PyTorchKR Papers

“Object Detection”

총 13,455편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:1607.05066

Recycle deep features for better object detection

Aiming at improving the performance of existing detection algorithms developed for different applications, we propose a region regression-based multi-stage class-agnostic detection pipeline, whereby the existing algorithms are employed for providing the initial detection proposals. Better detection is obtained by exploiting the power of deep learning in the region regress scheme while avoiding the requirement on a huge amount of reference data for training deep neural networks. Additionally, a novel network architecture with recycled deep features is proposed, which provides superior regression results compared to the commonly used architectures. As demonstrated on a data set with ~1200 samples of different classes, it is feasible to successfully train a deep neural network in our proposed architecture and use it to obtain the desired detection performance. Since only slight modifications are required to common network architectures and since the deep neural network is trained using the standard hyperparameters, the proposed detection is well accessible and can be easily adopted to a broad variety of detection tasks.

arXiv:2105.00369

Learning data association without data association: An EM approach to neural assignment prediction

Data association is a fundamental component of effective multi-object tracking. Current approaches to data-association tend to frame this as an assignment problem relying on gating and distance-based cost matrices, or offset the challenge of data association to a problem of tracking by detection. The latter is typically formulated as a supervised learning problem, and requires labelling information about tracked object identities to train a model for object recognition. This paper introduces an expectation maximisation approach to train neural models for data association, which does not require labelling information. Here, a Sinkhorn network is trained to predict assignment matrices that maximise the marginal likelihood of trajectory observations. Importantly, networks trained using the proposed approach can be re-used in downstream tracking applications.

arXiv:2110.10456

Noisy Annotation Refinement for Object Detection

Supervised training of object detectors requires well-annotated large-scale datasets, whose production is costly. Therefore, some efforts have been made to obtain annotations in economical ways, such as cloud sourcing. However, datasets obtained by these methods tend to contain noisy annotations such as inaccurate bounding boxes and incorrect class labels. In this study, we propose a new problem setting of training object detectors on datasets with entangled noises of annotations of class labels and bounding boxes. Our proposed method efficiently decouples the entangled noises, corrects the noisy annotations, and subsequently trains the detector using the corrected annotations. We verified the effectiveness of our proposed method and compared it with the baseline on noisy datasets with different noise levels. The experimental results show that our proposed method significantly outperforms the baseline.

arXiv:2112.02990

4DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understanding

We present a new approach to instill 4D dynamic object priors into learned 3D representations by unsupervised pre-training. We observe that dynamic movement of an object through an environment provides important cues about its objectness, and thus propose to imbue learned 3D representations with such dynamic understanding, that can then be effectively transferred to improved performance in downstream 3D semantic scene understanding tasks. We propose a new data augmentation scheme leveraging synthetic 3D shapes moving in static 3D environments, and employ contrastive learning under 3D-4D constraints that encode 4D invariances into the learned 3D representations. Experiments demonstrate that our unsupervised representation learning results in improvement in downstream 3D semantic segmentation, object detection, and instance segmentation tasks, and moreover, notably improves performance in data-scarce scenarios.

arXiv:2003.00888

3D Object Detection From LiDAR Data Using Distance Dependent Feature Extraction

This paper presents a new approach to 3D object detection that leverages the properties of the data obtained by a LiDAR sensor. State-of-the-art detectors use neural network architectures based on assumptions valid for camera images. However, point clouds obtained from LiDAR are fundamentally different. Most detectors use shared filter kernels to extract features which do not take into account the range dependent nature of the point cloud features. To show this, different detectors are trained on two splits of the KITTI dataset: close range (objects up to 25 meters from LiDAR) and long-range. Top view images are generated from point clouds as input for the networks. Combined results outperform the baseline network trained on the full dataset with a single backbone. Additional research compares the effect of using different input features when converting the point cloud to image. The results indicate that the network focuses on the shape and structure of the objects, rather than exact values of the input. This work proposes an improvement for 3D object detectors by taking into account the properties of LiDAR point clouds over distance. Results show that training separate networks for close-range and long-range objects boosts performance for all KITTI benchmark difficulties.

arXiv:2109.02497

Voxel Transformer for 3D Object Detection

We present Voxel Transformer (VoTr), a novel and effective voxel-based Transformer backbone for 3D object detection from point clouds. Conventional 3D convolutional backbones in voxel-based 3D detectors cannot efficiently capture large context information, which is crucial for object recognition and localization, owing to the limited receptive fields. In this paper, we resolve the problem by introducing a Transformer-based architecture that enables long-range relationships between voxels by self-attention. Given the fact that non-empty voxels are naturally sparse but numerous, directly applying standard Transformer on voxels is non-trivial. To this end, we propose the sparse voxel module and the submanifold voxel module, which can operate on the empty and non-empty voxel positions effectively. To further enlarge the attention range while maintaining comparable computational overhead to the convolutional counterparts, we propose two attention mechanisms for multi-head attention in those two modules: Local Attention and Dilated Attention, and we further propose Fast Voxel Query to accelerate the querying process in multi-head attention. VoTr contains a series of sparse and submanifold voxel modules and can be applied in most voxel-based detectors. Our proposed VoTr shows consistent improvement over the convolutional baselines while maintaining computational efficiency on the KITTI dataset and the Waymo Open dataset.

arXiv:2109.04627

ACFNet: Adaptively-Cooperative Fusion Network for RGB-D Salient Object Detection

The reasonable employment of RGB and depth data show great significance in promoting the development of computer vision tasks and robot-environment interaction. However, there are different advantages and disadvantages in the early and late fusion of the two types of data. Besides, due to the diversity of object information, using a single type of data in a specific scenario tends to result in semantic misleading. Based on the above considerations, we propose an adaptively-cooperative fusion network (ACFNet) with ResinRes structure for salient object detection. This structure is designed to flexibly utilize the advantages of feature fusion in early and late stages. Secondly, an adaptively-cooperative semantic guidance (ACG) scheme is designed to suppress inaccurate features in the guidance phase. Further, we proposed a type-based attention module (TAM) to optimize the network and enhance the multi-scale perception of different objects. For different objects, the features generated by different types of convolution are enhanced or suppressed by the gated mechanism for segmentation optimization. ACG and TAM optimize the transfer of feature streams according to their data attributes and convolution attributes, respectively. Sufficient experiments conducted on RGB-D SOD datasets illustrate that the proposed network performs favorably against 18 state-of-the-art algorithms.

arXiv:2308.02606

Improving Human-Object Interaction Detection via Virtual Image Learning

Human-Object Interaction (HOI) detection aims to understand the interactions between humans and objects, which plays a curtail role in high-level semantic understanding tasks. However, most works pursue designing better architectures to learn overall features more efficiently, while ignoring the long-tail nature of interaction-object pair categories. In this paper, we propose to alleviate the impact of such an unbalanced distribution via Virtual Image Leaning (VIL). Firstly, a novel label-to-image approach, Multiple Steps Image Creation (MUSIC), is proposed to create a high-quality dataset that has a consistent distribution with real images. In this stage, virtual images are generated based on prompts with specific characterizations and selected by multi-filtering processes. Secondly, we use both virtual and real images to train the model with the teacher-student framework. Considering the initial labels of some virtual images are inaccurate and inadequate, we devise an Adaptive Matching-and-Filtering (AMF) module to construct pseudo-labels. Our method is independent of the internal structure of HOI detectors, so it can be combined with off-the-shelf methods by training merely 10 additional epochs. With the assistance of our method, multiple methods obtain significant improvements, and new state-of-the-art results are achieved on two benchmarks.

arXiv:2409.01816공식 코드 · Papers with Code

GeoBEV: Learning Geometric BEV Representation for Multi-view 3D Object Detection

Bird's-Eye-View (BEV) representation has emerged as a mainstream paradigm for multi-view 3D object detection, demonstrating impressive perceptual capabilities. However, existing methods overlook the geometric quality of BEV representation, leaving it in a low-resolution state and failing to restore the authentic geometric information of the scene. In this paper, we identify the drawbacks of previous approaches that limit the geometric quality of BEV representation and propose Radial-Cartesian BEV Sampling (RC-Sampling), which outperforms other feature transformation methods in efficiently generating high-resolution dense BEV representation to restore fine-grained geometric information. Additionally, we design a novel In-Box Label to substitute the traditional depth label generated from the LiDAR points. This label reflects the actual geometric structure of objects rather than just their surfaces, injecting real-world geometric information into the BEV representation. In conjunction with the In-Box Label, Centroid-Aware Inner Loss (CAI Loss) is developed to capture the inner geometric structure of objects. Finally, we integrate the aforementioned modules into a novel multi-view 3D object detector, dubbed GeoBEV, which achieves a state-of-the-art result of 66.2\% NDS on the nuScenes test set. The code is available at https://github.com/mengtan00/GeoBEV.git.

arXiv:2411.19860

SpaRC: Sparse Radar-Camera Fusion for 3D Object Detection

In this work, we present SpaRC, a novel Sparse fusion transformer for 3D perception that integrates multi-view image semantics with Radar and Camera point features. The fusion of radar and camera modalities has emerged as an efficient perception paradigm for autonomous driving systems. While conventional approaches utilize dense Bird's Eye View (BEV)-based architectures for depth estimation, contemporary query-based transformers excel in camera-only detection through object-centric methodology. However, these query-based approaches exhibit limitations in false positive detections and localization precision due to implicit depth modeling. We address these challenges through three key contributions: (1) sparse frustum fusion (SFF) for cross-modal feature alignment, (2) range-adaptive radar aggregation (RAR) for precise object localization, and (3) local self-attention (LSA) for focused query aggregation. In contrast to existing methods requiring computationally intensive BEV-grid rendering, SpaRC operates directly on encoded point features, yielding substantial improvements in efficiency and accuracy. Empirical evaluations on the nuScenes and TruckScenes benchmarks demonstrate that SpaRC significantly outperforms existing dense BEV-based and sparse query-based detectors. Our method achieves state-of-the-art performance metrics of 67.1 NDS and 63.1 AMOTA. The code and pretrained models are available at https://github.com/phi-wol/sparc.

arXiv:2104.00885공식 코드 · Papers with Code

Adaptive Class Suppression Loss for Long-Tail Object Detection

To address the problem of long-tail distribution for the large vocabulary object detection task, existing methods usually divide the whole categories into several groups and treat each group with different strategies. These methods bring the following two problems. One is the training inconsistency between adjacent categories of similar sizes, and the other is that the learned model is lack of discrimination for tail categories which are semantically similar to some of the head categories. In this paper, we devise a novel Adaptive Class Suppression Loss (ACSL) to effectively tackle the above problems and improve the detection performance of tail categories. Specifically, we introduce a statistic-free perspective to analyze the long-tail distribution, breaking the limitation of manual grouping. According to this perspective, our ACSL adjusts the suppression gradients for each sample of each class adaptively, ensuring the training consistency and boosting the discrimination for rare categories. Extensive experiments on long-tail datasets LVIS and Open Images show that the our ACSL achieves 5.18% and 5.2% improvements with ResNet50-FPN, and sets a new state of the art. Code and models are available at https://github.com/CASIA-IVA-Lab/ACSL.

arXiv:2104.10985

VM-MODNet: Vehicle Motion aware Moving Object Detection for Autonomous Driving

Moving object Detection (MOD) is a critical task in autonomous driving as moving agents around the ego-vehicle need to be accurately detected for safe trajectory planning. It also enables appearance agnostic detection of objects based on motion cues. There are geometric challenges like motion-parallax ambiguity which makes it a difficult problem. In this work, we aim to leverage the vehicle motion information and feed it into the model to have an adaptation mechanism based on ego-motion. The motivation is to enable the model to implicitly perform ego-motion compensation to improve performance. We convert the six degrees of freedom vehicle motion into a pixel-wise tensor which can be fed as input to the CNN model. The proposed model using Vehicle Motion Tensor (VMT) achieves an absolute improvement of 5.6% in mIoU over the baseline architecture. We also achieve state-of-the-art results on the public KITTI_MoSeg_Extended dataset even compared to methods which make use of LiDAR and additional input frames. Our model is also lightweight and runs at 85 fps on a TitanX GPU. Qualitative results are provided in https://youtu.be/ezbfjti-kTk.

arXiv:2203.07669공식 코드 · Papers with Code

Progressive End-to-End Object Detection in Crowded Scenes

In this paper, we propose a new query-based detection framework for crowd detection. Previous query-based detectors suffer from two drawbacks: first, multiple predictions will be inferred for a single object, typically in crowded scenes; second, the performance saturates as the depth of the decoding stage increases. Benefiting from the nature of the one-to-one label assignment rule, we propose a progressive predicting method to address the above issues. Specifically, we first select accepted queries prone to generate true positive predictions, then refine the rest noisy queries according to the previously accepted predictions. Experiments show that our method can significantly boost the performance of query-based detectors in crowded scenes. Equipped with our approach, Sparse RCNN achieves 92.0\% $\text{AP}$, 41.4\% $\text{MR}^{-2}$ and 83.2\% $\text{JI}$ on the challenging CrowdHuman \cite{shao2018crowdhuman} dataset, outperforming the box-based method MIP \cite{chu2020detection} that specifies in handling crowded scenarios. Moreover, the proposed method, robust to crowdedness, can still obtain consistent improvements on moderately and slightly crowded datasets like CityPersons \cite{zhang2017citypersons} and COCO \cite{lin2014microsoft}. Code will be made publicly available at https://github.com/megvii-model/Iter-E2EDET.

arXiv:2301.01615

StereoDistill: Pick the Cream from LiDAR for Distilling Stereo-based 3D Object Detection

In this paper, we propose a cross-modal distillation method named StereoDistill to narrow the gap between the stereo and LiDAR-based approaches via distilling the stereo detectors from the superior LiDAR model at the response level, which is usually overlooked in 3D object detection distillation. The key designs of StereoDistill are: the X-component Guided Distillation~(XGD) for regression and the Cross-anchor Logit Distillation~(CLD) for classification. In XGD, instead of empirically adopting a threshold to select the high-quality teacher predictions as soft targets, we decompose the predicted 3D box into sub-components and retain the corresponding part for distillation if the teacher component pilot is consistent with ground truth to largely boost the number of positive predictions and alleviate the mimicking difficulty of the student model. For CLD, we aggregate the probability distribution of all anchors at the same position to encourage the highest probability anchor rather than individually distill the distribution at the anchor level. Finally, our StereoDistill achieves state-of-the-art results for stereo-based 3D detection on the KITTI test benchmark and extensive experiments on KITTI and Argoverse Dataset validate the effectiveness.

arXiv:2305.12476공식 코드 · Papers with Code

Zero-shot Visual Relation Detection via Composite Visual Cues from Large Language Models

Pretrained vision-language models, such as CLIP, have demonstrated strong generalization capabilities, making them promising tools in the realm of zero-shot visual recognition. Visual relation detection (VRD) is a typical task that identifies relationship (or interaction) types between object pairs within an image. However, naively utilizing CLIP with prevalent class-based prompts for zero-shot VRD has several weaknesses, e.g., it struggles to distinguish between different fine-grained relation types and it neglects essential spatial information of two objects. To this end, we propose a novel method for zero-shot VRD: RECODE, which solves RElation detection via COmposite DEscription prompts. Specifically, RECODE first decomposes each predicate category into subject, object, and spatial components. Then, it leverages large language models (LLMs) to generate description-based prompts (or visual cues) for each component. Different visual cues enhance the discriminability of similar relation categories from different perspectives, which significantly boosts performance in VRD. To dynamically fuse different cues, we further introduce a chain-of-thought method that prompts LLMs to generate reasonable weights for different visual cues. Extensive experiments on four VRD benchmarks have demonstrated the effectiveness and interpretability of RECODE.

arXiv:2403.10036

SparseFusion: Efficient Sparse Multi-Modal Fusion Framework for Long-Range 3D Perception

Multi-modal 3D object detection has exhibited significant progress in recent years. However, most existing methods can hardly scale to long-range scenarios due to their reliance on dense 3D features, which substantially escalate computational demands and memory usage. In this paper, we introduce SparseFusion, a novel multi-modal fusion framework fully built upon sparse 3D features to facilitate efficient long-range perception. The core of our method is the Sparse View Transformer module, which selectively lifts regions of interest in 2D image space into the unified 3D space. The proposed module introduces sparsity from both semantic and geometric aspects which only fill grids that foreground objects potentially reside in. Comprehensive experiments have verified the efficiency and effectiveness of our framework in long-range 3D perception. Remarkably, on the long-range Argoverse2 dataset, SparseFusion reduces memory footprint and accelerates the inference by about two times compared to dense detectors. It also achieves state-of-the-art performance with mAP of 41.2% and CDS of 32.1%. The versatility of SparseFusion is also validated in the temporal object detection task and 3D lane detection task. Codes will be released upon acceptance.

논문 ID: eprint/1006248

‘Unexpected item in the bagging area’: Anomaly Detection in X-ray Security Images

The role of Anomaly Detection in X-ray security imaging, as a supplement to targeted threat detection, is described; and a taxonomy of anomalies types in this domain is presented. Algorithms are described for detecting appearance anomalies, of shape, texture and density; and semantic anomalies of object category presence. The anomalies are detected on the basis of representations extracted from a convolutional neural network pre-trained to identify object categories in photographs: from the final pooling layer for appearance anomalies, and from the logit layer for semantic anomalies. The distribution of representations in normal data are modelled using high-dimensional, full- covariance, Gaussians; and anomalies are scored according to their likelihood relative to those models. The algorithms are tested on X-ray parcel images using stream-of-commerce data as the normal class, and parcels with firearms present as examples of anomalies to be detected. Despite the representations being learnt for photographic images, and the varied contents of stream-of- commerce parcels; the system, trained on stream-of-commerce images only, is able to detect 90% of firearms as anomalies, while raising false alarms on 18% of stream-of-commerce.

arXiv:2403.07263공식 코드 · Papers with Code

Adaptive Bounding Box Uncertainties via Two-Step Conformal Prediction

Quantifying a model's predictive uncertainty is essential for safety-critical applications such as autonomous driving. We consider quantifying such uncertainty for multi-object detection. In particular, we leverage conformal prediction to obtain uncertainty intervals with guaranteed coverage for object bounding boxes. One challenge in doing so is that bounding box predictions are conditioned on the object's class label. Thus, we develop a novel two-step conformal approach that propagates uncertainty in predicted class labels into the uncertainty intervals of bounding boxes. This broadens the validity of our conformal coverage guarantees to include incorrectly classified objects, thus offering more actionable safety assurances. Moreover, we investigate novel ensemble and quantile regression formulations to ensure the bounding box intervals are adaptive to object size, leading to a more balanced coverage. Validating our two-step approach on real-world datasets for 2D bounding box localization, we find that desired coverage levels are satisfied with practically tight predictive uncertainty intervals.

arXiv:2108.07482

G-DetKD: Towards General Distillation Framework for Object Detectors via Contrastive and Semantic-guided Feature Imitation

In this paper, we investigate the knowledge distillation (KD) strategy for object detection and propose an effective framework applicable to both homogeneous and heterogeneous student-teacher pairs. The conventional feature imitation paradigm introduces imitation masks to focus on informative foreground areas while excluding the background noises. However, we find that those methods fail to fully utilize the semantic information in all feature pyramid levels, which leads to inefficiency for knowledge distillation between FPN-based detectors. To this end, we propose a novel semantic-guided feature imitation technique, which automatically performs soft matching between feature pairs across all pyramid levels to provide the optimal guidance to the student. To push the envelop even further, we introduce contrastive distillation to effectively capture the information encoded in the relationship between different feature regions. Finally, we propose a generalized detection KD pipeline, which is capable of distilling both homogeneous and heterogeneous detector pairs. Our method consistently outperforms the existing detection KD techniques, and works when (1) components in the framework are used separately and in conjunction; (2) for both homogeneous and heterogenous student-teacher pairs and (3) on multiple detection benchmarks. With a powerful X101-FasterRCNN-Instaboost detector as the teacher, R50-FasterRCNN reaches 44.0% AP, R50-RetinaNet reaches 43.3% AP and R50-FCOS reaches 43.1% AP on COCO dataset.

arXiv:2109.01057

Shot boundary detection method based on a new extensive dataset and mixed features

Shot boundary detection in video is one of the key stages of video data processing. A new method for shot boundary detection based on several video features, such as color histograms and object boundaries, has been proposed. The developed algorithm was tested on the open BBC Planet Earth [1] and RAI [2] datasets, and the MSU CC datasets, based on videos used in the video codec comparison conducted at MSU, as well as videos from the IBM set, were also plotted. The total dataset for algorithm development and testing exceeded the known TRECVID datasets. Based on the test results, the proposed algorithm for scene change detection outperformed its counterparts with a final F-score of 0.9794.