arXiv subjects

Qian Zhang

Publications and source records attributed to Qian Zhang.

At least 307 records · Page 17Linked to original sources

arXiv2022

Multi-Camera Calibration Free BEV Representation for 3D Object Detection

In advanced paradigms of autonomous driving, learning Bird's Eye View (BEV) representation from surrounding views is crucial for multi-task framework. However, existing methods based on depth estimation or camera-driven attention are not stable to obtain transformation under noisy camera parameters, mainly with two challenges, accurate depth prediction and calibration. In this work, we present a completely Multi-Camera Calibration Free Transformer (CFT) for robust BEV representation, which focuses on exploring implicit mapping, not relied on camera intrinsics and extrinsics. To guide better feature learning from image views to BEV, CFT mines potential 3D information in BEV via our designed position-aware enhancement (PA). Instead of camera-driven point-wise or global transformation, for interaction within more effective region and lower computation cost, we propose a view-aware attention which also reduces redundant computation and promotes converge. CFT achieves 49.7% NDS on the nuScenes detection task leaderboard, which is the first work removing camera parameters, comparable to other geometry-guided methods. Without temporal input and other modal information, CFT achieves second highest performance with a smaller image input 1600 * 640. Thanks to view-attention variant, CFT reduces memory and transformer FLOPs for vanilla attention by about 12% and 60%, respectively, with improved NDS by 1.0%. Moreover, its natural robustness to noisy camera parameters makes CFT more competitive.

cs.CV↗

arXiv2022

Semi-supervised Body Parsing and Pose Estimation for Enhancing Infant General Movement Assessment

General movement assessment (GMA) of infant movement videos (IMVs) is an effective method for early detection of cerebral palsy (CP) in infants. We demonstrate in this paper that end-to-end trainable neural networks for image sequence recognition can be applied to achieve good results in GMA, and more importantly, augmenting raw video with infant body parsing and pose estimation information can significantly improve performance. To solve the problem of efficiently utilizing partially labeled IMVs for body parsing, we propose a semi-supervised model, termed SiamParseNet (SPN), which consists of two branches, one for intra-frame body parts segmentation and another for inter-frame label propagation. During training, the two branches are jointly trained by alternating between using input pairs of only labeled frames and input of both labeled and unlabeled frames. We also investigate training data augmentation by proposing a factorized video generative adversarial network (FVGAN) to synthesize novel labeled frames for training. When testing, we employ a multi-source inference mechanism, where the final result for a test frame is either obtained via the segmentation branch or via propagation from a nearby key frame. We conduct extensive experiments for body parsing using SPN on two infant movement video datasets, where SPN coupled with FVGAN achieves state-of-the-art performance. We further demonstrate that SPN can be easily adapted to the infant pose estimation task with superior performance. Last but not least, we explore the clinical application of our method for GMA. We collected a new clinical IMV dataset with GMA annotations, and our experiments show that SPN models for body parsing and pose estimation trained on the first two datasets generalize well to the new clinical dataset and their results can significantly boost the CRNN-based GMA prediction performance.

cs.CV↗

arXiv2022

Spiking Neural Operators for Scientific Machine Learning

The main computational task of Scientific Machine Learning (SciML) is function regression, required both for inputs as well as outputs of a simulation. Physics-Informed Neural Networks (PINNs) and neural operators (such as DeepONet) have been very effective in solving Partial Differential Equations (PDEs), but they tax computational resources heavily and cannot be readily adopted for edge computing. Here, we address this issue by considering Spiking Neural Networks (SNNs), which have shown promise in reducing energy consumption by two orders of magnitude or more. We present a SNN-based method to perform regression, which has been a challenge due to the inherent difficulty in representing a function's input domain and continuous output values as spikes. We first propose a new method for encoding continuous values into spikes based on a triangular matrix in space and time, and demonstrate its better performance compared to the existing methods. Next, we demonstrate that using a simple SNN architecture consisting of Leaky Integrate and Fire (LIF) activation and two dense layers, we can achieve relatively accurate function regression results. Moreover, we can replace the LIF with a trained Multi-Layer Perceptron (MLP) network and obtain comparable results but three times faster. Then, we introduce the DeepONet, consisting of a branch (typically a Fully-connected Neural Network, FNN) for inputs and a trunk (also a FNN) for outputs. We can build a spiking DeepONet by either replacing the branch or the trunk by a SNN. We demonstrate this new approach for classification using the SNN in the branch, achieving results comparable to the literature. Finally, we design a spiking DeepONet for regression by replacing its trunk with a SNN, and achieve good accuracy for approximating functions as well as inferring solutions of differential equations.

cs.NE↗

arXiv2022

Improving Visual-Semantic Embedding with Adaptive Pooling and Optimization Objective

Visual-Semantic Embedding (VSE) aims to learn an embedding space where related visual and semantic instances are close to each other. Recent VSE models tend to design complex structures to pool visual and semantic features into fixed-length vectors and use hard triplet loss for optimization. However, we find that: (1) combining simple pooling methods is no worse than these sophisticated methods; and (2) only considering the most difficult-to-distinguish negative sample leads to slow convergence and poor Recall@K improvement. To this end, we propose an adaptive pooling strategy that allows the model to learn how to aggregate features through a combination of simple pooling methods. We also introduce a strategy to dynamically select a group of negative samples to make the optimization converge faster and perform better. Experimental results on Flickr30K and MS-COCO demonstrate that a standard VSE using our pooling and optimization strategies outperforms current state-of-the-art systems (at least 1.0% on the metrics of recall) in image-to-text and text-to-image retrieval. Source code of our experiments is available at https://github.com/96-Zachary/vse_2ad.

cs.MM↗

arXiv2022

ELMformer: Efficient Raw Image Restoration with a Locally Multiplicative Transformer

In order to get raw images of high quality for downstream Image Signal Process (ISP), in this paper we present an Efficient Locally Multiplicative Transformer called ELMformer for raw image restoration. ELMformer contains two core designs especially for raw images whose primitive attribute is single-channel. The first design is a Bi-directional Fusion Projection (BFP) module, where we consider both the color characteristics of raw images and spatial structure of single-channel. The second one is that we propose a Locally Multiplicative Self-Attention (L-MSA) scheme to effectively deliver information from the local space to relevant parts. ELMformer can efficiently reduce the computational consumption and perform well on raw image restoration tasks. Enhanced by these two core designs, ELMformer achieves the highest performance and keeps the lowest FLOPs on raw denoising and raw deblurring benchmarks compared with state-of-the-arts. Extensive experiments demonstrate the superiority and generalization ability of ELMformer. On SIDD benchmark, our method has even better denoising performance than ISP-based methods which need huge amount of additional sRGB training images. The codes are release at https://github.com/leonmakise/ELMformer.

cs.CV↗

arXiv2022

Adversarial Relighting Against Face Recognition

Deep face recognition (FR) has achieved significantly high accuracy on several challenging datasets and fosters successful real-world applications, even showing high robustness to the illumination variation that is usually regarded as a main threat to the FR system. However, in the real world, illumination variation caused by diverse lighting conditions cannot be fully covered by the limited face dataset. In this paper, we study the threat of lighting against FR from a new angle, i.e., adversarial attack, and identify a new task, i.e., adversarial relighting. Given a face image, adversarial relighting aims to produce a naturally relighted counterpart while fooling the state-of-the-art deep FR methods. To this end, we first propose the physical modelbased adversarial relighting attack (ARA) denoted as albedoquotient-based adversarial relighting attack (AQ-ARA). It generates natural adversarial light under the physical lighting model and guidance of FR systems and synthesizes adversarially relighted face images. Moreover, we propose the auto-predictive adversarial relighting attack (AP-ARA) by training an adversarial relighting network (ARNet) to automatically predict the adversarial light in a one-step manner according to different input faces, allowing efficiency-sensitive applications. More importantly, we propose to transfer the above digital attacks to physical ARA (PhyARA) through a precise relighting device, making the estimated adversarial lighting condition reproducible in the real world. We validate our methods on three state-of-the-art deep FR methods, i.e., FaceNet, ArcFace, and CosFace, on two public datasets. The extensive and insightful results demonstrate our work can generate realistic adversarial relighted face images fooling face recognition tasks easily, revealing the threat of specific light directions and strengths.

cs.CV↗

arXiv2022

MixSKD: Self-Knowledge Distillation from Mixup for Image Recognition

Unlike the conventional Knowledge Distillation (KD), Self-KD allows a network to learn knowledge from itself without any guidance from extra networks. This paper proposes to perform Self-KD from image Mixture (MixSKD), which integrates these two techniques into a unified framework. MixSKD mutually distills feature maps and probability distributions between the random pair of original images and their mixup images in a meaningful way. Therefore, it guides the network to learn cross-image knowledge by modelling supervisory signals from mixup images. Moreover, we construct a self-teacher network by aggregating multi-stage feature maps for providing soft labels to supervise the backbone classifier, further improving the efficacy of self-boosting. Experiments on image classification and transfer learning to object detection and semantic segmentation demonstrate that MixSKD outperforms other state-of-the-art Self-KD and data augmentation methods. The code is available at https://github.com/winycg/Self-KD-Lib.

cs.CV↗

arXiv2022

ICAF: Iterative Contrastive Alignment Framework for Multimodal Abstractive Summarization

Integrating multimodal knowledge for abstractive summarization task is a work-in-progress research area, with present techniques inheriting fusion-then-generation paradigm. Due to semantic gaps between computer vision and natural language processing, current methods often treat multiple data points as separate objects and rely on attention mechanisms to search for connection in order to fuse together. In addition, missing awareness of cross-modal matching from many frameworks leads to performance reduction. To solve these two drawbacks, we propose an Iterative Contrastive Alignment Framework (ICAF) that uses recurrent alignment and contrast to capture the coherences between images and texts. Specifically, we design a recurrent alignment (RA) layer to gradually investigate fine-grained semantical relationships between image patches and text tokens. At each step during the encoding process, cross-modal contrastive losses are applied to directly optimize the embedding space. According to ROUGE, relevance scores, and human evaluation, our model outperforms the state-of-the-art baselines on MSMO dataset. Experiments on the applicability of our proposed framework and hyperparameters settings have been also conducted.

cs.AI↗

arXiv2022

Modeling Complex Dependencies for Session-based Recommendations via Graph Neural Networks

Session-based recommendations (SBRs) capture items' dependencies from the sessions to recommend the next item. In recent years, Graph neural networks (GNN) based SBRs have become the mainstream of SBRs benefited from the superiority of GNN in modeling complex dependencies. Based on a strong assumption of adjacent dependency, any two adjacent items in a session are necessarily dependent in most GNN-based SBRs. However, we argue that due to the uncertainty and complexity of user behaviors, adjacency does not necessarily indicate dependency. However, the above assumptions do not always hold in actual recommendation scenarios, so it can easily lead to two drawbacks: (1) false dependencies occur in the session because there are adjacent but not really dependent items, and (2) the missing of true dependencies occur in the session because there are non-adjacent but actually dependent items. These drawbacks significantly affect item representation learning, degrading the downstream recommendation performance. To address these deficiencies, we propose a novel review-refined inter-item graph neural network (RI-GNN), which utilizes topic information extracted from the reviews of items to improve dependencies between items. Experiments on two public real-world datasets demonstrate that RI-GNN outperforms SOTA methods.

cs.IR↗

arXiv2022

Vision-based Uneven BEV Representation Learning with Polar Rasterization and Surface Estimation

In this work, we propose PolarBEV for vision-based uneven BEV representation learning. To adapt to the foreshortening effect of camera imaging, we rasterize the BEV space both angularly and radially, and introduce polar embedding decomposition to model the associations among polar grids. Polar grids are rearranged to an array-like regular representation for efficient processing. Besides, to determine the 2D-to-3D correspondence, we iteratively update the BEV surface based on a hypothetical plane, and adopt height-based feature transformation. PolarBEV keeps real-time inference speed on a single 2080Ti GPU, and outperforms other methods for both BEV semantic segmentation and BEV instance segmentation. Thorough ablations are presented to validate the design. The code will be released at \url{https://github.com/SuperZ-Liu/PolarBEV}.

cs.CV↗

arXiv2022

RACS2: A Framework of Remote Autonomous Control System for Telescope Observation and its application

As the demand of astronomical observation rising, the telescope systems are becoming more and more complex. Thus, the observatory control software needs to be more intelligent, they have to control each instrument inside the observatory, finish the observation tasks autonomously, and report the information to users if needed. We developed a distributed autonomous observatory control framework named Remote Autonomous Control System 2nd, RACS2 to meet these requirements. The RACS2 framework uses decentralized distributed architecture, instrument control software and system service such as observation control service are implemented as different components. The communication between components is implemented based on a high-performance serialization library and a light-weighted messaging library.The interfaces towards python and Experimental Physics and Industrial Control System (EPICS) are implemented, so the RACS2 framework can communicate with EPICS based device control software and python-based software. Several system components including log, executor, scheduler and other modules are developed to help observation. Observation tasks can be programmed with python language, and the plans are scheduled by the scheduler component to achieve autonomous observation.A set of web service is implemented based on the FastAPI framework, with which user can control and manage the framework remotely.Based on the RACS2 framework, we have implemented the DATs telescope's observation system and the space object observation system.We performed remote autonomous observation and received many data with these systems.

astro-ph.IM↗

arXiv2022

Polar Parametrization for Vision-based Surround-View 3D Detection

3D detection based on surround-view camera system is a critical technique in autopilot. In this work, we present Polar Parametrization for 3D detection, which reformulates position parametrization, velocity decomposition, perception range, label assignment and loss function in polar coordinate system. Polar Parametrization establishes explicit associations between image patterns and prediction targets, exploiting the view symmetry of surround-view cameras as inductive bias to ease optimization and boost performance. Based on Polar Parametrization, we propose a surround-view 3D DEtection TRansformer, named PolarDETR. PolarDETR achieves promising performance-speed trade-off on different backbone configurations. Besides, PolarDETR ranks 1st on the leaderboard of nuScenes benchmark in terms of both 3D detection and 3D tracking at the submission time (Mar. 4th, 2022). Code will be released at \url{https://github.com/hustvl/PolarDETR}.

cs.CV↗

arXiv2022

Featurized Query R-CNN

The query mechanism introduced in the DETR method is changing the paradigm of object detection and recently there are many query-based methods have obtained strong object detection performance. However, the current query-based detection pipelines suffer from the following two issues. Firstly, multi-stage decoders are required to optimize the randomly initialized object queries, incurring a large computation burden. Secondly, the queries are fixed after training, leading to unsatisfying generalization capability. To remedy the above issues, we present featurized object queries predicted by a query generation network in the well-established Faster R-CNN framework and develop a Featurized Query R-CNN. Extensive experiments on the COCO dataset show that our Featurized Query R-CNN obtains the best speed-accuracy trade-off among all R-CNN detectors, including the recent state-of-the-art Sparse R-CNN detector. The code is available at {https://github.com/hustvl/Featurized-QueryRCNN.

cs.CV↗

arXiv2022

Efficient and Robust 2D-to-BEV Representation Learning via Geometry-guided Kernel Transformer

Learning Bird's Eye View (BEV) representation from surrounding-view cameras is of great importance for autonomous driving. In this work, we propose a Geometry-guided Kernel Transformer (GKT), a novel 2D-to-BEV representation learning mechanism. GKT leverages the geometric priors to guide the transformer to focus on discriminative regions and unfolds kernel features to generate BEV representation. For fast inference, we further introduce a look-up table (LUT) indexing method to get rid of the camera's calibrated parameters at runtime. GKT can run at $72.3$ FPS on 3090 GPU / $45.6$ FPS on 2080ti GPU and is robust to the camera deviation and the predefined BEV height. And GKT achieves the state-of-the-art real-time segmentation results, i.e., 38.0 mIoU (100m$\times$100m perception range at a 0.5m resolution) on the nuScenes val set. Given the efficiency, effectiveness, and robustness, GKT has great practical values in autopilot scenarios, especially for real-time running systems. Code and models will be available at \url{https://github.com/hustvl/GKT}.

cs.CV↗

arXiv2022

Contrastive Siamese Network for Semi-supervised Speech Recognition

This paper introduces contrastive siamese (c-siam) network, an architecture for leveraging unlabeled acoustic data in speech recognition. c-siam is the first network that extracts high-level linguistic information from speech by matching outputs of two identical transformer encoders. It contains augmented and target branches which are trained by: (1) masking inputs and matching outputs with a contrastive loss, (2) incorporating a stop gradient operation on the target branch, (3) using an extra learnable transformation on the augmented branch, (4) introducing new temporal augment functions to prevent the shortcut learning problem. We use the Libri-light 60k unsupervised data and the LibriSpeech 100hrs/960hrs supervised data to compare c-siam and other best-performing systems. Our experiments show that c-siam provides 20% relative word error rate improvement over wav2vec baselines. A c-siam network with 450M parameters achieves competitive results compared to the state-of-the-art networks with 600M parameters.

cs.LG↗

arXiv2022

Weakly-supervised 3D Human Pose Estimation with Cross-view U-shaped Graph Convolutional Network

Although monocular 3D human pose estimation methods have made significant progress, it is far from being solved due to the inherent depth ambiguity. Instead, exploiting multi-view information is a practical way to achieve absolute 3D human pose estimation. In this paper, we propose a simple yet effective pipeline for weakly-supervised cross-view 3D human pose estimation. By only using two camera views, our method can achieve state-of-the-art performance in a weakly-supervised manner, requiring no 3D ground truth but only 2D annotations. Specifically, our method contains two steps: triangulation and refinement. First, given the 2D keypoints that can be obtained through any classic 2D detection methods, triangulation is performed across two views to lift the 2D keypoints into coarse 3D poses. Then, a novel cross-view U-shaped graph convolutional network (CV-UGCN), which can explore the spatial configurations and cross-view correlations, is designed to refine the coarse 3D poses. In particular, the refinement progress is achieved through weakly-supervised learning, in which geometric and structure-aware consistency checks are performed. We evaluate our method on the standard benchmark dataset, Human3.6M. The Mean Per Joint Position Error on the benchmark dataset is 27.4 mm, which outperforms existing state-of-the-art methods remarkably (27.4 mm vs 30.2 mm).

cs.CV↗

arXiv2022

Cross-Image Relational Knowledge Distillation for Semantic Segmentation

Current Knowledge Distillation (KD) methods for semantic segmentation often guide the student to mimic the teacher's structured information generated from individual data samples. However, they ignore the global semantic relations among pixels across various images that are valuable for KD. This paper proposes a novel Cross-Image Relational KD (CIRKD), which focuses on transferring structured pixel-to-pixel and pixel-to-region relations among the whole images. The motivation is that a good teacher network could construct a well-structured feature space in terms of global pixel dependencies. CIRKD makes the student mimic better structured semantic relations from the teacher, thus improving the segmentation performance. Experimental results over Cityscapes, CamVid and Pascal VOC datasets demonstrate the effectiveness of our proposed approach against state-of-the-art distillation methods. The code is available at https://github.com/winycg/CIRKD.

cs.CV↗

arXiv2022

Learning Dynamic View Synthesis With Few RGBD Cameras

There have been significant advancements in dynamic novel view synthesis in recent years. However, current deep learning models often require (1) prior models (e.g., SMPL human models), (2) heavy pre-processing, or (3) per-scene optimization. We propose to utilize RGBD cameras to remove these limitations and synthesize free-viewpoint videos of dynamic indoor scenes. We generate feature point clouds from RGBD frames and then render them into free-viewpoint videos via a neural renderer. However, the inaccurate, unstable, and incomplete depth measurements induce severe distortions, flickering, and ghosting artifacts. We enforce spatial-temporal consistency via the proposed Cycle Reconstruction Consistency and Temporal Stabilization module to reduce these artifacts. We introduce a simple Regional Depth-Inpainting module that adaptively inpaints missing depth values to render complete novel views. Additionally, we present a Human-Things Interactions dataset to validate our approach and facilitate future research. The dataset consists of 43 multi-view RGBD video sequences of everyday activities, capturing complex interactions between human subjects and their surroundings. Experiments on the HTI dataset show that our method outperforms the baseline per-frame image fidelity and spatial-temporal consistency. We will release our code, and the dataset on the website soon.

cs.CV↗