arXiv subjects

Shanshan Zhang

Publications and source records attributed to Shanshan Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2025

OcRFDet: Object-Centric Radiance Fields for Multi-View 3D Object Detection in Autonomous Driving

Current multi-view 3D object detection methods typically transfer 2D features into 3D space using depth estimation or 3D position encoder, but in a fully data-driven and implicit manner, which limits the detection performance. Inspired by the success of radiance fields on 3D reconstruction, we assume they can be used to enhance the detector's ability of 3D geometry estimation. However, we observe a decline in detection performance, when we directly use them for 3D rendering as an auxiliary task. From our analysis, we find the performance drop is caused by the strong responses on the background when rendering the whole scene. To address this problem, we propose object-centric radiance fields, focusing on modeling foreground objects while discarding background noises. Specifically, we employ Object-centric Radiance Fields (OcRF) to enhance 3D voxel features via an auxiliary task of rendering foreground objects. We further use opacity - the side-product of rendering- to enhance the 2D foreground BEV features via Height-aware Opacity-based Attention (HOA), where attention maps at different height levels are generated separately via multiple networks in parallel. Extensive experiments on the nuScenes validation and test datasets demonstrate that our OcRFDet achieves superior performance, outperforming previous state-of-the-art methods with 57.2$\%$ mAP and 64.8$\%$ NDS on the nuScenes test benchmark. Code will be available at https://github.com/Mingqj/OcRFDet.

cs.CV↗

arXiv2025

DepthFusion: Depth-Aware Hybrid Feature Fusion for LiDAR-Camera 3D Object Detection

State-of-the-art LiDAR-camera 3D object detectors usually focus on feature fusion. However, they neglect the factor of depth while designing the fusion strategy. In this work, we are the first to observe that different modalities play different roles as depth varies via statistical analysis and visualization. Based on this finding, we propose a Depth-Aware Hybrid Feature Fusion (DepthFusion) strategy that guides the weights of point cloud and RGB image modalities by introducing depth encoding at both global and local levels. Specifically, the Depth-GFusion module adaptively adjusts the weights of image Bird's-Eye-View (BEV) features in multi-modal global features via depth encoding. Furthermore, to compensate for the information lost when transferring raw features to the BEV space, we propose a Depth-LFusion module, which adaptively adjusts the weights of original voxel features and multi-view image features in multi-modal local features via depth encoding. Extensive experiments on the nuScenes and KITTI datasets demonstrate that our DepthFusion method surpasses previous state-of-the-art methods. Moreover, our DepthFusion is more robust to various kinds of corruptions, outperforming previous methods on the nuScenes-C dataset.

cs.CV↗

arXiv2024

SoccerNet 2024 Challenges Results

The SoccerNet 2024 challenges represent the fourth annual video understanding challenges organized by the SoccerNet team. These challenges aim to advance research across multiple themes in football, including broadcast video understanding, field understanding, and player understanding. This year, the challenges encompass four vision-based tasks. (1) Ball Action Spotting, focusing on precisely localizing when and which soccer actions related to the ball occur, (2) Dense Video Captioning, focusing on describing the broadcast with natural language and anchored timestamps, (3) Multi-View Foul Recognition, a novel task focusing on analyzing multiple viewpoints of a potential foul incident to classify whether a foul occurred and assess its severity, (4) Game State Reconstruction, another novel task focusing on reconstructing the game state from broadcast videos onto a 2D top-view map of the field. Detailed information about the tasks, challenges, and leaderboards can be found at https://www.soccer-net.org, with baselines and development kits available at https://github.com/SoccerNet.

cs.CV↗

arXiv2024

Imagine the Unseen: Occluded Pedestrian Detection via Adversarial Feature Completion

Pedestrian detection has significantly progressed in recent years, thanks to the development of DNNs. However, detection performance at occluded scenes is still far from satisfactory, as occlusion increases the intra-class variance of pedestrians, hindering the model from finding an accurate classification boundary between pedestrians and background clutters. From the perspective of reducing intra-class variance, we propose to complete features for occluded regions so as to align the features of pedestrians across different occlusion patterns. An important premise for feature completion is to locate occluded regions. From our analysis, channel features of different pedestrian proposals only show high correlation values at visible parts and thus feature correlations can be used to model occlusion patterns. In order to narrow down the gap between completed features and real fully visible ones, we propose an adversarial learning method, which completes occluded features with a generator such that they can hardly be distinguished by the discriminator from real fully visible features. We report experimental results on the CityPersons, Caltech and CrowdHuman datasets. On CityPersons, we show significant improvements over five different baseline detectors, especially on the heavy occlusion subset. Furthermore, we show that our proposed method FeatComp++ achieves state-of-the-art results on all the above three datasets without relying on extra cues.

cs.CV↗

arXiv2024

Fairness Optimization for Intelligent Reflecting Surface Aided Uplink Rate-Splitting Multiple Access

This paper studies the fair transmission design for an intelligent reflecting surface (IRS) aided rate-splitting multiple access (RSMA). IRS is used to establish a good signal propagation environment and enhance the RSMA transmission performance. The fair rate adaption problem is constructed as a max-min optimization problem. To solve the optimization problem, we adopt an alternative optimization (AO) algorithm to optimize the power allocation, beamforming, and decoding order, respectively. A generalized power iteration (GPI) method is proposed to optimize the receive beamforming, which can improve the minimum rate of devices and reduce the optimization complexity. At the base station (BS), a successive group decoding (SGD) algorithm is proposed to tackle the uplink signal estimation, which trades off the fairness and complexity of decoding. At the same time, we also consider robust communication with imperfect channel state information at the transmitter (CSIT), which studies robust optimization by using lower bound expressions on the expected data rates. Extensive numerical results show that the proposed optimization algorithm can significantly improve the performance of fairness. It also provides reliable results for uplink communication with imperfect CSIT.

cs.IT↗

arXiv2024

Rate-Splitting Multiple Access for Transmissive Reconfigurable Intelligent Surface Transceiver Empowered ISAC System

In this paper, a novel transmissive reconfigurable intelligent surface (TRIS) transceiver empowered integrated sensing and communications (ISAC) system is proposed for future multi-demand terminals. To address interference management, we implement rate-splitting multiple access (RSMA), where the common stream is independently designed for the sensing service. We introduce the sensing quality of service (QoS) criteria based on this structure and construct an optimization problem with the sensing QoS criteria as the objective function to optimize the sensing stream precoding matrix and the communication stream precoding matrix. Due to the coupling of optimization variables, the formulated problem is a non-convex optimization problem that cannot be solved directly. To tackle the above-mentioned challenging problem, alternating optimization (AO) is utilized to decouple the optimization variables. Specifically, the problem is decoupled into three subproblems about the sensing stream precoding matrix, the communication stream precoding matrix, and the auxiliary variables, which is solved alternatively through AO until the convergence is reached. For solving the problem, successive convex approximation (SCA) is applied to deal with the sum-rate threshold constraints on communications, and difference-of-convex (DC) programming is utilized to solve rank-one non-convex constraints. Numerical simulation results verify the superiority of the proposed scheme in terms of improving the communication and sensing QoS.

cs.IT↗

arXiv2023

Divide and Conquer: Hybrid Pre-training for Person Search

Large-scale pre-training has proven to be an effective method for improving performance across different tasks. Current person search methods use ImageNet pre-trained models for feature extraction, yet it is not an optimal solution due to the gap between the pre-training task and person search task (as a downstream task). Therefore, in this paper, we focus on pre-training for person search, which involves detecting and re-identifying individuals simultaneously. Although labeled data for person search is scarce, datasets for two sub-tasks person detection and re-identification are relatively abundant. To this end, we propose a hybrid pre-training framework specifically designed for person search using sub-task data only. It consists of a hybrid learning paradigm that handles data with different kinds of supervisions, and an intra-task alignment module that alleviates domain discrepancy under limited resources. To the best of our knowledge, this is the first work that investigates how to support full-task pre-training using sub-task data. Extensive experiments demonstrate that our pre-trained model can achieve significant improvements across diverse protocols, such as person search method, fine-tuning data, pre-training data and model backbone. For example, our model improves ResNet50 based NAE by 10.3% relative improvement w.r.t. mAP. Our code and pre-trained models are released for plug-and-play usage to the person search community.

cs.CV↗

arXiv2023

Fairness Optimization of RSMA for Uplink Communication based on Intelligent Reflecting Surface

In this paper, we propose a rate-splitting multiple access (RSMA) scheme for uplink wireless communication systems with intelligent reflecting surface (IRS) aided. In the considered model, IRS is adopted to overcome power attenuation caused by path loss. We construct a max-min fairness optimization problem to obtain the resource allocation, including the receive beamforming at the base station (BS) and phase-shift beamforming at IRS. We also introduce a successive group decoding (SGD) algorithm at the receiver, which trades off the fairness and complexity of decoding. In the simulation, the results show that the proposed scheme has superiority in improving the fairness of uplink communication.

cs.IT↗

arXiv2023

Joint Device Activity Detection, Channel Estimation and Signal Detection for Massive Grant-free Access via BiGAMP

Massive access has been challenging for the fifth generation (5G) and beyond since the abundance of devices causes communication overload to skyrocket. In an uplink massive access scenario, device traffic is sporadic in any given coherence time. Thus, channels across the antennas of each device exhibit correlation, which can be characterized by the row sparse channel matrix structure. In this work, we develop a bilinear generalized approximate message passing (BiGAMP) algorithm based on the row sparse channel matrix structure. This algorithm can jointly detect device activities, estimate channels, and detect signals in massive multiple-input multiple-output (MIMO) systems by alternating updates between channel matrices and signal matrices. The signal observation provides additional information for performance improvement compared to the existing algorithms. We further analyze state evolution (SE) to measure the performance of the proposed algorithm and characterize the convergence condition for SE. Moreover, we perform theoretical analysis on the error probability of device activity detection, the mean square error of channel estimation, and the symbol error rate of signal detection. The numerical results demonstrate the superiority of the proposed algorithm over the state-of-the-art methods in DADCE-SD, and the numerical results are relatively close to the theoretical analysis results.

cs.IT↗

arXiv2022

MFA-Conformer: Multi-scale Feature Aggregation Conformer for Automatic Speaker Verification

In this paper, we present Multi-scale Feature Aggregation Conformer (MFA-Conformer), an easy-to-implement, simple but effective backbone for automatic speaker verification based on the Convolution-augmented Transformer (Conformer). The architecture of the MFA-Conformer is inspired by recent stateof-the-art models in speech recognition and speaker verification. Firstly, we introduce a convolution subsampling layer to decrease the computational cost of the model. Secondly, we adopt Conformer blocks which combine Transformers and convolution neural networks (CNNs) to capture global and local features effectively. Finally, the output feature maps from all Conformer blocks are concatenated to aggregate multi-scale representations before final pooling. We evaluate the MFA-Conformer on the widely used benchmarks. The best system obtains 0.64%, 1.29% and 1.63% EER on VoxCeleb1-O, SITW.Dev, and SITW.Eval set, respectively. MFA-Conformer significantly outperforms the popular ECAPA-TDNN systems in both recognition performance and inference speed. Last but not the least, the ablation studies clearly demonstrate that the combination of global and local feature learning can lead to robust and accurate speaker embedding extraction. We have also released the code for future comparison.

cs.SD↗

arXiv2022

Learning Audio-Visual embedding for Person Verification in the Wild

It has already been observed that audio-visual embedding is more robust than uni-modality embedding for person verification. Here, we proposed a novel audio-visual strategy that considers aggregators from a fusion perspective. First, we introduced weight-enhanced attentive statistics pooling for the first time in face verification. We find that a strong correlation exists between modalities during pooling, so joint attentive pooling is proposed which contains cycle consistency to learn the implicit inter-frame weight. Finally, each modality is fused with a gated attention mechanism to gain robust audio-visual embedding. All the proposed models are trained on the VoxCeleb2 dev dataset and the best system obtains 0.18%, 0.27%, and 0.49% EER on three official trial lists of VoxCeleb1 respectively, which is to our knowledge the best-published results for person verification.

cs.CV↗

arXiv2022

Grouped Adaptive Loss Weighting for Person Search

Person search is an integrated task of multiple sub-tasks such as foreground/background classification, bounding box regression and person re-identification. Therefore, person search is a typical multi-task learning problem, especially when solved in an end-to-end manner. Recently, some works enhance person search features by exploiting various auxiliary information, e.g. person joint keypoints, body part position, attributes, etc., which brings in more tasks and further complexifies a person search model. The inconsistent convergence rate of each task could potentially harm the model optimization. A straightforward solution is to manually assign different weights to different tasks, compensating for the diverse convergence rates. However, given the special case of person search, i.e. with a large number of tasks, it is impractical to weight the tasks manually. To this end, we propose a Grouped Adaptive Loss Weighting (GALW) method which adjusts the weight of each task automatically and dynamically. Specifically, we group tasks according to their convergence rates. Tasks within the same group share the same learnable weight, which is dynamically assigned by considering the loss uncertainty. Experimental results on two typical benchmarks, CUHK-SYSU and PRW, demonstrate the effectiveness of our method.

cs.CV↗

arXiv2022

PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection

In this paper, we delve into two key techniques in Semi-Supervised Object Detection (SSOD), namely pseudo labeling and consistency training. We observe that these two techniques currently neglect some important properties of object detection, hindering efficient learning on unlabeled data. Specifically, for pseudo labeling, existing works only focus on the classification score yet fail to guarantee the localization precision of pseudo boxes; For consistency training, the widely adopted random-resize training only considers the label-level consistency but misses the feature-level one, which also plays an important role in ensuring the scale invariance. To address the problems incurred by noisy pseudo boxes, we design Noisy Pseudo box Learning (NPL) that includes Prediction-guided Label Assignment (PLA) and Positive-proposal Consistency Voting (PCV). PLA relies on model predictions to assign labels and makes it robust to even coarse pseudo boxes; while PCV leverages the regression consistency of positive proposals to reflect the localization quality of pseudo boxes. Furthermore, in consistency training, we propose Multi-view Scale-invariant Learning (MSL) that includes mechanisms of both label- and feature-level consistency, where feature consistency is achieved by aligning shifted feature pyramids between two images with identical content but varied scales. On COCO benchmark, our method, termed PSEudo labeling and COnsistency training (PseCo), outperforms the SOTA (Soft Teacher) by 2.0, 1.8, 2.0 points under 1%, 5%, and 10% labelling ratios, respectively. It also significantly improves the learning efficiency for SSOD, e.g., PseCo halves the training time of the SOTA approach but achieves even better performance. Code is available at https://github.com/ligang-cs/PseCo.

cs.CV↗

arXiv2022

DTG-SSOD: Dense Teacher Guidance for Semi-Supervised Object Detection

The Mean-Teacher (MT) scheme is widely adopted in semi-supervised object detection (SSOD). In MT, the sparse pseudo labels, offered by the final predictions of the teacher (e.g., after Non Maximum Suppression (NMS) post-processing), are adopted for the dense supervision for the student via hand-crafted label assignment. However, the sparse-to-dense paradigm complicates the pipeline of SSOD, and simultaneously neglects the powerful direct, dense teacher supervision. In this paper, we attempt to directly leverage the dense guidance of teacher to supervise student training, i.e., the dense-to-dense paradigm. Specifically, we propose the Inverse NMS Clustering (INC) and Rank Matching (RM) to instantiate the dense supervision, without the widely used, conventional sparse pseudo labels. INC leads the student to group candidate boxes into clusters in NMS as the teacher does, which is implemented by learning grouping information revealed in NMS procedure of the teacher. After obtaining the same grouping scheme as the teacher via INC, the student further imitates the rank distribution of the teacher over clustered candidates through Rank Matching. With the proposed INC and RM, we integrate Dense Teacher Guidance into Semi-Supervised Object Detection (termed DTG-SSOD), successfully abandoning sparse pseudo labels and enabling more informative learning on unlabeled data. On COCO benchmark, our DTG-SSOD achieves state-of-the-art performance under various labelling ratios. For example, under 10% labelling ratio, DTG-SSOD improves the supervised baseline from 26.9 to 35.9 mAP, outperforming the previous best method Soft Teacher by 1.9 points.

cs.CV↗

arXiv2022

Adversarial Sample Detection for Speaker Verification by Neural Vocoders

Automatic speaker verification (ASV), one of the most important technology for biometric identification, has been widely adopted in security-critical applications. However, ASV is seriously vulnerable to recently emerged adversarial attacks, yet effective countermeasures against them are limited. In this paper, we adopt neural vocoders to spot adversarial samples for ASV. We use the neural vocoder to re-synthesize audio and find that the difference between the ASV scores for the original and re-synthesized audio is a good indicator for discrimination between genuine and adversarial samples. This effort is, to the best of our knowledge, among the first to pursue such a technical direction for detecting time-domain adversarial samples for ASV, and hence there is a lack of established baselines for comparison. Consequently, we implement the Griffin-Lim algorithm as the detection baseline. The proposed approach achieves effective detection performance that outperforms the baselines in all the settings. We also show that the neural vocoder adopted in the detection framework is dataset-independent. Our codes will be made open-source for future works to do fair comparison.

cs.SD↗

arXiv2022

Bi-level Alignment for Cross-Domain Crowd Counting

Recently, crowd density estimation has received increasing attention. The main challenge for this task is to achieve high-quality manual annotations on a large amount of training data. To avoid reliance on such annotations, previous works apply unsupervised domain adaptation (UDA) techniques by transferring knowledge learned from easily accessible synthetic data to real-world datasets. However, current state-of-the-art methods either rely on external data for training an auxiliary task or apply an expensive coarse-to-fine estimation. In this work, we aim to develop a new adversarial learning based method, which is simple and efficient to apply. To reduce the domain gap between the synthetic and real data, we design a bi-level alignment framework (BLA) consisting of (1) task-driven data alignment and (2) fine-grained feature alignment. In contrast to previous domain augmentation methods, we introduce AutoML to search for an optimal transform on source, which well serves for the downstream task. On the other hand, we do fine-grained alignment for foreground and background separately to alleviate the alignment difficulty. We evaluate our approach on five real-world crowd counting benchmarks, where we outperform existing approaches by a large margin. Also, our approach is simple, easy to implement and efficient to apply. The code is publicly available at https://github.com/Yankeegsj/BLA.

cs.CV↗

arXiv2021

Keypoint Message Passing for Video-based Person Re-Identification

Video-based person re-identification (re-ID) is an important technique in visual surveillance systems which aims to match video snippets of people captured by different cameras. Existing methods are mostly based on convolutional neural networks (CNNs), whose building blocks either process local neighbor pixels at a time, or, when 3D convolutions are used to model temporal information, suffer from the misalignment problem caused by person movement. In this paper, we propose to overcome the limitations of normal convolutions with a human-oriented graph method. Specifically, features located at person joint keypoints are extracted and connected as a spatial-temporal graph. These keypoint features are then updated by message passing from their connected nodes with a graph convolutional network (GCN). During training, the GCN can be attached to any CNN-based person re-ID model to assist representation learning on feature maps, whilst it can be dropped after training for better inference speed. Our method brings significant improvements over the CNN-based baseline model on the MARS dataset with generated person keypoints and a newly annotated dataset: PoseTrackReID. It also defines a new state-of-the-art method in terms of top-1 accuracy and mean average precision in comparison to prior works.

cs.CV↗

arXiv2021

Knowledge Distillation for Object Detection via Rank Mimicking and Prediction-guided Feature Imitation

Knowledge Distillation (KD) is a widely-used technology to inherit information from cumbersome teacher models to compact student models, consequently realizing model compression and acceleration. Compared with image classification, object detection is a more complex task, and designing specific KD methods for object detection is non-trivial. In this work, we elaborately study the behaviour difference between the teacher and student detection models, and obtain two intriguing observations: First, the teacher and student rank their detected candidate boxes quite differently, which results in their precision discrepancy. Second, there is a considerable gap between the feature response differences and prediction differences between teacher and student, indicating that equally imitating all the feature maps of the teacher is the sub-optimal choice for improving the student's accuracy. Based on the two observations, we propose Rank Mimicking (RM) and Prediction-guided Feature Imitation (PFI) for distilling one-stage detectors, respectively. RM takes the rank of candidate boxes from teachers as a new form of knowledge to distill, which consistently outperforms the traditional soft label distillation. PFI attempts to correlate feature differences with prediction differences, making feature imitation directly help to improve the student's accuracy. On MS COCO and PASCAL VOC benchmarks, extensive experiments are conducted on various detectors with different backbones to validate the effectiveness of our method. Specifically, RetinaNet with ResNet50 achieves 40.4% mAP in MS COCO, which is 3.5% higher than its baseline, and also outperforms previous KD methods.

cs.CV↗