Pinhao Song

Zhan Chen, Hong Liu, Tianyu Guo et al.

Self-supervised skeleton-based action recognition with contrastive learning has attracted much attention. Recent literature shows that data augmentation and large sets of contrastive pairs are crucial in learning such representations. In this paper, we found that directly extending contrastive pairs based on normal augmentations brings limited returns in terms of performance, because the contribution of contrastive pairs from the normal data augmentation to the loss get smaller as training progresses. Therefore, we delve into hard contrastive pairs for contrastive learning. Motivated by the success of mixing augmentation strategy which improves the performance of many tasks by synthesizing novel samples, we propose SkeleMixCLR: a contrastive learning framework with a spatio-temporal skeleton mixing augmentation (SkeleMix) to complement current contrastive learning approaches by providing hard contrastive samples. First, SkeleMix utilizes the topological information of skeleton data to mix two skeleton sequences by randomly combing the cropped skeleton fragments (the trimmed view) with the remaining skeleton sequences (the truncated view). Second, a spatio-temporal mask pooling is applied to separate these two views at the feature level. Third, we extend contrastive pairs with these two views. SkeleMixCLR leverages the trimmed and truncated views to provide abundant hard contrastive pairs since they involve some context information from each other due to the graph convolution operations, which allows the model to learn better motion representations for action recognition. Extensive experiments on NTU-RGB+D, NTU120-RGB+D, and PKU-MMD datasets show that SkeleMixCLR achieves state-of-the-art performance. Codes are available at https://github.com/czhaneva/SkeleMixCLR.

Xutao Liang, Pinhao Song

Self-attention is one of the most successful designs in deep learning, which calculates the similarity of different tokens and reconstructs the feature based on the attention matrix. Originally designed for NLP, self-attention is also popular in computer vision, and can be categorized into pixel-level attention and patch-level attention. In object detection, RoI features can be seen as patches from base feature maps. This paper aims to apply the attention module to RoI features to improve performance. Instead of employing an original self-attention module, we choose the external attention module, a modified self-attention with reduced parameters. With the proposed double head structure and the Positional Encoding module, our method can achieve promising performance in object detection. The comprehensive experiments show that it achieves promising performance, especially in the underwater object detection dataset. The code will be avaiable in: https://github.com/zsyasd/Excavating-RoI-Attention-for-Underwater-Object-Detection

Linhui Dai, Hong Liu, Pinhao Song et al.

Underwater object detection (UOD) plays a significant role in aquaculture and marine environmental protection. Considering the challenges posed by low contrast and low-light conditions in underwater environments, several underwater image enhancement (UIE) methods have been proposed to improve the quality of underwater images. However, only using the enhanced images does not improve the performance of UOD, since it may unavoidably remove or alter critical patterns and details of underwater objects. In contrast, we believe that exploring the complementary information from the two domains is beneficial for UOD. The raw image preserves the natural characteristics of the scene and texture information of the objects, while the enhanced image improves the visibility of underwater objects. Based on this perspective, we propose a Gated Cross-domain Collaborative Network (GCC-Net) to address the challenges of poor visibility and low contrast in underwater environments, which comprises three dedicated components. Firstly, a real-time UIE method is employed to generate enhanced images, which can improve the visibility of objects in low-contrast areas. Secondly, a cross-domain feature interaction module is introduced to facilitate the interaction and mine complementary information between raw and enhanced image features. Thirdly, to prevent the contamination of unreliable generated results, a gated feature fusion module is proposed to adaptively control the fusion ratio of cross-domain information. Our method presents a new UOD paradigm from the perspective of cross-domain information interaction and fusion. Experimental results demonstrate that the proposed GCC-Net achieves state-of-the-art performance on four underwater datasets.

Pinhao Song, Pengteng Li, Linhui Dai et al.

Complicated underwater environments bring new challenges to object detection, such as unbalanced light conditions, low contrast, occlusion, and mimicry of aquatic organisms. Under these circumstances, the objects captured by the underwater camera will become vague, and the generic detectors often fail on these vague objects. This work aims to solve the problem from two perspectives: uncertainty modeling and hard example mining. We propose a two-stage underwater detector named boosting R-CNN, which comprises three key components. First, a new region proposal network named RetinaRPN is proposed, which provides high-quality proposals and considers objectness and IoU prediction for uncertainty to model the object prior probability. Second, the probabilistic inference pipeline is introduced to combine the first-stage prior uncertainty and the second-stage classification score to model the final detection score. Finally, we propose a new hard example mining method named boosting reweighting. Specifically, when the region proposal network miscalculates the object prior probability for a sample, boosting reweighting will increase the classification loss of the sample in the R-CNN head during training, while reducing the loss of easy samples with accurately estimated priors. Thus, a robust detection head in the second stage can be obtained. During the inference stage, the R-CNN has the capability to rectify the error of the first stage to improve the performance. Comprehensive experiments on two underwater datasets and two generic object detection datasets demonstrate the effectiveness and robustness of our method.

Yurui Du, Pinhao Song, Yutong Hu et al.

A central challenge of visual control with model-based reinforcement learning (RL) is reliable long-horizon planning: long rollouts with learned latent dynamics exhibit branching futures and multi-modal action-value distributions. In addition, compounding model errors amplified by visual occlusions make deep imagination brittle. We present ELVIS, a latent model predictive controller (MPC) designed to make long-horizon planning practical. ELVIS plans in a Dreamer-style recurrent state space model (RSSM) and replaces standard unimodal model predictive path integral (MPPI) with a Gaussian-mixture MPPI that maintains multiple coherent hypotheses over long horizons, avoiding mode averaging under branching rollouts. In parallel, ELVIS stabilizes deep imagination with a shared uncertainty-aware lambda-return: an ensemble of latent critics defines an upper-confidence-bound (UCB) score that gates a time-varying lambda, adaptively trading off bootstrapping versus look-ahead to limit compounding error during planning. The same return is used both to train an actor-critic prior from imagined rollouts and to score candidate trajectories inside GMM-MPPI, aligning RL objectives with the planner's long-horizon optimization. On fourteen DeepMind Control Suite visual tasks, ELVIS establishes state-of-the-art performance compared with TD-MPC2 and DreamerV3. Finally, ELVIS transfers zero-shot to a real-world sand-spraying task with severe occlusions, improving surface-quality metrics and demonstrating robustness beyond simulation.

Linhui Dai, Hong Liu, Hao Tang et al.

Arbitrary-oriented object detection (AOOD) is a challenging task to detect objects in the wild with arbitrary orientations and cluttered arrangements. Existing approaches are mainly based on anchor-based boxes or dense points, which rely on complicated hand-designed processing steps and inductive bias, such as anchor generation, transformation, and non-maximum suppression reasoning. Recently, the emerging transformer-based approaches view object detection as a direct set prediction problem that effectively removes the need for hand-designed components and inductive biases. In this paper, we propose an Arbitrary-Oriented Object DEtection TRansformer framework, termed AO2-DETR, which comprises three dedicated components. More precisely, an oriented proposal generation mechanism is proposed to explicitly generate oriented proposals, which provides better positional priors for pooling features to modulate the cross-attention in the transformer decoder. An adaptive oriented proposal refinement module is introduced to extract rotation-invariant region features and eliminate the misalignment between region features and objects. And a rotation-aware set matching loss is used to ensure the one-to-one matching process for direct set prediction without duplicate predictions. Our method considerably simplifies the overall pipeline and presents a new AOOD paradigm. Comprehensive experiments on several challenging datasets show that our method achieves superior performance on the AOOD task.

Linhui Dai, Hong Liu, Pinhao Song et al.

Underwater object detection (UOD) is crucial for marine economic development, environmental protection, and the planet's sustainable development. The main challenges of this task arise from low-contrast, small objects, and mimicry of aquatic organisms. The key to addressing these challenges is to focus the model on obtaining more discriminative information. We observe that the edges of underwater objects are highly unique and can be distinguished from low-contrast or mimicry environments based on their edges. Motivated by this observation, we propose an Edge-guided Representation Learning Network, termed ERL-Net, that aims to achieve discriminative representation learning and aggregation under the guidance of edge cues. Firstly, we introduce an edge-guided attention module to model the explicit boundary information, which generates more discriminative features. Secondly, a feature aggregation module is proposed to aggregate the multi-scale discriminative features by regrouping them into three levels, effectively aggregating global and local information for locating and recognizing underwater objects. Finally, we propose a wide and asymmetric receptive field block to enable features to have a wider receptive field, allowing the model to focus on more small object information. Comprehensive experiments on three challenging underwater datasets show that our method achieves superior performance on the UOD task.

Pinhao Song, Pengteng Li, Erwin Aertbelien et al.

We address the problem of (a) predicting the trajectory of an arm reaching motion, based on a few seconds of the motion's onset, and (b) leveraging this predictor to facilitate shared-control manipulation tasks, easing the cognitive load of the operator by assisting them in their anticipated direction of motion. Our novel intent estimator, dubbed the \emph{Robot Trajectron} (RT), produces a probabilistic representation of the robot's anticipated trajectory based on its recent position, velocity and acceleration history. Taking arm dynamics into account allows RT to capture the operator's intent better than other SOTA models that only use the arm's position, making it particularly well-suited to assist in tasks where the operator's intent is susceptible to change. We derive a novel shared-control solution that combines RT's predictive capacity to a representation of the locations of potential reaching targets. Our experiments demonstrate RT's effectiveness in both intent estimation and shared-control tasks. We will make the code and data supporting our experiments publicly available at https://github.com/mousecpn/Robot-Trajectron.git.

Yutong Hu, Pinhao Song, Kehan Wen et al.

We present a method that reduces, by an order of magnitude, the time and memory needed to train multi-task vision-language robotic diffusion policies. This improvement arises from a previously underexplored distinction between action diffusion and the image diffusion techniques that inspired it: In image generation, the target is high-dimensional. By contrast, in action generation, the dimensionality of the target is comparatively small, and only the image condition is high-dimensional. Our approach, \emph{Mini Diffuser}, exploits this asymmetry by introducing \emph{two-level minibatching}, which pairs multiple noised action samples with each vision-language condition, instead of the conventional one-to-one sampling strategy. To support this batching scheme, we introduce architectural adaptations to the diffusion transformer that prevent information leakage across samples while maintaining full conditioning access. In RLBench simulations, Mini-Diffuser achieves 95\% of the performance of state-of-the-art multi-task diffusion policies, while using only 5\% of the training time and 7\% of the memory. Real-world experiments further validate that Mini-Diffuser preserves the key strengths of diffusion-based policies, including the ability to model multimodal action distributions and produce behavior conditioned on diverse perceptual inputs. Code available at mini-diffuse-actor.github.io

Tao Wang, Hong Liu, Pinhao Song et al.

Occluded person re-identification is a challenging task as human body parts could be occluded by some obstacles (e.g. trees, cars, and pedestrians) in certain scenes. Some existing pose-guided methods solve this problem by aligning body parts according to graph matching, but these graph-based methods are not intuitive and complicated. Therefore, we propose a transformer-based Pose-guided Feature Disentangling (PFD) method by utilizing pose information to clearly disentangle semantic components (e.g. human body or joint parts) and selectively match non-occluded parts correspondingly. First, Vision Transformer (ViT) is used to extract the patch features with its strong capability. Second, to preliminarily disentangle the pose information from patch information, the matching and distributing mechanism is leveraged in Pose-guided Feature Aggregation (PFA) module. Third, a set of learnable semantic views are introduced in transformer decoder to implicitly enhance the disentangled body part features. However, those semantic views are not guaranteed to be related to the body without additional supervision. Therefore, Pose-View Matching (PVM) module is proposed to explicitly match visible body parts and automatically separate occlusion features. Fourth, to better prevent the interference of occlusions, we design a Pose-guided Push Loss to emphasize the features of visible body parts. Extensive experiments over five challenging datasets for two tasks (occluded and holistic Re-ID) demonstrate that our proposed PFD is superior promising, which performs favorably against state-of-the-art methods. Code is available at https://github.com/WangTaoAs/PFD_Net

Pinhao Song, Yutong Hu, Pengteng Li et al.

We propose a new volumetric grasp model that is equivariant to rotations around the vertical axis, leading to a significant improvement in sample efficiency. Our model employs a tri-plane volumetric feature representation -- i.e., the projection of 3D features onto three canonical planes. We introduce a novel tri-plane feature design in which features on the horizontal plane are equivariant to 90° rotations, while the sum of features from the other two planes remains invariant to the same transformations. This design is enabled by a new deformable steerable convolution, which combines the adaptability of deformable convolutions with the rotational equivariance of steerable ones. This allows the receptive field to adapt to local object geometry while preserving equivariance properties. We further develop equivariant adaptations of two state-of-the-art volumetric grasp planners, GIGA and IGD. Specifically, we derive a new equivariant formulation of IGD's deformable attention mechanism and propose an equivariant generative model of grasp orientations based on flow matching. We provide a detailed analytical justification of the proposed equivariance properties and validate our approach through extensive simulated and real-world experiments. Our results demonstrate that the proposed projection-based design significantly reduces both computational and memory costs. Moreover, the equivariant grasp models built on top of our tri-plane features consistently outperform their non-equivariant counterparts, achieving higher performance with only a modest computational overhead. Video and code can be viewed in: https://mousecpn.github.io/evg-page/

Pinhao Song

Object detection aims to obtain the location and the category of specific objects in a given image, which includes two tasks: classification and location. In recent years, researchers tend to apply object detection to underwater robots equipped with vision systems to complete tasks including seafood fishing, fish farming, biodiversity monitoring and so on. However, the diversity and complexity of underwater environments bring new challenges to object detection. First, aquatic organisms tend to live together, which leads to severe occlusion. Second, theaquatic organisms are good at hiding themselves, which have a similar color to the background. Third, the various water quality and changeable and extreme lighting conditions lead to the distorted, low contrast, blue or green images obtained by the underwater camera, resulting in domain shift. And the deep model is generally vulnerable to facing domain shift. Fourth, the movement of the underwater robot leads to the blur of the captured image and makes the water muddy, which results in low visibility of the water. This paper investigates the problems brought by the underwater environment mentioned above, and aims to design a high-performance and robust underwater object detector.

Pengteng Li, Yunfan Lu, Pinhao Song et al.

In this paper, we propose the first Structure-from-Motion (SfM)-free deblurring 3D Gaussian Splatting method via event camera, dubbed DeblurSplat. We address the motion-deblurring problem in two ways. First, we leverage the pretrained capability of the dense stereo module (DUSt3R) to directly obtain accurate initial point clouds from blurred images. Without calculating camera poses as an intermediate result, we avoid the cumulative errors transfer from inaccurate camera poses to the initial point clouds' positions. Second, we introduce the event stream into the deblur pipeline for its high sensitivity to dynamic change. By decoding the latent sharp images from the event stream and blurred images, we can provide a fine-grained supervision signal for scene reconstruction optimization. Extensive experiments across a range of scenes demonstrate that DeblurSplat not only excels in generating high-fidelity novel views but also achieves significant rendering efficiency compared to the SOTAs in deblur 3D-GS.

Pengteng Li, Pinhao Song, Wuyang Li et al.

We introduce SEE&TREK, the first training-free prompting framework tailored to enhance the spatial understanding of Multimodal Large Language Models (MLLMS) under vision-only constraints. While prior efforts have incorporated modalities like depth or point clouds to improve spatial reasoning, purely visualspatial understanding remains underexplored. SEE&TREK addresses this gap by focusing on two core principles: increasing visual diversity and motion reconstruction. For visual diversity, we conduct Maximum Semantic Richness Sampling, which employs an off-the-shell perception model to extract semantically rich keyframes that capture scene structure. For motion reconstruction, we simulate visual trajectories and encode relative spatial positions into keyframes to preserve both spatial relations and temporal coherence. Our method is training&GPU-free, requiring only a single forward pass, and can be seamlessly integrated into existing MLLM'S. Extensive experiments on the VSI-B ENCH and STI-B ENCH show that S EE &T REK consistently boosts various MLLM S performance across diverse spatial reasoning tasks with the most +3.5% improvement, offering a promising path toward stronger spatial intelligence.

Xisheng Li, Wei Li, Pinhao Song et al.

The inherent characteristics and light fluctuations of water bodies give rise to the huge difference between different layers and regions in underwater environments. When the test set is collected in a different marine area from the training set, the issue of domain shift emerges, significantly compromising the model's ability to generalize. The Domain Adversarial Learning (DAL) training strategy has been previously utilized to tackle such challenges. However, DAL heavily depends on manually one-hot domain labels, which implies no difference among the samples in the same domain. Such an assumption results in the instability of DAL. This paper introduces the concept of Domain Similarity-Perceived Label Assignment (DSP). The domain label for each image is regarded as its similarity to the specified domains. Through domain-specific data augmentation techniques, we achieved state-of-the-art results on the underwater cross-domain object detection benchmark S-UODAC2020. Furthermore, we validated the effectiveness of our method in the Cityscapes dataset.

Yang Chen, Pinhao Song, Hong Liu et al.

The performance of existing underwater object detection methods degrades seriously when facing domain shift caused by complicated underwater environments. Due to the limitation of the number of domains in the dataset, deep detectors easily memorize a few seen domains, which leads to low generalization ability. There are two common ideas to improve the domain generalization performance. First, it can be inferred that the detector trained on as many domains as possible is domain-invariant. Second, for the images with the same semantic content in different domains, their hidden features should be equivalent. This paper further excavates these two ideas and proposes a domain generalization framework (named DMC) that learns how to generalize across domains from Domain Mixup and Contrastive Learning. First, based on the formation of underwater images, an image in an underwater environment is the linear transformation of another underwater environment. Thus, a style transfer model, which outputs a linear transformation matrix instead of the whole image, is proposed to transform images from one source domain to another, enriching the domain diversity of the training data. Second, mixup operation interpolates different domains on the feature level, sampling new domains on the domain manifold. Third, contrastive loss is selectively applied to features from different domains to force the model to learn domain invariant features but retain the discriminative capacity. With our method, detectors will be robust to domain shift. Also, a domain generalization benchmark S-UODAC2020 for detection is set up to measure the performance of our method. Comprehensive experiments on S-UODAC2020 and two object recognition benchmarks (PACS and VLCS) demonstrate that the proposed method is able to learn domain-invariant representations, and outperforms other domain generalization methods.

Hong Liu, Pinhao Song, Runwei Ding

A General Underwater Object Detector (GUOD) should perform well on most of underwater circumstances. However, with limited underwater dataset, conventional object detection methods suffer from domain shift severely. This paper aims to build a GUOD with small underwater dataset with limited types of water quality. First, we propose a data augmentation method Water Quality Transfer (WQT) to increase domain diversity of the original small dataset. Second, for mining the semantic information from data generated by WQT, DG-YOLO is proposed, which consists of three parts: YOLOv3, DIM and IRM penalty. Finally, experiments on original and synthetic URPC2019 dataset prove that WQT+DG-YOLO achieves promising performance of domain generalization in underwater object detection.