Integrating large language models (LLMs) into autonomous driving has attracted significant attention with the hope of improving generalization and explainability. However, existing methods often focus on either driving or vision-language understanding but achieving both high driving performance and extensive language understanding remains challenging. In addition, the dominant approach to tackle vision-language understanding is using visual question answering. However, for autonomous driving, this is only useful if it is aligned with the action space. Otherwise, the model's answers could be inconsistent with its behavior. Therefore, we propose a model that can handle three different tasks: (1) closed-loop driving, (2) vision-language understanding, and (3) language-action alignment. Our model SimLingo is based on a vision language model (VLM) and works using only camera, excluding expensive sensors like LiDAR. SimLingo obtains state-of-the-art performance on the widely used CARLA simulator on the Bench2Drive benchmark and is the winning entry at the CARLA challenge 2024. Additionally, we achieve strong results in a wide variety of language-related tasks while maintaining high driving performance.
论文检索
输入标题、作者或关键词，从 9,654 篇学术成果中精准定位
As a globally celebrated sport, soccer has attracted widespread interest from fans over the world. This paper aims to develop a comprehensive multi-modal framework for soccer video understanding.Specifically, we make the following contributions in this paper:(i) we introduce **SoccerReplay-1988**, the largest multi-modal soccer dataset to date, featuring videos and detailed annotations from 1,988 complete matches, with an automated annotation pipeline;(ii) we present the first visual-language foundation model in the soccer domain, **MatchVision**, which leverages spatiotemporal information across soccer videos and excels in various downstream tasks;(iii) we conduct extensive experiments and ablation studies on action classification, commentary generation, and multi-view foul recognition,and demonstrate state-of-the-art performance on all of them, substantially outperforming existing models, which has demonstrated the superiority of our proposed data and model. We believe that this work will offer a standard paradigm for sports understanding research. The code and model will be publicly available for reproduction.
Multimodal unsupervised domain adaptation leverages unlabeled data in the target domain to enhance multimodal systems continuously. While current state-of-the-art methods encourage interaction between sub-models of different modalities through pseudo-labeling and feature-level exchange, varying sample quality across modalities can lead to the propagation of inaccurate information, resulting in error accumulation. To address this, we propose Modal-Affinity Multimodal Domain Adaptation (MODfinity), a method that dynamically manages multimodal information flow through fine-grained control over teacher model selection, guiding information intertwining at both feature and label levels. By treating labels as an independent modality, MODfinity enables balanced performance assessment across modalities, employing a novel modal-affinity measurement to evaluate information quality. Additionally, we introduce a modal-affinity distillation technique to control sample-level information exchange, ensuring reliable multimodal interaction based on affinity evaluations within the feature space. Extensive experiments on three multimodal datasets demonstrate that our framework consistently outperforms state-of-the-art methods, particularly in high-noise environments.
Diffusion Bridge: Leveraging Diffusion Model to Reduce the Modality Gap Between Text and Vision for Zero-Shot Image Captioning
PDF ↗The modality gap between vision and text embeddings in CLIP presents a significant challenge for zero-shot image captioning, limiting effective cross-modal representation. Traditional approaches, such as noise injection and memory-based similarity matching, attempt to address this gap, yet these methods either rely on indirect alignment or relatively naive solutions with heavy computation. Diffusion Bridge introduces a novel approach to directly reduce this modality gap by leveraging Denoising Diffusion Probabilistic Models (DDPM), trained exclusively on text embeddings to model their distribution. Our approach is motivated by the observation that, while paired vision and text embeddings are relatively close, a modality gap still exists due to stable regions created by the contrastive loss. This gap can be interpreted as noise in cross-modal mappings, which we approximate as Gaussian noise. To bridge this gap, we employ a reverse diffusion process, where image embeddings are strategically introduced at an intermediate step in the reverse process, allowing them to be refined progressively toward the text embedding distribution. This process transforms vision embeddings into text-like representations closely aligned with paired text embeddings, effectively minimizing discrepancies between modalities. Experimental results demonstrate that these text-like vision embeddings significantly enhance alignment with their paired text embeddings, leading to improved zero-shot captioning performance on MSCOCO and Flickr30K. Diffusion Bridge achieves competitive results without reliance on memory banks or entity-driven methods, offering a novel pathway for cross-modal alignment and opening new possibilities for the application of diffusion models in multi-modal tasks. The source code is available at: https://github.com/mongeoroo/diffusion-bridge
Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions
PDF ↗Recent advances in text-to-image (T2I) diffusion models have significantly improved the quality of generated images. However, providing efficient control over individual subjects, particularly the attributes characterizing them, remains a key challenge. While existing methods have introduced mechanisms to modulate attribute expression, they typically provide either detailed, object-specific localization of such a modification or full-scale fine-grained, nuanced control of attributes. No current approach offers both simultaneously, resulting in a gap when trying to achieve precise continuous and subject-specific attribute modulation in image generation. In this work, we demonstrate that token-level directions exist within commonly used CLIP text embeddings that enable fine-grained, subject-specific control of high-level attributes in T2I models. We introduce two methods to identify these directions: a simple, optimization-free technique and a learning-based approach that utilizes the T2I model to characterize semantic concepts more specifically. Our methods allow the augmentation of the prompt text input, enabling fine-grained control over multiple attributes of individual subjects simultaneously, without requiring any modifications to the diffusion model itself. This approach offers a unified solution that fills the gap between global and localized control, providing competitive flexibility and precision in text-guided image generation.
Multi-task learning (MTL) is a paradigm that aims to improve the generalization of models by simultaneously learning multiple related tasks, leveraging shared representations and task-specific information to enhance performance on individual tasks. However, existing work has shown that MTL can potentially hinder generalization, with one key factor being spurious correlations between tasks. Owing to the knowledge-sharing property, the per-task predictors are more likely to develop reliance on spurious features. Most existing approaches address this issue through distributional robustness, aiming to maintain consistent performance across different distributions under unknown covariate shifts. However, this formulation lacks theoretical guarantees and can be sensitive to the construction of covariate shifts. In this work, we propose a novel perspective, where we seek to identify spurious correlations between tasks. Drawing inspirations from conventional formulations on spurious correlation, for each task, we propose to distinguish its spurious tasks using the difference in correlation coefficients between the empirical distribution and class-wise resampled distributions, thereby capturing the correlations between task labels w.r.t. each class. We prove theoretically the feasibility of the resampling strategy in characterizing spurious correlations between tasks. Furthermore, we propose a simple fine-tuning strategy, debiased adversarial training, where the per-task predictors are adversarially trained to disregard information associated with their spurious tasks. Experimental results on six benchmark datasets show that our method effectively mitigates spurious correlations and outperforms state-of-the-art methods in improving generalization.
Recent advancements in learning-based methods have opened new avenues for exploring and interpreting art forms, such as shadow art, origami, and sketch art, through computational models. One notable visual art form is 3D Anamorphic Art in which an ensemble of arbitrarily shaped 3D objects creates a realistic and meaningful expression when observed from a particular viewpoint and loses its coherence over the other viewpoints. In this work, we build on insights from 3D Anamorphic Art to perform 3D object arrangement. We introduce RASP, a differentiable-rendering-based framework to arrange arbitrarily shaped 3D objects within a bounded volume via shadow (or silhouette)-guided optimization with an aim of minimal inter-object spacing and near-maximal occupancy. Furthermore, we propose a novel SDF-based formulation to handle inter-object intersection and container extrusion. We demonstrate that RASP can be extended to part assembly alongside object packing considering 3D objects to be "parts" of another 3D object. Finally, we present artistic illustrations of multi-view anamorphic art, achieving meaningful expressions from multiple viewpoints within a single ensemble.
Currently, deep learning-based methods for remote sensing pansharpening have advanced rapidly. However, many existing methods struggle to fully leverage feature heterogeneity and redundancy, thereby limiting their effectiveness. To address these challenges across two key dimensions, we introduce a general adaptive dual-level weighting mechanism (ADWM), designed to enhance a wide range of existing deep-learning methods. First, Intra-Feature Weighting (IFW) evaluates correlations among channels within each feature and selectively weighs to reduce redundancy and enhance unique information. Second, Cross-Feature Weighting (CFW) adjusts contributions across layers based on inter-layer correlations, refining the final output by preserving key distinctions across feature depths. This dual-level weighting is efficiently implemented through our proposed Correlation-Aware Covariance Weighting (CACW), which generates weights by utilizing the correlations captured within the covariance matrix. Extensive experiments demonstrate the superior performance of ADWM compared to recent state-of-the-art (SOTA) methods. Furthermore, we validate the effectiveness of our approach through generality experiments, ablation studies, comparison experiments, and detailed visual analysis.
Common choices of architecture give neural networks a preference for fitting data with simple functions. This simplicity bias is known as key to their success. This paper explores the limits of this assumption. Building on recent work that showed that activation functions are the origin of the simplicity bias (Teney, 2024), we introduce a method to meta-learn activation functions to modulate this bias.**Findings.** We discover multiple tasks where the assumption of simplicity is inadequate, and standard ReLU architectures are therefore suboptimal. In these cases, we find activation functions that perform better by inducing a prior of higher complexity. Interestingly, these cases correspond to domains where neural networks have historically struggled: tabular data, regression tasks, cases of shortcut learning, and algorithmic grokking tasks. In comparison, the simplicity bias proves adequate on image tasks, where learned activations are nearly identical to ReLUs and GeLUs.**Implications.** (1) Contrary to common belief, the simplicity bias is not universally useful. There exist real tasks where it is suboptimal. (2) The suitability of ReLU models for image classification is not accidental. (3) The success of ML ultimately depends on the adequacy between data and architectures, and there may be benefits for architectures tailored to specific distributions of tasks.
Infants develop complex visual understanding rapidly, even preceding of the acquisition of linguistic skills. As computer vision seeks to replicate the human vision system, understanding infant visual development may offer valuable insights. In this paper, we present an interdisciplinary study exploring this question: can a computational model that imitates the infant learning process develop broader visual concepts that extend beyond the vocabulary it has heard, similar to how infants naturally learn? To investigate this, we analyze a recently published model in Science by Vong et al., which is trained on longitudinal, egocentric images of a single child paired with transcribed parental speech. We perform neuron labeling to identify visual concept neurons hidden in the model's internal representations. We then demonstrate that these neurons can recognize objects beyond the model's original vocabulary. Furthermore, we compare the differences in representation between infant models and those in modern computer vision models, such as CLIP and ImageNet pre-trained model. Ultimately, our work bridges cognitive science and computer vision by analyzing the internal representations of a computational model trained on an infant visual and linguistic inputs. Our code is available at https://github.com/Kexueyi/discover_infant_vis.
Few-shot counting estimates the number of target objects in an image using only a few annotated exemplars. However, domain shift severely hinders existing methods to generalize to unseen scenarios. This falls into the realm of single domain generalization that remains unexplored in few-shot counting. To solve this problem, we begin by analyzing the main limitations of current methods, which typically follow a standard pipeline that extract the object prototypes from exemplars and then match them with image feature to construct the correlation map. We argue that existing methods overlook the significance of learning highly generalized prototypes. Building on this insight, we propose the first domain generalization few-shot counter, Universal Representation Matching, termed URM. Our primary contribution is the discovery that incorporating universal vision-language representations distilled from a large scale pretrained vision-language model into the correlation construction process substantially improves robustness to domain shifts without compromising in domain performance. As a result, URM achieves state-of-the-art performance on both in domain and the newly introduced domain generalization setting.
GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding
PDF ↗3D Semantic Occupancy Prediction is fundamental for spatial understanding, yet existing approaches face challenges in scalability and generalization due to their reliance on extensive labeled data and computationally intensive voxel-wise representations. In this paper, we introduce GaussTR, a novel Gaussian-based Transformer framework that unifies sparse 3D modeling with foundation model alignment through Gaussian representations to advance 3D spatial understanding. GaussTR predicts sparse sets of Gaussians in a feed-forward manner to represent 3D scenes. By splatting the Gaussians into 2D views and aligning the rendered features with foundation models, GaussTR facilitates self-supervised 3D representation learning and enables open-vocabulary semantic occupancy prediction without requiring explicit annotations. Empirical experiments on the Occ3D-nuScenes dataset demonstrate GaussTR's state-of-the-art zero-shot performance of 12.27 mIoU, along with a 40% reduction in training time. These results highlight the efficacy of GaussTR for scalable and holistic 3D spatial understanding, with promising implications in autonomous driving and embodied agents. The code is available at https://github.com/hustvl/GaussTR.
InPO: Inversion Preference Optimization with Reparametrized DDIM for Efficient Diffusion Model Alignment
PDF ↗Without using explicit reward, direct preference optimization (DPO) employs paired human preference data to fine-tune generative models, a method that has garnered considerable attention in large language models (LLMs). However, exploration of aligning text-to-image (T2I) diffusion models with human preferences remains limited. In comparison to supervised fine-tuning, existing methods that align diffusion model suffer from low training efficiency and subpar generation quality due to the long Markov chain process and the intractability of the reverse process. To address these limitations, we introduce DDIM-InPO, an efficient method for direct preference alignment of diffusion models. Our approach conceptualizes diffusion model as a single-step generative model, allowing us to fine-tune the outputs of specific latent variables selectively. In order to accomplish this objective, we first assign implicit rewards to any latent variable directly via a reparameterization technique. Then we construct an Inversion technique to estimate appropriate latent variables for preference optimization. This modification process enables the diffusion model to only fine-tune the outputs of latent variables that have a strong correlation with the preference dataset. Experimental results indicate that our DDIM-InPO achieves state-of-the-art performance with just 400 steps of fine-tuning, surpassing all preference aligning baselines for T2I diffusion models in human preference evaluation tasks.
We present "Humans and Structure from Motion" (HSfM), a method for jointly reconstructing multiple human meshes, scene point clouds, and camera parameters in a metric world coordinate system from a sparse set of uncalibrated multi-view images featuring people. Our approach combines data-driven scene reconstruction with the traditional Structure-from-Motion (SfM) framework to achieve more accurate scene reconstruction and camera estimation while simultaneously recovering human meshes. In contrast to existing scene reconstruction and SfM methods that lack metric scale information, our method estimates approximate metric scale by leveraging the human statistical model. Furthermore, our method reconstructs multiple human meshes within the same world coordinate system with the scene point cloud, effectively capturing spatial relationships among individuals and their positions in the environment. We initialize the reconstruction of humans, scenes, and cameras using robust foundational models and jointly optimize these elements. This joint optimization synergistically improves the accuracy of each component. We compare our method with existing methods on two challenging benchmarks, EgoHumans and EgoExo4D, demonstrating significant improvements in human localization accuracy within the world coordinate frame (reducing error from 3.59m to 1.04m in EgoHumans and from 3.01m to 0.50m in EgoExo4D). Notably, our results show that incorporating human data into the SfM pipeline improves camera pose estimation (e.g., increasing RRA@15 by 20.3% on EgoHumans). Additionally, qualitative results show that our approach improves scene reconstruction quality. Our code is available at muelea.github.io/hsfm.
Satellite Observations Guided Diffusion Model for Accurate Meteorological States at Arbitrary Resolution
PDF ↗Accurate acquisition of surface meteorological conditions at arbitrary locations holds significant importance for weather forecasting and climate simulation. Meteorological states derived from satellite observations are often provided in the form of low-resolution grid fields. If spatial interpolation is applied directly to obtain meteorological states for specific locations, there will often be significant discrepancies compared to actual observations. Existing downscaling methods for acquiring meteorological state information at higher resolutions commonly overlook the correlation with satellite observations. To bridge the gap, we propose Satellite-observations Guided Diffusion Model (SGD), a conditional diffusion model pre-trained on ERA5 reanalysis data with satellite observations (GridSat) as conditions, which is employed for sampling downscaled meteorological states through a zero-shot guided sampling strategy and patch-based methods. During the training process, we propose to fuse the information from GridSat satellite observations into ERA5 maps via the attention mechanism, enabling SGD to generate atmospheric states that align more accurately with actual conditions. In the sampling, we employed optimizable convolutional kernels to simulate the upscale process, thereby generating high-resolution ERA5 maps using low-resolution ERA5 maps as well as observations from weather stations as guidance. Moreover, our devised patch-based method promotes SGD to generate meteorological states at arbitrary resolutions. Experiments demonstrate SGD fulfills accurate meteorological states downscaling to 6.25km.
Generative methods for image and video editing use generative models as priors to perform edits despite incomplete information, such as changing the composition of 3D objects shown in a single image. Recent methods have shown promising composition editing results in the image setting, but in the video setting, editing methods have focused on editing object appearance, object motion, or camera motion, and as a result, methods to edit object composition in videos are still missing. We propose VideoHandles as a method for editing 3D object compositions in videos of static scenes with camera motion. Our approach allows editing the 3D position of a 3D object across all frames of a video in a temporally consistent manner. This is achieved by lifting intermediate features of a generative model to a 3D reconstruction that is shared between all frames, editing the reconstruction, and projecting the features on the edited reconstruction back to each frame. To the best of our knowledge, this is the first generative approach to edit object compositions in videos. Our approach is simple and training-free, while outperforming state-of-the-art image editing baselines.
Thanks to the introduction of large-scale datasets, deep-learning has become the mainstream approach for appearance-based gaze estimation problems. However, current large-scale datasets contain annotation errors and provide only a single vector for gaze annotation, lacking key information such as 3D eyeball structures. Limitations in annotation accuracy and variety have constrained the progress in research and development of deep-learning methods for appearance-based gaze-related tasks. In this paper, we present GazeGene, a new large-scale synthetic gaze dataset with photo-realistic samples. More importantly, GazeGene not only provides accurate gaze annotations, but also offers 3D annotations of vital eye structures such as the pupil, iris, eyeball, optical and visual axes for the first time. Experiments show that GazeGene achieves comparable quality and generalization ability with real-world datasets, even outperforms most existing datasets on high-resolution images. Furthermore, its 3D eyeball annotations expand the application of deep-learning methods on various gaze-related tasks, offering new insights into this field. The dataset is available at: https://phiai.buaa.edu.cn/GazeGene/.
We aim to solve unsupervised anomaly detection in a practical challenging environment where the normal dataset is both contaminated with defective regions and its product class distribution is tailed but unknown. We observe that existing models suffer from tail-versus-noise trade-off where if a model is robust against pixel noise, then its performance deteriorates on tail class samples, and vice versa. To mitigate the issue, we handle the tail class and noise samples independently. To this end, we propose TailSampler, a novel class size predictor that estimates the class cardinality of samples based on a symmetric assumption on the class-wise distribution of embedding similarities. TailSampler can be utilized to sample the tail class samples exclusively, allowing to handle them separately. Based on these facets, we build a memory-based anomaly detection model TailedCore, whose memory both well captures tail class information and is noise-robust. We extensively validate the effectiveness of TailedCore on the unsupervised long-tail noisy anomaly detection setting, and show that TailedCore outperforms the state-of-the-art in most settings. Code is available in TailedCore
Analyses of human motion kinematics have achieved tremendous advances. However, the production mechanism, known as human dynamics, is still undercovered. In this paper, we aim to push data-driven human dynamics understanding forward. We identify a major obstacle to this as the heterogeneity of existing human motion understanding efforts. Specifically, heterogeneity exists in not only the diverse kinematics representations and hierarchical dynamics representations but also in the data from different domains, namely biomechanics and reinforcement learning. With an in-depth analysis of the existing heterogeneity, we propose to emphasize the beneath homogeneity: all of them represent the homogeneous fact of human motion, though from different perspectives. Given this, we propose Homogeneous Dynamics Space (HDyS) as a fundamental space for human dynamics by aggregating heterogeneous data and training a homogeneous latent space with inspiration from the inverse-forward dynamics procedure. Leveraging the heterogeneous representations and datasets, HDyS achieves decent mapping between human kinematics and dynamics. We demonstrate the feasibility of HDyS with extensive experiments and applications. The project page is https://foruck.github.io/HDyS.
Federated Graph Learning (FGL) has emerged as a solution to address real-world privacy concerns and data silos in graph learning, which relies on Graph Neural Networks (GNNs). Nevertheless, the homophily level discrepancies within the local graph data of clients, termed homophily heterogeneity, significantly degrade the generalizability of a global GNN. Existing research ignores this issue and suffers from unpromising collaboration. In this paper, we propose FedSPA, an effective framework that addresses homophily heterogeneity from the perspectives of homophily conflict and homophily bias. In the first place, the homophily conflict arises when training on inconsistent homophily levels across clients. Correspondingly, we propose Subgraph Feature Propagation Decoupling (SFPD), thereby achieving collaboration on unified homophily levels across clients. To further address homophily bias, we design Homophily Bias-Driven Aggregation (HBDA) which emphasizes clients with lower biases. It enables the adaptive adjustment of each client contribution to the global GNN based on its homophily bias. The superiority of FedSPA is validated through extensive experiments. The code is available at https://github.com/OakleyTan/FedSPA.