We present Segment Anything Model 2 (SAM 2), a foundation model towards solving promptable visual segmentation in images and videos. We build a data engine, which improves model and data via user interaction, to collect the largest video segmentation dataset to date. Our model is a simple transformer architecture with streaming memory for real-time video processing. SAM 2 trained on our data provides strong performance across a wide range of tasks. In video segmentation, we observe better accuracy, using 3x fewer interactions than prior approaches. In image segmentation, our model is more accurate and 6x faster than the Segment Anything Model (SAM). We believe that our data, model, and insights will serve as a significant milestone for video segmentation and related perception tasks. We are releasing our main model, the dataset, an interactive demo and code.
论文检索
输入标题、作者或关键词，从 5,999 篇学术成果中精准定位
Applications · Computer Vision
The development of 2D foundation models for image segmentation has been significantly advanced by the Segment Anything Model (SAM). However, achieving similar success in 3D models remains a challenge due to issues such as non-unified data formats, poor model scalability, and the scarcity of labeled data with diverse masks. To this end, we propose a 3D promptable segmentation model Point-SAM, focusing on point clouds. We employ an efficient transformer-based architecture tailored for point clouds, extending SAM to the 3D domain. We then distill the rich knowledge from 2D SAM for Point-SAM training by introducing a data engine to generate part-level and object-level pseudo-labels at scale from 2D SAM. Our model outperforms state-of-the-art 3D segmentation models on several indoor and outdoor benchmarks and demonstrates a variety of applications, such as interactive 3D annotation and zero-shot 3D instance proposal.
This paper investigates the conformal isometry hypothesis as a potential explanation for the hexagonal periodic patterns in grid cell response maps. We posit that grid cell activities form a high-dimensional vector in neural space, encoding the agent's position in 2D physical space. As the agent moves, this vector rotates within a 2D manifold in the neural space, driven by a recurrent neural network. The conformal hypothesis proposes that this neural manifold is a conformal isometric embedding of 2D physical space, where local physical distance is preserved by the embedding up to a scaling factor (or unit of metric). Such distance-preserving position embedding is indispensable for path planning in navigation, especially planning local straight path segments. We conduct numerical experiments to show that this hypothesis leads to the hexagonal grid firing patterns by learning maximally distance-preserving position embedding, agnostic to the choice of the recurrent neural network. Furthermore, we present a theoretical explanation of why hexagon periodic patterns emerge by minimizing our loss function by showing that hexagon flat torus is maximally distance preserving.
Deep Learning · Robustness
While audio-visual learning equips models with a richer understanding of the real world by leveraging multiple sensory modalities, this integration also introduces new vulnerabilities to adversarial attacks. In this paper, we present a comprehensive study of the adversarial robustness of audio-visual models, considering both temporal and modality-specific vulnerabilities. We propose two powerful adversarial attacks: 1) a temporal invariance attack that exploits the inherent temporal redundancy across consecutive time segments and 2) a modality misalignment attack that introduces incongruence between the audio and visual modalities. These attacks are designed to thoroughly assess the robustness of audio-visual models against diverse threats. Furthermore, to defend against such attacks, we introduce a novel audio-visual adversarial training framework. This framework addresses key challenges in vanilla adversarial training by incorporating efficient adversarial perturbation crafting tailored to multi-modal data and an adversarial curriculum strategy. Extensive experiments in the Kinetics-Sounds dataset demonstrate that our proposed temporal and modality-based attacks in degrading model performance can achieve state-of-the-art performance, while our adversarial training defense largely improves the adversarial robustness as well as the adversarial training efficiency.
Applications · Computer Vision
The Segment Anything model (SAM) has shown a generalized ability to group image pixels into patches, but applying it to semantic-aware segmentation still faces major challenges. This paper presents SAM-CP, a simple approach that establishes two types of composable prompts beyond SAM and composes them for versatile segmentation. Specifically, given a set of classes (in texts) and a set of SAM patches, the Type-I prompt judges whether a SAM patch aligns with a text label, and the Type-II prompt judges whether two SAM patches with the same text label also belong to the same instance. To decrease the complexity in dealing with a large number of semantic classes and patches, we establish a unified framework that calculates the affinity between (semantic and instance) queries and SAM patches, and then merges patches with high affinity to the query. Experiments show that SAM-CP achieves semantic, instance, and panoptic segmentation in both open and closed domains. In particular, it achieves state-of-the-art performance in open-vocabulary segmentation. Our research offers a novel and generalized methodology for equipping vision foundation models like SAM with multi-grained semantic perception abilities. Codes are released on https://github.com/ucas-vg/SAM-CP.
Applications · Computer Vision
The primary focus of most recent works on open-vocabulary neural fields is extracting precise semantic featuresfrom the VLMs and then consolidating them efficiently into a multi-view consistent 3D neural fieldsrepresentation. However, most existing works over-trusted SAM to regularize image-level CLIP without any further refinement. Moreover, several existing works improved efficiency by dimensionality reduction of semantic features from 2D VLMs before fusing with 3DGS semantic fields, which inevitably leads to multi-view inconsistency. In this work, we propose econSG for open-vocabulary semantic segmentation with 3DGS. Our econSG consists of: 1) A Confidence-region Guided Regularization (CRR) that mutually refines SAM and CLIP to get the best of both worlds for precise semantic features with complete and precise boundaries. 2) A low dimensional contextual space to enforce 3D multi-view consistency while improving computational efficiency by fusing backprojected multi-view 2D features and follow by dimensional reduction directly on the fused 3D features instead of operating on each 2D view separately. Our econSG show state-of-the-art performance on four benchmark datasets compared to the existing methods. Furthermore, we are also the most efficient training among all the methods.
Social Aspects · Trustworthy Machine Learning
The fusion of raw sensor data to create a Bird's Eye View (BEV) representation is critical for autonomous vehicle planning and control. Despite the growing interest in using deep learning models for BEV semantic segmentation, anticipating segmentation errors and enhancing the explainability of these models remain underexplored. This paper introduces a comprehensive benchmark for predictive uncertainty quantification in BEV segmentation, evaluating multiple uncertainty quantification methods across three popular datasets with three representative network architectures. Our study focuses on the effectiveness of quantified uncertainty in detecting misclassified and out-of-distribution (OOD) pixels while also improving model calibration. Through empirical analysis, we uncover challenges in existing uncertainty quantification methods and demonstrate the potential of evidential deep learning techniques, which capture both aleatoric and epistemic uncertainty. To address these challenges, we propose a novel loss function, Uncertainty-Focal-Cross-Entropy (UFCE), specifically designed for highly imbalanced data, along with a simple uncertainty-scaling regularization term that improves both uncertainty quantification and model calibration for BEV segmentation.
Deep Learning · Large Language Models
Vehicle trajectory prediction is a crucial aspect of autonomous driving, which requires extensive trajectory data to train prediction models to understand the complex, varied, and unpredictable patterns of vehicular interactions. However, acquiring real-world data is expensive, so we advocate using Large Language Models (LLMs) to generate abundant and realistic trajectories of interacting vehicles efficiently. These models rely on textual descriptions of vehicle-to-vehicle interactions on a map to produce the trajectories. We introduce Trajectory-LLM (Traj-LLM), a new approach that takes brief descriptions of vehicular interactions as input and generates corresponding trajectories. Unlike language-based approaches that translate text directly to trajectories, Traj-LLM uses reasonable driving behaviors to align the vehicle trajectories with the text. This results in an "interaction-behavior-trajectory" translation process. We have also created a new dataset, Language-to-Trajectory (L2T), which includes 240K textual descriptions of vehicle interactions and behaviors, each paired with corresponding map topologies and vehicle trajectory segments. By leveraging the L2T dataset, Traj-LLM can adapt interactive trajectories to diverse map topologies. Furthermore, Traj-LLM generates additional data that enhances downstream prediction models, leading to consistent performance improvements across public benchmarks. The source code is released at https://github.com/TJU-IDVLab/Traj-LLM.
Large video models, pretrained on massive quantities of amount of Internet video, provide a rich source of physical knowledge about the dynamics and motions of objects and tasks.However, video models are not grounded in the embodiment of an agent, and do not describe how to actuate the world to reach the visual states depicted in a video.To tackle this problem, current methods use a separate vision-based inverse dynamic model trained on embodiment-specific data to map image states to actions. Gathering data to train such a model is often expensive and challenging, and this model is limited to visual settings similar to the ones in which data is available.In this paper, we investigate how to directly ground video models to continuous actions through self-exploration in the embodied environment -- using generated video states as visual goals for exploration.We propose a framework that uses trajectory level action generation in combination with video guidance toenable an agent to solve complex tasks without any external supervision, e.g., rewards, action labels, or segmentation masks.We validate the proposed approach on 8 tasks in Libero, 6 tasks in MetaWorld, 4 tasks in Calvin, and 12 tasks in iThor Visual Navigation. We show how our approach is on par with or even surpasses multiple behavior cloning baselines trained on expert demonstrations while without requiring any action annotations.
Applications · Health
Multi-modal multi-task learning holds significant promise in tackling complex diagnostic tasks and many significant medical imaging problems. It fulfills the needs in real-world diagnosis protocol to leverage information from different data sources and simultaneously perform mutually informative tasks. However, medical imaging domains introduce two key challenges: dynamic modality fusion and modality-task dependence. The quality and amount of task-related information from different modalities could vary significantly across patient samples, due to biological and demographic factors. Traditional fusion methods apply fixed combination strategies that fail to capture this dynamic relationship, potentially underutilizing modalities that carry stronger diagnostic signals for specific patients. Additionally, different clinical tasks may require dynamic feature selection and combination from various modalities, a phenomenon we term “modality-task dependence.” To address these issues, we propose M4oE, a novel Multi-modal Multi-task Mixture of Experts framework for precise Medical diagnosis. M4oE comprises Modality-Specific (MSoE) modules and a Modality-shared Modality-Task MoE (MToE) module. With collaboration from both modules, our model dynamically decomposes and learns distinct and shared information from different modalities and achieves dynamic fusion. MToE provides a joint probability model of modalities and tasks by using experts as a link and encourages experts to learn modality-task dependence via conditional mutual information loss. By doing so, M4oE offers sample and population-level interpretability of modality contributions. We evaluate M4oE on four public multi-modal medical benchmark datasets for solving two important medical diagnostic problems including breast cancer screening and retinal disease diagnosis. Results demonstrate our method's superiority over state-of-the-art methods under different metrics of classification and segmentation tasks like Accuracy, AUROC, AUPRC, and DICE.
Applications · Health
Electrocardiogram (ECG) is essential for the clinical diagnosis of arrhythmias and other heart diseases, but deep learning methods based on ECG often face limitations due to the need for high-quality annotations. Although previous ECG self-supervised learning (eSSL) methods have made significant progress in representation learning from unannotated ECG data, they typically treat ECG signals as ordinary time-series data, segmenting the signals using fixed-size and fixed-step time windows, which often ignore the form and rhythm characteristics and latent semantic relationships in ECG signals. In this work, we introduce a novel perspective on ECG signals, treating heartbeats as words and rhythms as sentences. Based on this perspective, we first designed the QRS-Tokenizer, which generates semantically meaningful ECG sentences from the raw ECG signals. Building on these, we then propose HeartLang, a novel self-supervised learning framework for ECG language processing, learning general representations at form and rhythm levels. Additionally, we construct the largest heartbeat-based ECG vocabulary to date, which will further advance the development of ECG language processing. We evaluated HeartLang across six public ECG datasets, where it demonstrated robust competitiveness against other eSSL methods. Our data and code are publicly available at https://github.com/PKUDigitalHealth/HeartLang.
Applications · Computer Vision
Existing Video Scene Graph Generation (VidSGG) studies are trained in a fully supervised manner, which requires all frames in a video to be annotated, thereby incurring high annotation cost compared to Image Scene Graph Generation (ImgSGG). Although the annotation cost of VidSGG can be alleviated by adopting a weakly supervised approach commonly used for ImgSGG (WS-ImgSGG) that uses image captions, there are two key reasons that hinder such a naive adoption: 1) Temporality within video captions, i.e., unlike image captions, video captions include temporal markers (e.g., before, while, then, after) that indicate time-related details, and 2) Variability in action duration, i.e., unlike human actions in image captions, human actions in video captions unfold over varying duration. To address these issues, we propose a Natural Language-based Video Scene Graph Generation (NL-VSGG) framework that only utilizes the readily available video captions for training a VidSGG model. NL-VSGG consists of two key modules: Temporality-aware Caption Segmentation (TCS) module and Action Duration Variability-aware caption-frame alignment (ADV) module. Specifically, TCS segments the video captions into multiple sentences in a temporal order based on a Large Language Model (LLM), and ADV aligns each segmented sentence with appropriate frames considering the variability in action duration. Our approach leads to a significant enhancement in performance compared to simply applying the WS-ImgSGG pipeline to VidSGG on the Action Genome dataset. As a further benefit of utilizing the video captions as weak supervision, we show that the VidSGG model trained by NL-VSGG is able to predict a broader range of action classes that are not included in the training data, which makes our framework practical in reality.
Applications · Computer Vision
Distance field-based implicit representations like signed/unsigned distance fields have recently gained prominence in geometry modeling and analysis. However, these distance fields are reliant on the closest distance of points to the surface, introducing inaccuracies when interpolating along cube edges during surface extraction. Additionally, their gradients are ill-defined at certain locations, causing distortions in the extracted surfaces. To address this limitation, we propose Shape as Line Segments (SALS), an accurate and efficient implicit geometry representation based on attributed line segments, which can handle arbitrary structures. Unlike previous approaches, SALS leverages a differentiable Line Segment Field to implicitly capture the spatial relationship between line segments and the surface. Each line segment is associated with two key attributes, intersection flag and ratio, from which we propose edge-based dual contouring to extract a surface. We further implement SALS with a neural network, producing a new neural implicit presentation. Additionally, based on SALS, we design a novel learning-based pipeline for reconstructing surfaces from 3D point clouds. We conduct extensive experiments, showcasing the significant advantages of our methods over state-of-the-art methods.The source code is available at https://github.com/rsy6318/SALS.
Applications · Computer Vision
We introduce MIM (Masked Image Modeling)-Refiner, a contrastive learning boost for pre-trained MIM models. MIM-Refiner is motivated by the insight that strong representations within MIM models generally reside in intermediate layers. Accordingly, MIM-Refiner leverages multiple instance discrimination (ID) heads that are connected to different intermediate layers. In each head, a nearest neighbor ID objective constructs clusters that capture semantic information which improves performance on downstream tasks, including off-the-shelf and fine-tuning settings.The refinement process is short and simple - yet highly effective. Within a few epochs, we refine the features of MIM models from subpar to state-of-the-art, off-the-shelf features. Refining a ViT-H, pre-trained with data2vec 2.0 on ImageNet-1K, sets a new state-of-the-art in linear probing (84.7\%) and low-shot classification among models that are pre-trained on ImageNet-1K. MIM-Refiner efficiently combines the advantages of MIM and ID objectives, enabling scaling ID objectives to billion parameter models using relatively little compute. MIM-Refiner compares favorably against previous state-of-the-art SSL models on various benchmarks such as low-shot classification, long-tailed classification and semantic segmentation.
Applications · Time Series
Spiking Neural Networks (SNNs) offer a promising, biologically inspired approach for processing spatiotemporal data, particularly for time series forecasting.However, conventional neuron models like the Leaky Integrate-and-Fire (LIF) struggle to capture long-term dependencies and effectively process multi-scale temporal dynamics.To overcome these limitations, we introduce the Temporal Segment Leaky Integrate-and-Fire (TS-LIF) model, featuring a novel dual-compartment architecture.The dendritic and somatic compartments specialize in capturing distinct frequency components, providing functional heterogeneity that enhances the neuron's ability to process both low- and high-frequency information.Furthermore, the newly introduced direct somatic current injection reduces information loss during intra-neuronal transmission, while dendritic spike generation improves multi-scale information extraction.We provide a theoretical stability analysis of the TS-LIF model and explain how each compartment contributes to distinct frequency response characteristics.Experimental results show that TS-LIF outperforms traditional SNNs in time series forecasting, demonstrating better accuracy and robustness, even with missing data.TS-LIF advances the application of SNNs in time-series forecasting, providing a biologically inspired approach that captures complex temporal dynamics and offers potential for practical implementation in diverse forecasting scenarios.
Applications · Everything Else
Large Language Models (LLMs) applied to code-related applications have emerged as a prominent field, attracting significant interest from academia and industry. However, as new and improved LLMs are developed, existing evaluation benchmarks (e.g., HumanEvla, MBPP) are no longer sufficient for assessing their capabilities suffering from data contamination, overfitting, saturation, and focus on merely code generation. In this work, we propose LiveCodeBench, a comprehensive and contamination-free evaluation of LLMs for code, which collects new problems over time from contests across three competition platforms, Leetcode, Atcoder, and Codeforces. Notably, our benchmark also focuses on a broader range of code-related capabilities, such as self-repair, code execution, and test output prediction, beyond just code generation. Currently, LiveCodeBench hosts over six hundred coding problems that were published between May 2023 and Aug 2024. We evaluate over 50 LLMs on LiveCodeBench (LCB for brevity) presenting the largest evaluation study of code LLMs on competition problems. Based on the study, we present novel empirical findings on contamination, overfitting, and holistic evaluations. We demonstrate that time-segmented evaluations serve as a robust approach to evade contamination; they are successful at detecting contamination across a wide range of open and closed models including GPT-4O, Claude, Deepseek, and Codestral. Next, we highlight overfitting and saturation of traditional coding benchmarks like HumanEvla and demonstrate LCB allows more reliable evaluations. Finally, our holistic evaluation scenarios allow for measuring the different capabilities of programming agents in isolation.
fVDB : A Deep-Learning Framework for Sparse, Large Scale, and High Performance Spatial Intelligence
PDF ↗We present fVDB, a novel GPU-optimized framework for deep learning on large-scale 3D data. fVDB provides a complete set of differentiable primitives to build deep learning architectures for common tasks in 3D learning such as convolution, pooling, attention, ray-tracing, meshing, etc. fVDB simultaneously provides a much larger feature set (primitives and operators) than established frameworks with no loss in efficiency: our operators match or exceed the performance of other frameworks with narrower scope. Furthermore, fVDB can process datasets with much larger footprint and spatial resolution than prior works, while providing a competitive memory footprint on small inputs. To achieve this combination of versatility and performance, fVDB relies on a single novel VDB index grid acceleration structure paired with several key innovations including GPU accelerated sparse grid construction, convolution using tensorcores, fast ray tracing kernels using a Hierarchical Digital Differential Analyzer algorithm (HDDA), and jagged tensors. Our framework is fully integrated with PyTorch enabling interoperability with existing pipelines, and we demonstrate its effectiveness on a number of representative tasks such as large-scale point-cloud segmentation, high resolution 3D generative modeling, unbounded scale Neural Radiance Fields, and large-scale point cloud reconstruction.
Computer Graphics has a long history in the design of effective algorithms for handling contact and friction between solid objects. For the sake of simplicity and versatility, most methods rely on low-order primitives such as line segments or triangles, both for the detection and the response stages. In this paper we carefully analyse, in the case of fibre systems, the impact of such choices on the retrieved contact forces. We highlight the presence of artifacts in the force response that are tightly related to the low-order geometry used for contact detection. Our analysis draws upon thorough comparisons between the high-order super-helix model and the low-order discrete elastic rod model. These reveal that when coupled to a low-order, segment-based detection scheme, both models yield spurious jumps in the contact force profile. Moreover, these artifacts are shown to be all the more visible as the geometry of fibres at contact is curved. In order to remove such artifacts we develop an accurate high-order detection scheme between two smooth curves, which relies on an efficient adaptive pruning strategy. We use this algorithm to detect contact between super-helices at high precision, allowing us to recover, in the range of wavy to highly curly fibres, much smoother force profiles during sliding motion than with a classical segment-based strategy. Furthermore, we show that our approach offers better scaling properties in terms of efficiency vs. precision compared to segment-based approaches, making it attractive for applications where accurate and reliable forces are desired. Finally, we demonstrate the robustness and accuracy of our fully high-order approach on a challenging hair combing scenario.
We present an unsupervised 3D shape co-segmentation method which learns a set of deformable part templates from a shape collection. To accommodate structural variations in the collection, our network composes each shape by a selected subset of template parts which are affine-transformed. To maximize the expressive power of the part templates, we introduce a per-part deformation network to enable the modeling of diverse parts with substantial geometry variations, while imposing constraints on the deformation capacity to ensure fidelity to the originally represented parts. We also propose a training scheme to effectively overcome local minima. Architecturally, our network is a branched autoencoder, with a CNN encoder taking a voxel shape as input and producing per-part transformation matrices, latent codes, and part existence scores, and the decoder outputting point occupancies to define the reconstruction loss. Our network, coined DAE-Net for Deforming Auto-Encoder, can achieve unsupervised 3D shape co-segmentation that yields fine-grained, compact, and meaningful parts that are consistent across diverse shapes. We conduct extensive experiments on the ShapeNet Part dataset, DFAUST, and an animal subset of Objaverse to show superior performance over prior methods. Code and data are available at https://github.com/czq142857/DAE-Net.
As 3D content becomes increasingly prevalent, there’s a growing focus on the development of engagements with 3D virtual content. Unfortunately, traditional techniques for creating, editing, and interacting with this content are fraught with difficulties. They tend to be not only engineering-intensive but also require extensive expertise, which adds to the frustration and inefficiency in virtual object manipulation. Our proposed VR-GS system represents a leap forward in human-centered 3D content interaction, offering a seamless and intuitive user experience. By developing a physical dynamics-aware interactive Gaussian Splatting (GS) in a Virtual Reality (VR) setting, and constructing a highly efficient two-level embedding strategy alongside deformable body simulations, VR-GS ensures real-time execution with highly realistic dynamic responses. The components of our system are designed for high efficiency and effectiveness, starting from detailed scene reconstruction and object segmentation, advancing through multi-view image in-painting, and extending to interactive physics-based editing. The system also incorporates real-time deformation embedding and dynamic shadow casting, ensuring a comprehensive and engaging virtual experience.