PyTorchKR Papers

최신 논문

총 9,822편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2503.10779

The Power of One: A Single Example is All it Takes for Segmentation in VLMs

Large-scale vision-language models (VLMs), trained on extensive datasets of image-text pairs, exhibit strong multimodal understanding capabilities by implicitly learning associations between textual descriptions and image regions. This emergent ability enables zero-shot object detection and segmentation, using techniques that rely on text-image attention maps, without necessarily training on abundant labeled segmentation datasets. However, performance of such methods depends heavily on prompt engineering and manually selected layers or head choices for the attention layers. In this work, we demonstrate that, rather than relying solely on textual prompts, providing a single visual example for each category and fine-tuning the text-to-image attention layers and embeddings significantly improves the performance. Additionally, we propose learning an ensemble through few-shot fine-tuning across multiple layers and/or prompts. An entropy-based ranking and selection mechanism for text-to-image attention layers is proposed to identify the top-performing layers without the need for segmentation labels. This eliminates the need for hyper-parameter selection of text-to-image attention layers, providing a more flexible and scalable solution for open-vocabulary segmentation. We show that this approach yields strong zero-shot performance, further enhanced through fine-tuning with a single visual example. Moreover, we demonstrate that our method and findings are general and can be applied across various vision-language models (VLMs).

arXiv:2503.10777

HeightFormer: Learning Height Prediction in Voxel Features for Roadside Vision Centric 3D Object Detection via Transformer

Roadside vision centric 3D object detection has received increasing attention in recent years. It expands the perception range of autonomous vehicles, enhances the road safety. Previous methods focused on predicting per-pixel height rather than depth, making significant gains in roadside visual perception. While it is limited by the perspective property of near-large and far-small on image features, making it difficult for network to understand real dimension of objects in the 3D world. BEV features and voxel features present the real distribution of objects in 3D world compared to the image features. However, BEV features tend to lose details due to the lack of explicit height information, and voxel features are computationally expensive. Inspired by this insight, an efficient framework learning height prediction in voxel features via transformer is proposed, dubbed HeightFormer. It groups the voxel features into local height sequences, and utilize attention mechanism to obtain height distribution prediction. Subsequently, the local height sequences are reassembled to generate accurate 3D features. The proposed method is applied to two large-scale roadside benchmarks, DAIR-V2X-I and Rope3D. Extensive experiments are performed and the HeightFormer outperforms the state-of-the-art methods in roadside vision centric 3D object detection task.

arXiv:2503.11538

FLASHμ: Fast Localizing And Sizing of Holographic Microparticles

Reconstructing the 3D location and size of microparticles from diffraction images - holograms - is a computationally expensive inverse problem that has traditionally been solved using physics-based reconstruction methods. More recently, researchers have used machine learning methods to speed up the process. However, for small particles in large sample volumes the performance of these methods falls short of standard physics-based reconstruction methods. Here we designed a two-stage neural network architecture, FLASH$\mu$, to detect small particles (6-100$\mu$m) from holograms with large sample depths up to 20cm. Trained only on synthetic data with added physical noise, our method reliably detects particles of at least 9$\mu$m diameter in real holograms, comparable to the standard reconstruction-based approaches while operating on smaller crops, at quarter of the original resolution and providing roughly a 600-fold speedup. In addition to introducing a novel approach to a non-local object detection or signal demixing problem, our work could enable low-cost, real-time holographic imaging setups.

arXiv:2503.10579

Semantic-Supervised Spatial-Temporal Fusion for LiDAR-based 3D Object Detection

LiDAR-based 3D object detection presents significant challenges due to the inherent sparsity of LiDAR points. A common solution involves long-term temporal LiDAR data to densify the inputs. However, efficiently leveraging spatial-temporal information remains an open problem. In this paper, we propose a novel Semantic-Supervised Spatial-Temporal Fusion (ST-Fusion) method, which introduces a novel fusion module to relieve the spatial misalignment caused by the object motion over time and a feature-level semantic supervision to sufficiently unlock the capacity of the proposed fusion module. Specifically, the ST-Fusion consists of a Spatial Aggregation (SA) module and a Temporal Merging (TM) module. The SA module employs a convolutional layer with progressively expanding receptive fields to aggregate the object features from the local regions to alleviate the spatial misalignment, the TM module dynamically extracts object features from the preceding frames based on the attention mechanism for a comprehensive sequential presentation. Besides, in the semantic supervision, we propose a Semantic Injection method to enrich the sparse LiDAR data via injecting the point-wise semantic labels, using it for training a teacher model and providing a reconstruction target at the feature level supervised by the proposed object-aware loss. Extensive experiments on various LiDAR-based detectors demonstrate the effectiveness and universality of our proposal, yielding an improvement of approximately +2.8% in NDS based on the nuScenes benchmark.

arXiv:2503.10410공식 코드 · Papers with Code

RoCo-Sim: Enhancing Roadside Collaborative Perception through Foreground Simulation

Roadside Collaborative Perception refers to a system where multiple roadside units collaborate to pool their perceptual data, assisting vehicles in enhancing their environmental awareness. Existing roadside perception methods concentrate on model design but overlook data issues like calibration errors, sparse information, and multi-view consistency, leading to poor performance on recent published datasets. To significantly enhance roadside collaborative perception and address critical data issues, we present the first simulation framework RoCo-Sim for road-side collaborative perception. RoCo-Sim is capable of generating diverse, multi-view consistent simulated roadside data through dynamic foreground editing and full-scene style transfer of a single image. RoCo-Sim consists of four components: (1) Camera Extrinsic Optimization ensures accurate 3D to 2D projection for roadside cameras; (2) A novel Multi-View Occlusion-Aware Sampler (MOAS) determines the placement of diverse digital assets within 3D space; (3) DepthSAM innovatively models foreground-background relationships from single-frame fixed-view images, ensuring multi-view consistency of foreground; and (4) Scalable Post-Processing Toolkit generates more realistic and enriched scenes through style transfer and other enhancements. RoCo-Sim significantly improves roadside 3D object detection, outperforming SOTA methods by 83.74 on Rcooper-Intersection and 83.12 on TUMTraf-V2X for AP70. RoCo-Sim fills a critical gap in roadside perception simulation. Code and pre-trained models will be released soon: https://github.com/duyuwen-duen/RoCo-Sim

arXiv:2503.10210

TARS: Traffic-Aware Radar Scene Flow Estimation

Scene flow provides crucial motion information for autonomous driving. Recent LiDAR scene flow models utilize the rigid-motion assumption at the instance level, assuming objects are rigid bodies. However, these instance-level methods are not suitable for sparse radar point clouds. In this work, we present a novel $\textbf{T}$raffic-$\textbf{A}$ware $\textbf{R}$adar $\textbf{S}$cene flow estimation method, named $\textbf{TARS}$, which utilizes the motion rigidity at the traffic level. To address the challenges in radar scene flow, we perform object detection and scene flow jointly and boost the latter. We incorporate the feature map from the object detector, trained with detection losses, to make radar scene flow aware of the environment and road users. Therefrom, we construct a Traffic Vector Field (TVF) in the feature space, enabling a holistic traffic-level scene understanding in our scene flow branch. When estimating the scene flow, we consider both point-level motion cues from point neighbors and traffic-level consistency of rigid motion within the space. TARS outperforms the state of the art on a proprietary dataset and the View-of-Delft dataset, improving the benchmarks by 23% and 15%, respectively.

arXiv:2503.10152공식 코드 · Papers with Code

A Hierarchical Semantic Distillation Framework for Open-Vocabulary Object Detection

Open-vocabulary object detection (OVD) aims to detect objects beyond the training annotations, where detectors are usually aligned to a pre-trained vision-language model, eg, CLIP, to inherit its generalizable recognition ability so that detectors can recognize new or novel objects. However, previous works directly align the feature space with CLIP and fail to learn the semantic knowledge effectively. In this work, we propose a hierarchical semantic distillation framework named HD-OVD to construct a comprehensive distillation process, which exploits generalizable knowledge from the CLIP model in three aspects. In the first hierarchy of HD-OVD, the detector learns fine-grained instance-wise semantics from the CLIP image encoder by modeling relations among single objects in the visual space. Besides, we introduce text space novel-class-aware classification to help the detector assimilate the highly generalizable class-wise semantics from the CLIP text encoder, representing the second hierarchy. Lastly, abundant image-wise semantics containing multi-object and their contexts are also distilled by an image-wise contrastive distillation. Benefiting from the elaborated semantic distillation in triple hierarchies, our HD-OVD inherits generalizable recognition ability from CLIP in instance, class, and image levels. Thus, we boost the novel AP on the OV-COCO dataset to 46.4% with a ResNet50 backbone, which outperforms others by a clear margin. We also conduct extensive ablation studies to analyze how each component works.

arXiv:2503.09968

Style Evolving along Chain-of-Thought for Unknown-Domain Object Detection

Recently, a task of Single-Domain Generalized Object Detection (Single-DGOD) is proposed, aiming to generalize a detector to multiple unknown domains never seen before during training. Due to the unavailability of target-domain data, some methods leverage the multimodal capabilities of vision-language models, using textual prompts to estimate cross-domain information, enhancing the model's generalization capability. These methods typically use a single textual prompt, often referred to as the one-step prompt method. However, when dealing with complex styles such as the combination of rain and night, we observe that the performance of the one-step prompt method tends to be relatively weak. The reason may be that many scenes incorporate not just a single style but a combination of multiple styles. The one-step prompt method may not effectively synthesize combined information involving various styles. To address this limitation, we propose a new method, i.e., Style Evolving along Chain-of-Thought, which aims to progressively integrate and expand style information along the chain of thought, enabling the continual evolution of styles. Specifically, by progressively refining style descriptions and guiding the diverse evolution of styles, this approach enables more accurate simulation of various style characteristics and helps the model gradually learn and adapt to subtle differences between styles. Additionally, it exposes the model to a broader range of style features with different data distributions, thereby enhancing its generalization capability in unseen domains. The significant performance gains over five adverse-weather scenarios and the Real to Art benchmark demonstrate the superiorities of our method.

arXiv:2503.08421공식 코드 · Papers with Code

Learning to Detect Objects from Multi-Agent LiDAR Scans without Manual Labels

Unsupervised 3D object detection serves as an important solution for offline 3D object annotation. However, due to the data sparsity and limited views, the clustering-based label fitting in unsupervised object detection often generates low-quality pseudo-labels. Multi-agent collaborative dataset, which involves the sharing of complementary observations among agents, holds the potential to break through this bottleneck. In this paper, we introduce a novel unsupervised method that learns to Detect Objects from Multi-Agent LiDAR scans, termed DOtA, without using labels from external. DOtA first uses the internally shared ego-pose and ego-shape of collaborative agents to initialize the detector, leveraging the generalization performance of neural networks to infer preliminary labels. Subsequently,DOtA uses the complementary observations between agents to perform multi-scale encoding on preliminary labels, then decodes high-quality and low-quality labels. These labels are further used as prompts to guide a correct feature learning process, thereby enhancing the performance of the unsupervised object detection task. Extensive experiments on the V2V4Real and OPV2V datasets show that our DOtA outperforms state-of-the-art unsupervised 3D object detection methods. Additionally, we also validate the effectiveness of the DOtA labels under various collaborative perception frameworks.The code is available at https://github.com/xmuqimingxia/DOtA.

arXiv:2503.10392공식 코드 · Papers with Code

RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing

Recent advances in self-supervised learning for Vision Transformers (ViTs) have fueled breakthroughs in remote sensing (RS) foundation models. However, the quadratic complexity of self-attention poses a significant barrier to scalability, particularly for large models and high-resolution images. While the linear-complexity Mamba architecture offers a promising alternative, existing RS applications of Mamba remain limited to supervised tasks on small, domain-specific datasets. To address these challenges, we propose RoMA, a framework that enables scalable self-supervised pretraining of Mamba-based RS foundation models using large-scale, diverse, unlabeled data. RoMA enhances scalability for high-resolution images through a tailored auto-regressive learning strategy, incorporating two key innovations: 1) a rotation-aware pretraining mechanism combining adaptive cropping with angular embeddings to handle sparsely distributed objects with arbitrary orientations, and 2) multi-scale token prediction objectives that address the extreme variations in object scales inherent to RS imagery. Systematic empirical studies validate that Mamba adheres to RS data and parameter scaling laws, with performance scaling reliably as model and data size increase. Furthermore, experiments across scene classification, object detection, and semantic segmentation tasks demonstrate that RoMA-pretrained Mamba models consistently outperform ViT-based counterparts in both accuracy and computational efficiency. The source code and pretrained models will be released at https://github.com/MiliLab/RoMA.

arXiv:2503.10356

Object detection characteristics in a learning factory environment using YOLOv8

AI-based object detection, and efforts to explain and investigate their characteristics, is a topic of high interest. The impact of, e.g., complex background structures with similar appearances as the objects of interest, on the detection accuracy and, beforehand, the necessary dataset composition are topics of ongoing research. In this paper, we present a systematic investigation of background influences and different features of the object to be detected. The latter includes various materials and surfaces, partially transparent and with shiny reflections in the context of an Industry 4.0 learning factory. Different YOLOv8 models have been trained for each of the materials on different sized datasets, where the appearance was the only changing parameter. In the end, similar characteristics tend to show different behaviours and sometimes unexpected results. While some background components tend to be detected, others with the same features are not part of the detection. Additionally, some more precise conclusions can be drawn from the results. Therefore, we contribute a challenging dataset with detailed investigations on 92 trained YOLO models, addressing some issues on the detection accuracy and possible overfitting.

arXiv:2503.09807

How good are deep learning methods for automated road safety analysis using video data? An experimental study

Image-based multi-object detection (MOD) and multi-object tracking (MOT) are advancing at a fast pace. A variety of 2D and 3D MOD and MOT methods have been developed for monocular and stereo cameras. Road safety analysis can benefit from those advancements. As crashes are rare events, surrogate measures of safety (SMoS) have been developed for safety analyses. (Semi-)Automated safety analysis methods extract road user trajectories to compute safety indicators, for example, Time-to-Collision (TTC) and Post-encroachment Time (PET). Inspired by the success of deep learning in MOD and MOT, we investigate three MOT methods, including one based on a stereo-camera, using the annotated KITTI traffic video dataset. Two post-processing steps, IDsplit and SS, are developed to improve the tracking results and investigate the factors influencing the TTC. The experimental results show that, despite some advantages in terms of the numbers of interactions or similarity to the TTC distributions, all the tested methods systematically over-estimate the number of interactions and under-estimate the TTC: they report more interactions and more severe interactions, making the road user interactions appear less safe than they are. Further efforts will be directed towards testing more methods and more data, in particular from roadside sensors, to verify the results and improve the performance.

arXiv:2503.09803

Evaluating the Impact of Synthetic Data on Object Detection Tasks in Autonomous Driving

The increasing applications of autonomous driving systems necessitates large-scale, high-quality datasets to ensure robust performance across diverse scenarios. Synthetic data has emerged as a viable solution to augment real-world datasets due to its cost-effectiveness, availability of precise ground-truth labels, and the ability to model specific edge cases. However, synthetic data may introduce distributional differences and biases that could impact model performance in real-world settings. To evaluate the utility and limitations of synthetic data, we conducted controlled experiments using multiple real-world datasets and a synthetic dataset generated by BIT Technology Solutions GmbH. Our study spans two sensor modalities, camera and LiDAR, and investigates both 2D and 3D object detection tasks. We compare models trained on real, synthetic, and mixed datasets, analyzing their robustness and generalization capabilities. Our findings demonstrate that the use of a combination of real and synthetic data improves the robustness and generalization of object detection models, underscoring the potential of synthetic data in advancing autonomous driving technologies.

arXiv:2503.09878

CleverDistiller: Simple and Spatially Consistent Cross-modal Distillation

Vision foundation models (VFMs) such as DINO have led to a paradigm shift in 2D camera-based perception towards extracting generalized features to support many downstream tasks. Recent works introduce self-supervised cross-modal knowledge distillation (KD) as a way to transfer these powerful generalization capabilities into 3D LiDAR-based models. However, they either rely on highly complex distillation losses, pseudo-semantic maps, or limit KD to features useful for semantic segmentation only. In this work, we propose CleverDistiller, a self-supervised, cross-modal 2D-to-3D KD framework introducing a set of simple yet effective design choices: Unlike contrastive approaches relying on complex loss design choices, our method employs a direct feature similarity loss in combination with a multi layer perceptron (MLP) projection head to allow the 3D network to learn complex semantic dependencies throughout the projection. Crucially, our approach does not depend on pseudo-semantic maps, allowing for direct knowledge transfer from a VFM without explicit semantic supervision. Additionally, we introduce the auxiliary self-supervised spatial task of occupancy prediction to enhance the semantic knowledge, obtained from a VFM through KD, with 3D spatial reasoning capabilities. Experiments on standard autonomous driving benchmarks for 2D-to-3D KD demonstrate that CleverDistiller achieves state-of-the-art performance in both semantic segmentation and 3D object detection (3DOD) by up to 10% mIoU, especially when fine tuning on really low data amounts, showing the effectiveness of our simple yet powerful KD strategy

arXiv:2503.08092

SparseVoxFormer: Sparse Voxel-based Transformer for Multi-modal 3D Object Detection

Most previous 3D object detection methods that leverage the multi-modality of LiDAR and cameras utilize the Bird's Eye View (BEV) space for intermediate feature representation. However, this space uses a low x, y-resolution and sacrifices z-axis information to reduce the overall feature resolution, which may result in declined accuracy. To tackle the problem of using low-resolution features, this paper focuses on the sparse nature of LiDAR point cloud data. From our observation, the number of occupied cells in the 3D voxels constructed from a LiDAR data can be even fewer than the number of total cells in the BEV map, despite the voxels' significantly higher resolution. Based on this, we introduce a novel sparse voxel-based transformer network for 3D object detection, dubbed as SparseVoxFormer. Instead of performing BEV feature extraction, we directly leverage sparse voxel features as the input for a transformer-based detector. Moreover, with regard to the camera modality, we introduce an explicit modality fusion approach that involves projecting 3D voxel coordinates onto 2D images and collecting the corresponding image features. Thanks to these components, our approach can leverage geometrically richer multi-modal features while even reducing the computational cost. Beyond the proof-of-concept level, we further focus on facilitating better multi-modal fusion and flexible control over the number of sparse features. Finally, thorough experimental results demonstrate that utilizing a significantly smaller number of sparse features drastically reduces computational costs in a 3D object detector while enhancing both overall and long-range performance.

arXiv:2503.08507공식 코드 · Papers with Code

Referring to Any Person

Humans are undoubtedly the most important participants in computer vision, and the ability to detect any individual given a natural language description, a task we define as referring to any person, holds substantial practical value. However, we find that existing models generally fail to achieve real-world usability, and current benchmarks are limited by their focus on one-to-one referring, that hinder progress in this area. In this work, we revisit this task from three critical perspectives: task definition, dataset design, and model architecture. We first identify five aspects of referable entities and three distinctive characteristics of this task. Next, we introduce HumanRef, a novel dataset designed to tackle these challenges and better reflect real-world applications. From a model design perspective, we integrate a multimodal large language model with an object detection framework, constructing a robust referring model named RexSeek. Experimental results reveal that state-of-the-art models, which perform well on commonly used benchmarks like RefCOCO/+/g, struggle with HumanRef due to their inability to detect multiple individuals. In contrast, RexSeek not only excels in human referring but also generalizes effectively to common object referring, making it broadly applicable across various perception tasks. Code is available at https://github.com/IDEA-Research/RexSeek

arXiv:2503.09354

Fully-Synthetic Training for Visual Quality Inspection in Automotive Production

Visual Quality Inspection plays a crucial role in modern manufacturing environments as it ensures customer safety and satisfaction. The introduction of Computer Vision (CV) has revolutionized visual quality inspection by improving the accuracy and efficiency of defect detection. However, traditional CV models heavily rely on extensive datasets for training, which can be costly, time-consuming, and error-prone. To overcome these challenges, synthetic images have emerged as a promising alternative. They offer a cost-effective solution with automatically generated labels. In this paper, we propose a pipeline for generating synthetic images using domain randomization. We evaluate our approach in three real inspection scenarios and demonstrate that an object detection model trained solely on synthetic data can outperform models trained on real images.

arXiv:2503.09271

DitHub: A Modular Framework for Incremental Open-Vocabulary Object Detection

Open-Vocabulary object detectors can recognize a wide range of categories using simple textual prompts. However, improving their ability to detect rare classes or specialize in certain domains remains a challenge. While most recent methods rely on a single set of model weights for adaptation, we take a different approach by using modular deep learning. We introduce DitHub, a framework designed to create and manage a library of efficient adaptation modules. Inspired by Version Control Systems, DitHub organizes expert modules like branches that can be fetched and merged as needed. This modular approach enables a detailed study of how adaptation modules combine, making it the first method to explore this aspect in Object Detection. Our approach achieves state-of-the-art performance on the ODinW-13 benchmark and ODinW-O, a newly introduced benchmark designed to evaluate how well models adapt when previously seen classes reappear. For more details, visit our project page: https://aimagelab.github.io/DitHub/

arXiv:2503.09187

Polygonizing Roof Segments from High-Resolution Aerial Images Using Yolov8-Based Edge Detection

This study presents a novel approach for roof detail extraction and vectorization using remote sensing images. Unlike previous geometric-primitive-based methods that rely on the detection of corners, our method focuses on edge detection as the primary mechanism for roof reconstruction, while utilizing geometric relationships to define corners and faces. We adapt the YOLOv8 OBB model, originally designed for rotated object detection, to extract roof edges effectively. Our method demonstrates robustness against noise and occlusion, leading to precise vectorized representations of building roofs. Experiments conducted on the SGA and Melville datasets highlight the method's effectiveness. At the raster level, our model outperforms the state-of-the-art foundation segmentation model (SAM), achieving a mIoU between 0.85 and 1 for most samples and an ovIoU close to 0.97. At the vector level, evaluation using the Hausdorff distance, PolyS metric, and our raster-vector-metric demonstrates significant improvements after polygonization, with a close approximation to the reference data. The method successfully handles diverse roof structures and refines edge gaps, even on complex roof structures of new, excluded from training datasets. Our findings underscore the potential of this approach to address challenges in automatic roof structure vectorization, supporting various applications such as urban terrain reconstruction.

arXiv:2503.08992

Dual-Domain Homogeneous Fusion with Cross-Modal Mamba and Progressive Decoder for 3D Object Detection

Fusing LiDAR point cloud features and image features in a homogeneous BEV space has been widely adopted for 3D object detection in autonomous driving. However, such methods are limited by the excessive compression of multi-modal features. While some works explore feature fusion in dense voxel spaces, they suffer from high computational costs and inefficiencies in query generation. To address these limitations, we propose a Dual-Domain Homogeneous Fusion network (DDHFusion), which leverages the complementary advantages of both BEV and voxel domains while mitigating their respective drawbacks. Specifically, we first transform image features into BEV and sparse voxel spaces using LSS and our proposed semantic-aware feature sampling module which can significantly reduces computational overhead by filtering unimportant voxels. For feature encoding, we design two networks for BEV and voxel feature fusion, incorporating novel cross-modal voxel and BEV Mamba blocks to resolve feature misalignment and enable efficient yet comprehensive scene perception. The output voxel features are injected into the BEV space to compensate for the loss of 3D details caused by height compression. For feature decoding, a progressive query generation module is implemented in the BEV domain to alleviate false negatives during query selection caused by feature compression and small object sizes. Finally, a progressive decoder can sequentially aggregate not only context-rich BEV features but also geometry-aware voxel features, ensuring more precise confidence prediction and bounding box regression. On the NuScenes dataset, DDHfusion achieves state-of-the-art performance, and further experiments demonstrate its superiority over other homogeneous fusion methods.