arXiv subjects

Di Huang

Publications and source records attributed to Di Huang.

At least 181 records · Page 10Linked to original sources

arXiv2023

Unilaterally Aggregated Contrastive Learning with Hierarchical Augmentation for Anomaly Detection

Anomaly detection (AD), aiming to find samples that deviate from the training distribution, is essential in safety-critical applications. Though recent self-supervised learning based attempts achieve promising results by creating virtual outliers, their training objectives are less faithful to AD which requires a concentrated inlier distribution as well as a dispersive outlier distribution. In this paper, we propose Unilaterally Aggregated Contrastive Learning with Hierarchical Augmentation (UniCon-HA), taking into account both the requirements above. Specifically, we explicitly encourage the concentration of inliers and the dispersion of virtual outliers via supervised and unsupervised contrastive losses, respectively. Considering that standard contrastive data augmentation for generating positive views may induce outliers, we additionally introduce a soft mechanism to re-weight each augmented inlier according to its deviation from the inlier distribution, to ensure a purified concentration. Moreover, to prompt a higher concentration, inspired by curriculum learning, we adopt an easy-to-hard hierarchical augmentation strategy and perform contrastive aggregation at different depths of the network based on the strengths of data augmentation. Our method is evaluated under three AD settings including unlabeled one-class, unlabeled multi-class, and labeled multi-class, demonstrating its consistent superiority over other competitors.

cs.CV↗

arXiv2023

Denoising Diffusion Autoencoders are Unified Self-supervised Learners

Inspired by recent advances in diffusion models, which are reminiscent of denoising autoencoders, we investigate whether they can acquire discriminative representations for classification via generative pre-training. This paper shows that the networks in diffusion models, namely denoising diffusion autoencoders (DDAE), are unified self-supervised learners: by pre-training on unconditional image generation, DDAE has already learned strongly linear-separable representations within its intermediate layers without auxiliary encoders, thus making diffusion pre-training emerge as a general approach for generative-and-discriminative dual learning. To validate this, we conduct linear probe and fine-tuning evaluations. Our diffusion-based approach achieves 95.9% and 50.0% linear evaluation accuracies on CIFAR-10 and Tiny-ImageNet, respectively, and is comparable to contrastive learning and masked autoencoders for the first time. Transfer learning from ImageNet also confirms the suitability of DDAE for Vision Transformers, suggesting the potential to scale DDAEs as unified foundation models. Code is available at github.com/FutureXiang/ddae.

cs.CV↗

arXiv2023

Search for light dark matter from atmosphere in PandaX-4T

We report a search for light dark matter produced through the cascading decay of $η$ mesons, which are created as a result of inelastic collisions between cosmic rays and Earth's atmosphere. We introduce a new and general framework, publicly accessible, designed to address boosted dark matter specifically, with which a full and dedicated simulation including both elastic and quasi-elastic processes of Earth attenuation effect on the dark matter particles arriving at the detector is performed. In the PandaX-4T commissioning data of 0.63 tonne$\cdot$year exposure, no significant excess over background is observed. The first constraints on the interaction between light dark matter generated in the atmosphere and nucleus through a light scalar mediator are obtained. The lowest excluded cross-section is set at $5.9 \times 10^{-37}{\rm cm^2}$ for dark matter mass of $0.1$ MeV$/c^2$ and mediator mass of 300 MeV$/c^2$. The lowest upper limit of $η$ to dark matter decay branching ratio is $1.6 \times 10^{-7}$.

hep-ex↗

arXiv2023

A Search for Light Fermionic Dark Matter Absorption on Electrons in PandaX-4T

We report a search on a sub-MeV fermionic dark matter absorbed by electrons with an outgoing active neutrino using the 0.63 tonne-year exposure collected by PandaX-4T liquid xenon experiment. No significant signals are observed over the expected background. The data are interpreted into limits to the effective couplings between such dark matter and electrons. For axial-vector or vector interactions, our sensitivity is competitive in comparison to existing astrophysical bounds on the decay of such dark matter into photon final states. In particular, we present the first direct detection limits for an axial-vector (vector) interaction which are the strongest in the mass range from 25 to 45 (35 to 50) keV/c$^2$.

hep-ex↗

arXiv2023

FR-Net:A Light-weight FFT Residual Net For Gaze Estimation

Gaze estimation is a crucial task in computer vision, however, existing methods suffer from high computational costs, which limit their practical deployment in resource-limited environments. In this paper, we propose a novel lightweight model, FR-Net, for accurate gaze angle estimation while significantly reducing computational complexity. FR-Net utilizes the Fast Fourier Transform (FFT) to extract gaze-relevant features in frequency domains while reducing the number of parameters. Additionally, we introduce a shortcut component that focuses on the spatial domain to further improve the accuracy of our model. Our experimental results demonstrate that our approach achieves substantially lower gaze error angles (3.86 on MPII and 4.51 on EYEDIAP) compared to state-of-the-art gaze estimation methods, while utilizing 17 times fewer parameters (0.67M) and only 12\% of FLOPs (0.22B). Furthermore, our method outperforms existing lightweight methods in terms of accuracy and efficiency for the gaze estimation task. These results suggest that our proposed approach has significant potential applications in areas such as human-computer interaction and driver assistance systems.

cs.CV↗

arXiv2023

NeuFace: Realistic 3D Neural Face Rendering from Multi-view Images

Realistic face rendering from multi-view images is beneficial to various computer vision and graphics applications. Due to the complex spatially-varying reflectance properties and geometry characteristics of faces, however, it remains challenging to recover 3D facial representations both faithfully and efficiently in the current studies. This paper presents a novel 3D face rendering model, namely NeuFace, to learn accurate and physically-meaningful underlying 3D representations by neural rendering techniques. It naturally incorporates the neural BRDFs into physically based rendering, capturing sophisticated facial geometry and appearance clues in a collaborative manner. Specifically, we introduce an approximated BRDF integration and a simple yet new low-rank prior, which effectively lower the ambiguities and boost the performance of the facial BRDFs. Extensive experiments demonstrate the superiority of NeuFace in human face rendering, along with a decent generalization ability to common objects.

cs.CV↗

arXiv2023

Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Images

Object detection on drone images with low-latency is an important but challenging task on the resource-constrained unmanned aerial vehicle (UAV) platform. This paper investigates optimizing the detection head based on the sparse convolution, which proves effective in balancing the accuracy and efficiency. Nevertheless, it suffers from inadequate integration of contextual information of tiny objects as well as clumsy control of the mask ratio in the presence of foreground with varying scales. To address the issues above, we propose a novel global context-enhanced adaptive sparse convolutional network (CEASC). It first develops a context-enhanced group normalization (CE-GN) layer, by replacing the statistics based on sparsely sampled features with the global contextual ones, and then designs an adaptive multi-layer masking strategy to generate optimal mask ratios at distinct scales for compact foreground coverage, promoting both the accuracy and efficiency. Extensive experimental results on two major benchmarks, i.e. VisDrone and UAVDT, demonstrate that CEASC remarkably reduces the GFLOPs and accelerates the inference procedure when plugging into the typical state-of-the-art detection frameworks (e.g. RetinaNet and GFL V1) with competitive performance. Code is available at https://github.com/Cuogeihong/CEASC.

cs.CV↗

arXiv2023

OcTr: Octree-based Transformer for 3D Object Detection

A key challenge for LiDAR-based 3D object detection is to capture sufficient features from large scale 3D scenes especially for distant or/and occluded objects. Albeit recent efforts made by Transformers with the long sequence modeling capability, they fail to properly balance the accuracy and efficiency, suffering from inadequate receptive fields or coarse-grained holistic correlations. In this paper, we propose an Octree-based Transformer, named OcTr, to address this issue. It first constructs a dynamic octree on the hierarchical feature pyramid through conducting self-attention on the top level and then recursively propagates to the level below restricted by the octants, which captures rich global context in a coarse-to-fine manner while maintaining the computational complexity under control. Furthermore, for enhanced foreground perception, we propose a hybrid positional embedding, composed of the semantic-aware positional embedding and attention mask, to fully exploit semantic and geometry clues. Extensive experiments are conducted on the Waymo Open Dataset and KITTI Dataset, and OcTr reaches newly state-of-the-art results.

cs.CV↗

arXiv2023

Quantum Dynamics of Attractive and Repulsive Polarons in a Doped MoSe$_2$ Monolayer

When mobile impurities are introduced and coupled to a Fermi sea, new quasiparticles known as Fermi polarons are formed. There are two interesting, yet drastically different regimes of the Fermi polaron problem: (I) the attractive polaron (AP) branch, connected to pairing phenomena spanning the crossover from BCS superfluidity to the Bose-Einstein condensation of molecules; and (II) the repulsive branch (RP), which underlies the physics responsible for Stoner's itinerant ferromagnetism. Here, we study Fermi polarons in two dimensional systems, where many questions and debates regarding their nature persist. The model system we investigate is a doped MoSe$_2$ monolayer. We find the observed AP-RP energy splitting and the quantum dynamics of attractive polarons agree with the predictions of polaron theory. As the doping density increases, the quantum dephasing of the attractive polarons remains constant, indicative of stable quasiparticles, while the repulsive polaron dephasing rate increases nearly quadratically. The dynamics of Fermi polarons are of critical importance for understanding the pairing and magnetic instabilities that lead to the formation of rich quantum phases found in a wide range of physical systems including nuclei, cold atomic gases, and solids.

cond-mat.mes-hall↗

arXiv2023

RGB-D Grasp Detection via Depth Guided Learning with Cross-modal Attention

Planar grasp detection is one of the most fundamental tasks to robotic manipulation, and the recent progress of consumer-grade RGB-D sensors enables delivering more comprehensive features from both the texture and shape modalities. However, depth maps are generally of a relatively lower quality with much stronger noise compared to RGB images, making it challenging to acquire grasp depth and fuse multi-modal clues. To address the two issues, this paper proposes a novel learning based approach to RGB-D grasp detection, namely Depth Guided Cross-modal Attention Network (DGCAN). To better leverage the geometry information recorded in the depth channel, a complete 6-dimensional rectangle representation is adopted with the grasp depth dedicatedly considered in addition to those defined in the common 5-dimensional one. The prediction of the extra grasp depth substantially strengthens feature learning, thereby leading to more accurate results. Moreover, to reduce the negative impact caused by the discrepancy of data quality in two modalities, a Local Cross-modal Attention (LCA) module is designed, where the depth features are refined according to cross-modal relations and concatenated to the RGB ones for more sufficient fusion. Extensive simulation and physical evaluations are conducted and the experimental results highlight the superiority of the proposed approach.

cs.RO↗

arXiv2023

Online Symbolic Regression with Informative Query

Symbolic regression, the task of extracting mathematical expressions from the observed data $\{ \vx_i, y_i \}$, plays a crucial role in scientific discovery. Despite the promising performance of existing methods, most of them conduct symbolic regression in an \textit{offline} setting. That is, they treat the observed data points as given ones that are simply sampled from uniform distributions without exploring the expressive potential of data. However, for real-world scientific problems, the data used for symbolic regression are usually actively obtained by doing experiments, which is an \textit{online} setting. Thus, how to obtain informative data that can facilitate the symbolic regression process is an important problem that remains challenging. In this paper, we propose QUOSR, a \textbf{qu}ery-based framework for \textbf{o}nline \textbf{s}ymbolic \textbf{r}egression that can automatically obtain informative data in an iterative manner. Specifically, at each step, QUOSR receives historical data points, generates new $\vx$, and then queries the symbolic expression to get the corresponding $y$, where the $(\vx, y)$ serves as new data points. This process repeats until the maximum number of query steps is reached. To make the generated data points informative, we implement the framework with a neural network and train it by maximizing the mutual information between generated data points and the target expression. Through comprehensive experiments, we show that QUOSR can facilitate modern symbolic regression methods by generating informative data.

cs.LG↗

arXiv2023

OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models

We propose a new method for object pose estimation without CAD models. The previous feature-matching-based method OnePose has shown promising results under a one-shot setting which eliminates the need for CAD models or object-specific training. However, OnePose relies on detecting repeatable image keypoints and is thus prone to failure on low-textured objects. We propose a keypoint-free pose estimation pipeline to remove the need for repeatable keypoint detection. Built upon the detector-free feature matching method LoFTR, we devise a new keypoint-free SfM method to reconstruct a semi-dense point-cloud model for the object. Given a query image for object pose estimation, a 2D-3D matching network directly establishes 2D-3D correspondences between the query image and the reconstructed point-cloud model without first detecting keypoints in the image. Experiments show that the proposed pipeline outperforms existing one-shot CAD-model-free methods by a large margin and is comparable to CAD-model-based methods on LINEMOD even for low-textured objects. We also collect a new dataset composed of 80 sequences of 40 low-textured objects to facilitate future research on one-shot object pose estimation. The supplementary material, code and dataset are available on the project page: https://zju3dv.github.io/onepose_plus_plus/.

cs.CV↗

arXiv2023

A First Search for Solar $^8$B Neutrino in the PandaX-4T Experiment using Neutrino-Nucleus Coherent Scattering

A search for interactions from solar $^8$B neutrinos elastically scattering off xenon nuclei using PandaX-4T commissioning data is reported. The energy threshold of this search is further lowered compared with the previous search for dark matter, with various techniques utilized to suppress the background that emerges from data with the lowered threshold. A blind analysis is performed on the data with an effective exposure of 0.48 tonne$\cdot$year, and no significant excess of events is observed. Among results obtained using the neutrino-nucleus coherent scattering, our results give the best constraint on the solar $^8$B neutrino flux. We further provide a more stringent limit on the cross section between dark matter and nucleon in the mass range from 3 to 9 GeV/c$^2$.

hep-ex↗

arXiv2022

Measurement of Double Beta Decay Half-life of $^{136}$Xe with the PandaX-4T Detector

Precise measurement of two-neutrino double beta decay (DBD) half-life is an important step for the searches of Majorana neutrinos with neutrinoless double beta decay. We report the measurement of DBD half-life of $^{136}$Xe using the PandaX-4T dual-phase Time Projection Chamber (TPC) with 3.7-tonne natural xenon and the first 94.9-day physics data release. The background model in the fiducial volume is well constrained in situ by events in the outer active region. With a $^{136}$Xe exposure of 15.5 kg-year, we establish the half-life as $2.27 \pm 0.03 (stat.)\pm 0.10 (syst.)\times 10^{21}$ years. This is the first DBD half-life measurement with natural xenon and demonstrates the physics capability of a large-scale liquid xenon TPC in the field of rare event searches.

nucl-ex↗

arXiv2022

Towards Scale Balanced 6-DoF Grasp Detection in Cluttered Scenes

In this paper, we focus on the problem of feature learning in the presence of scale imbalance for 6-DoF grasp detection and propose a novel approach to especially address the difficulty in dealing with small-scale samples. A Multi-scale Cylinder Grouping (MsCG) module is presented to enhance local geometry representation by combining multi-scale cylinder features and global context. Moreover, a Scale Balanced Learning (SBL) loss and an Object Balanced Sampling (OBS) strategy are designed, where SBL enlarges the gradients of the samples whose scales are in low frequency by apriori weights while OBS captures more points on small-scale objects with the help of an auxiliary segmentation network. They alleviate the influence of the uneven distribution of grasp scales in training and inference respectively. In addition, Noisy-clean Mix (NcM) data augmentation is introduced to facilitate training, aiming to bridge the domain gap between synthetic and raw scenes in an efficient way by generating more data which mix them into single ones at instance-level. Extensive experiments are conducted on the GraspNet-1Billion benchmark and competitive results are reached with significant gains on small-scale cases. Besides, the performance of real-world grasping highlights its generalization ability. Our code is available at https://github.com/mahaoxiang822/Scale-Balanced-Grasp.

cs.RO↗

arXiv2022

Learning Polysemantic Spoof Trace: A Multi-Modal Disentanglement Network for Face Anti-spoofing

Along with the widespread use of face recognition systems, their vulnerability has become highlighted. While existing face anti-spoofing methods can be generalized between attack types, generic solutions are still challenging due to the diversity of spoof characteristics. Recently, the spoof trace disentanglement framework has shown great potential for coping with both seen and unseen spoof scenarios, but the performance is largely restricted by the single-modal input. This paper focuses on this issue and presents a multi-modal disentanglement model which targetedly learns polysemantic spoof traces for more accurate and robust generic attack detection. In particular, based on the adversarial learning mechanism, a two-stream disentangling network is designed to estimate spoof patterns from the RGB and depth inputs, respectively. In this case, it captures complementary spoofing clues inhering in different attacks. Furthermore, a fusion module is exploited, which recalibrates both representations at multiple stages to promote the disentanglement in each individual modality. It then performs cross-modality aggregation to deliver a more comprehensive spoof trace representation for prediction. Extensive evaluations are conducted on multiple benchmarks, demonstrating that learning polysemantic spoof traces favorably contributes to anti-spoofing with more perceptible and interpretable results.

cs.CV↗

arXiv2022

Reconstructing Hand-Held Objects from Monocular Video

This paper presents an approach that reconstructs a hand-held object from a monocular video. In contrast to many recent methods that directly predict object geometry by a trained network, the proposed approach does not require any learned prior about the object and is able to recover more accurate and detailed object geometry. The key idea is that the hand motion naturally provides multiple views of the object and the motion can be reliably estimated by a hand pose tracker. Then, the object geometry can be recovered by solving a multi-view reconstruction problem. We devise an implicit neural representation-based method to solve the reconstruction problem and address the issues of imprecise hand pose estimation, relative hand-object motion, and insufficient geometry optimization for small objects. We also provide a newly collected dataset with 3D ground truth to validate the proposed approach.

cs.CV↗

arXiv2022

First search for the absorption of fermionic dark matter with the PandaX-4T experiment

Compared with the signature of dark matter elastic scattering off nuclei, the absorption of fermionic dark matter by nuclei opens up a new searching channel for light dark matter with a characteristic monoenergetic signal. In this Letter, we explore the $95.0$-day data from the PandaX-4T commissioning run and report the first dedicated searching results of the fermionic dark matter absorption signal through a neutral current process. No significant signal was found, and the lowest limit on the dark matter-nucleon interaction cross section is set to be $1.5\times10^{-50}$ cm$^2$ for a fermionic dark matter mass of $40$ MeV/$c^2$ with 90\% confidence level.

hep-ex↗