Xin Peng et al.

Quaternion singular value decomposition (QSVD) is a robust technique of digital watermarking which can extract high quality watermarks from watermarked images with low distortion. In this paper, QSVD technique is further investigated and an efficient robust watermarking scheme is proposed. The improved algebraic structure-preserving method is proposed to handle the problem of "explosion of complexity" occurred in the conventional QSVD design. Secret information is transmitted blindly by incorporating in QSVD two new strategies, namely, coefficient pair selection and adaptive embedding. Unlike conventional QSVD which embeds watermarks in a single imaginary unit, we propose to adaptively embed the watermark into the optimal hiding position using the Normalized Cross-Correlation (NC) method. This avoids the selection of coefficient pair with less correlation, and thus, it reduces embedding impact by decreasing the maximum modification of coefficient values. In this way, compared with conventional QSVD, the proposed watermarking strategy avoids more modifications to a single color image layer and a better visual quality of the watermarked image is observed. Meanwhile, adaptive QSVD resists some common geometric attacks, and it improves the robustness of conventional QSVD. With these improvements, our method outperforms conventional QSVD. Its superiority over other state-of-the-art methods is also demonstrated experimentally.

Zhenyu Zhang, Xiangfeng Luo, Tong Liu et al.

Instability and slowness are two main problems in deep reinforcement learning. Even if proximal policy optimization (PPO) is the state of the art, it still suffers from these two problems. We introduce an improved algorithm based on proximal policy optimization, mixed distributed proximal policy optimization (MDPPO), and show that it can accelerate and stabilize the training process. In our algorithm, multiple different policies train simultaneously and each of them controls several identical agents that interact with environments. Actions are sampled by each policy separately as usual, but the trajectories for the training process are collected from all agents, instead of only one policy. We find that if we choose some auxiliary trajectories elaborately to train policies, the algorithm will be more stable and quicker to converge especially in the environments with sparse rewards.

Peng Yin, Yuqing He, Lingyun Xu et al.

Loop Closure Detection (LCD) is the essential module in the simultaneous localization and mapping (SLAM) task. In the current appearance-based SLAM methods, the visual inputs are usually affected by illumination, appearance and viewpoints changes. Comparing to the visual inputs, with the active property, light detection and ranging (LiDAR) based point-cloud inputs are invariant to the illumination and appearance changes. In this paper, we extract 3D voxel maps and 2D top view maps from LiDAR inputs, and the former could capture the local geometry into a simplified 3D voxel format, the later could capture the local road structure into a 2D image format. However, the most challenge problem is to obtain efficient features from 3D and 2D maps to against the viewpoints difference. In this paper, we proposed a synchronous adversarial feature learning method for the LCD task, which could learn the higher level abstract features from different domains without any label data. To the best of our knowledge, this work is the first to extract multi-domain adversarial features for the LCD task in real time. To investigate the performance, we test the proposed method on the KITTI odometry dataset. The extensive experiments results show that, the proposed method could largely improve LCD accuracy even under huge viewpoints differences.