Searcharxiv⌕ Search

arXiv subjects

Hao Zhang

Publications and source records attributed to Hao Zhang.

At least 847 records · Page 47Linked to original sources
arXiv2023

TSNet-SAC: Leveraging Transformers for Efficient Task Scheduling

In future 6G Mobile Edge Computing (MEC), autopilot systems require the capability of processing multimodal data with strong interdependencies. However, traditional heuristic algorithms are inadequate for real-time scheduling due to their requirement for multiple iterations to derive the optimal scheme. We propose a novel TSNet-SAC based on Transformer, that utilizes heuristic algorithms solely to guide the training of TSNet. Additionally, a Sliding Augment Component (SAC) is introduced to enhance the robustness and resolve algorithm defects. Furthermore, the Extender component is designed to handle multi-scale training data and provide network scalability, enabling TSNet to adapt to different access scenarios. Simulation demonstrates that TSNet-SAC outperforms existing networks in accuracy and robustness, achieving superior scheduling-making latency compared to heuristic algorithms.

cs.NI↗
arXiv2023

CLIPXPlore: Coupled CLIP and Shape Spaces for 3D Shape Exploration

This paper presents CLIPXPlore, a new framework that leverages a vision-language model to guide the exploration of the 3D shape space. Many recent methods have been developed to encode 3D shapes into a learned latent shape space to enable generative design and modeling. Yet, existing methods lack effective exploration mechanisms, despite the rich information. To this end, we propose to leverage CLIP, a powerful pre-trained vision-language model, to aid the shape-space exploration. Our idea is threefold. First, we couple the CLIP and shape spaces by generating paired CLIP and shape codes through sketch images and training a mapper network to connect the two spaces. Second, to explore the space around a given shape, we formulate a co-optimization strategy to search for the CLIP code that better matches the geometry of the shape. Third, we design three exploration modes, binary-attribute-guided, text-guided, and sketch-guided, to locate suitable exploration trajectories in shape space and induce meaningful changes to the shape. We perform a series of experiments to quantitatively and visually compare CLIPXPlore with different baselines in each of the three exploration modes, showing that CLIPXPlore can produce many meaningful exploration results that cannot be achieved by the existing solutions.

cs.CV↗
arXiv2023

A Novel Channel-Constrained Model for 6G Vehicular Networks with Traffic Spikes

Mobile Edge Computing (MEC) holds excellent potential in Congestion Management (CM) of 6G vehicular networks. A reasonable schedule of MEC ensures a more reliable and efficient CM system. Unfortunately, existing parallel and sequential models cannot cope with scarce computing resources and constrained channels, especially during traffic rush hour. In this paper, we propose a channel-constrained multi-core sequential model (CCMSM) for task offloading and resource allocation. The CCMSM incorporates a utility index that couples system energy consumption and delay, applying Genetic Algorithm combining Sparrow Search Algorithm (GA-SSA) in the branching optimization. Furthermore, we prove that the system delay is the shortest with the FCFS computing strategy in the MEC server. Simulation demonstrates that the proposed CCMSM achieves a higher optimization level and exhibits better robustness and resilient scalability for traffic spikes.

cs.NI↗
arXiv2023

FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction

The recent advent of self-supervised pre-training techniques has led to a surge in the use of multimodal learning in form document understanding. However, existing approaches that extend the mask language modeling to other modalities require careful multi-task tuning, complex reconstruction target designs, or additional pre-training data. In FormNetV2, we introduce a centralized multimodal graph contrastive learning strategy to unify self-supervised pre-training for all modalities in one loss. The graph contrastive objective maximizes the agreement of multimodal representations, providing a natural interplay for all modalities without special customization. In addition, we extract image features within the bounding box that joins a pair of tokens connected by a graph edge, capturing more targeted visual cues without loading a sophisticated and separately pre-trained image embedder. FormNetV2 establishes new state-of-the-art performance on FUNSD, CORD, SROIE and Payment benchmarks with a more compact model size.

cs.CL↗
arXiv2023

detrex: Benchmarking Detection Transformers

The DEtection TRansformer (DETR) algorithm has received considerable attention in the research community and is gradually emerging as a mainstream approach for object detection and other perception tasks. However, the current field lacks a unified and comprehensive benchmark specifically tailored for DETR-based models. To address this issue, we develop a unified, highly modular, and lightweight codebase called detrex, which supports a majority of the mainstream DETR-based instance recognition algorithms, covering various fundamental tasks, including object detection, segmentation, and pose estimation. We conduct extensive experiments under detrex and perform a comprehensive benchmark for DETR-based models. Moreover, we enhance the performance of detection transformers through the refinement of training hyper-parameters, providing strong baselines for supported algorithms.We hope that detrex could offer research communities a standardized and unified platform to evaluate and compare different DETR-based models while fostering a deeper understanding and driving advancements in DETR-based instance recognition. Our code is available at https://github.com/IDEA-Research/detrex. The project is currently being actively developed. We encourage the community to use detrex codebase for further development and contributions.

cs.CV↗
arXiv2023

Introducing Depth into Transformer-based 3D Object Detection

In this paper, we present DAT, a Depth-Aware Transformer framework designed for camera-based 3D detection. Our model is based on observing two major issues in existing methods: large depth translation errors and duplicate predictions along depth axes. To mitigate these issues, we propose two key solutions within DAT. To address the first issue, we introduce a Depth-Aware Spatial Cross-Attention (DA-SCA) module that incorporates depth information into spatial cross-attention when lifting image features to 3D space. To address the second issue, we introduce an auxiliary learning task called Depth-aware Negative Suppression loss. First, based on their reference points, we organize features as a Bird's-Eye-View (BEV) feature map. Then, we sample positive and negative features along each object ray that connects an object and a camera and train the model to distinguish between them. The proposed DA-SCA and DNS methods effectively alleviate these two problems. We show that DAT is a versatile method that enhances the performance of all three popular models, BEVFormer, DETR3D, and PETR. Our evaluation on BEVFormer demonstrates that DAT achieves a significant improvement of +2.8 NDS on nuScenes val under the same settings. Moreover, when using pre-trained VoVNet-99 as the backbone, DAT achieves strong results of 60.0 NDS and 51.5 mAP on nuScenes test. Our code will be soon.

cs.CV↗
arXiv2023

Weight Bank Addition Photonic Accelerator for Artificial Intelligence

Neural networks powered by artificial intelligence play a pivotal role in current estimation and classification applications due to the escalating computational demands of evolving deep learning systems. The hindrances posed by existing computational limitations threaten to impede the further progression of these neural networks. In response to these issues, we propose neuromorphic networks founded on photonics that offer superior processing speed than electronic counterparts, thereby enhancing support for real time, three dimensional, and virtual reality applications. The weight bank, an integral component of these networks has a direct bearing on their overall performance. Our study demonstrates the implementation of a weight bank utilizing parallelly cascaded micro ring resonators. We present our observations on neuromorphic networks based on silicon on insulators, where cascaded MRRs play a crucial role in mitigating interchannel and intrachannel cross talk, a persistent issue in wavelength division multiplexing systems. Additionally, we design a standard silicon photonic accelerator to perform weight addition. Optimized to offer increased speed and reduced energy consumption, this photonic accelerator ensures comparable processing power to electronic devices.

physics.optics↗
arXiv2023

D$^2$CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropouts

We present D$^2$CSG, a neural model composed of two dual and complementary network branches, with dropouts, for unsupervised learning of compact constructive solid geometry (CSG) representations of 3D CAD shapes. Our network is trained to reconstruct a 3D shape by a fixed-order assembly of quadric primitives, with both branches producing a union of primitive intersections or inverses. A key difference between D$^2$CSG and all prior neural CSG models is its dedicated residual branch to assemble the potentially complex shape complement, which is subtracted from an overall shape modeled by the cover branch. With the shape complements, our network is provably general, while the weight dropout further improves compactness of the CSG tree by removing redundant primitives. We demonstrate both quantitatively and qualitatively that D$^2$CSG produces compact CSG reconstructions with superior quality and more natural primitives than all existing alternatives, especially over complex and high-genus CAD shapes.

cs.CV↗
arXiv2023

Approach to Hyperuniformity in a Metallic Glass-Forming Material Exhibiting a Fragile to Strong Glass Transition

We investigate a metallic glass-forming (GF) material (Al90Sm10) exhibiting a fragile-strong (FS) glass-formation by molecular dynamics simulation to better understand this highly distinctive pattern of glass-formation in which many of the usual phenomenological relations describing relaxation times and diffusion of OGF liquids no longer apply, and where instead genuine thermodynamic features are observed in response functions and little thermodynamic signature is exhibited at the glass transition temperature, Tg. Given the many unexpected similarities between the thermodynamics and dynamics of this metallic GF material with water, we first focus on the anomalous static scattering in this liquid, following recent studies on water, silicon and other FS GF liquids. In particular, we quantify the 'hyperuniformity index' H of our liquid which provides a quantitative measure of molecular 'jamming'. To gain insight into the T-dependence and magnitude of H, we also estimated another more familiar measure of particle localization, the Debye-Waller parameter $ $ describing the mean-square particle displacement on a timescale on the order of the fast relaxation time, and we also calculate H and $ $ for heated crystalline Cu. This comparative analysis between H and $ $ for crystalline and metallic glass materials allows us to understand the critical value of H on the order of $10^{-3}$ as being analogous to the Lindemann criterion for both the melting of crystals and the 'softening' of glasses. We further interpret the emergence of FS GF and liquid-liquid phase separation in this class of liquids to arise from a cooperative assembly process in the GF liquid.

cond-mat.soft↗
arXiv2023

MS-DETR: Natural Language Video Localization with Sampling Moment-Moment Interaction

Given a query, the task of Natural Language Video Localization (NLVL) is to localize a temporal moment in an untrimmed video that semantically matches the query. In this paper, we adopt a proposal-based solution that generates proposals (i.e., candidate moments) and then select the best matching proposal. On top of modeling the cross-modal interaction between candidate moments and the query, our proposed Moment Sampling DETR (MS-DETR) enables efficient moment-moment relation modeling. The core idea is to sample a subset of moments guided by the learnable templates with an adopted DETR (DEtection TRansformer) framework. To achieve this, we design a multi-scale visual-linguistic encoder, and an anchor-guided moment decoder paired with a set of learnable templates. Experimental results on three public datasets demonstrate the superior performance of MS-DETR.

cs.CV↗
arXiv2023

Probing Ring Resonator Sensor Based on Vernier Effect

The Vernier effect has seen extensive application in optical structures, serving to augment the free spectral range (FSR). A substantial FSR is vital in a myriad of applications including multiplexers, enabling a broad, clear band comparable to the C-band to accommodate a maximum number of channels. Nevertheless, a large FSR often conflicts with bending loss, as it necessitates a smaller resonator radius, thus increase the insertion loss in the bending portion. To facilitate FSR expansion without amplifying bending loss, we employed cascaded and parallel racetrack resonators and ring resonators of varying radius that demonstrate the Vernier effect. In this study, we designed, fabricated, and tested multiple types of racetrack resonators to validate the Vernier effect and its FSR extension capabilities. Our investigations substantiate that the Vernier effect, based on cascaded and series-coupled micro-ring resonator (MRR) sensors, can efficiently mitigate intra-channel cross-talk at higher data rates. This is achieved by providing larger input-to-through suppression, thus paving the way for future applications.

physics.optics↗
arXiv2023

Semantic Segmentation with Bidirectional Language Models Improves Long-form ASR

We propose a method of segmenting long-form speech by separating semantically complete sentences within the utterance. This prevents the ASR decoder from needlessly processing faraway context while also preventing it from missing relevant context within the current sentence. Semantically complete sentence boundaries are typically demarcated by punctuation in written text; but unfortunately, spoken real-world utterances rarely contain punctuation. We address this limitation by distilling punctuation knowledge from a bidirectional teacher language model (LM) trained on written, punctuated text. We compare our segmenter, which is distilled from the LM teacher, against a segmenter distilled from a acoustic-pause-based teacher used in other works, on a streaming ASR pipeline. The pipeline with our segmenter achieves a 3.2% relative WER gain along with a 60 ms median end-of-segment latency reduction on a YouTube captioning task.

cs.CL↗
arXiv2023

Mobile Safety Application for Pedestrians

Vulnerable Road User (VRU) safety has been an important issue throughout the years as corresponding fatality numbers in traffic have been increasing each year. With the developments in connected vehicle technology, there are new and easier ways of implementing Vehicle to Everything (V2X) communication which can be utilized to provide safety and early warning benefits for VRUs. Mobile phones are one important point of interest with their sensors being increased in quantity and quality and improved in terms of accuracy. Bluetooth and extended Bluetooth technology in mobile phones has enhanced support to carry larger chunks of information to longer distances. The work we discuss in this paper is related to a mobile application that utilizes the mobile phone sensors and Bluetooth communication to implement Personal Safety Message (PSM) broadcast using the SAE J2735 standard to create a Pedestrian to Vehicle (P2V) based safety warning structure. This implementation allows the drivers to receive a warning on their mobile phones and be more careful about the pedestrian intending to cross the street. As a result, the driver has much more time to safely slow down and stop at the intersection. Most importantly, thanks to the wireless nature of Bluetooth connection and long-range mode in Bluetooth 5.0, most dangerous cases such as reduced visibility or No-Line-of-Sight (NLOS) conditions can be remedied.

eess.SY↗
arXiv2023

NoisywikiHow: A Benchmark for Learning with Real-world Noisy Labels in Natural Language Processing

Large-scale datasets in the real world inevitably involve label noise. Deep models can gradually overfit noisy labels and thus degrade model generalization. To mitigate the effects of label noise, learning with noisy labels (LNL) methods are designed to achieve better generalization performance. Due to the lack of suitable datasets, previous studies have frequently employed synthetic label noise to mimic real-world label noise. However, synthetic noise is not instance-dependent, making this approximation not always effective in practice. Recent research has proposed benchmarks for learning with real-world noisy labels. However, the noise sources within may be single or fuzzy, making benchmarks different from data with heterogeneous label noises in the real world. To tackle these issues, we contribute NoisywikiHow, the largest NLP benchmark built with minimal supervision. Specifically, inspired by human cognition, we explicitly construct multiple sources of label noise to imitate human errors throughout the annotation, replicating real-world noise, whose corruption is affected by both ground-truth labels and instances. Moreover, we provide a variety of noise levels to support controlled experiments on noisy data, enabling us to evaluate LNL methods systematically and comprehensively. After that, we conduct extensive multi-dimensional experiments on a broad range of LNL methods, obtaining new and intriguing findings.

cs.CL↗
arXiv2023

UKP-SQuARE v3: A Platform for Multi-Agent QA Research

The continuous development of Question Answering (QA) datasets has drawn the research community's attention toward multi-domain models. A popular approach is to use multi-dataset models, which are models trained on multiple datasets to learn their regularities and prevent overfitting to a single dataset. However, with the proliferation of QA models in online repositories such as GitHub or Hugging Face, an alternative is becoming viable. Recent works have demonstrated that combining expert agents can yield large performance gains over multi-dataset models. To ease research in multi-agent models, we extend UKP-SQuARE, an online platform for QA research, to support three families of multi-agent systems: i) agent selection, ii) early-fusion of agents, and iii) late-fusion of agents. We conduct experiments to evaluate their inference speed and discuss the performance vs. speed trade-off compared to multi-dataset models. UKP-SQuARE is open-source and publicly available at http://square.ukp-lab.de.

cs.CL↗
arXiv2023

Deep Learning for Joint Acoustic Echo and Acoustic Howling Suppression in Hybrid Meetings

Hybrid meetings have become increasingly necessary during the post-COVID period and also brought new challenges for solving audio-related problems. In particular, the interplay between acoustic echo and acoustic howling in a hybrid meeting makes the joint suppression of them difficult. This paper proposes a deep learning approach to tackle this problem by formulating a recurrent feedback suppression process as an instantaneous speech separation task using the teacher-forced training strategy. Specifically, a self-attentive recurrent neural network is utilized to extract the target speech from microphone recordings with accessible and learned reference signals, thus suppressing acoustic echo and acoustic howling simultaneously. Different combinations of input signals and loss functions have been investigated for performance improvement. Experimental results demonstrate the effectiveness of the proposed method for suppressing echo and howling jointly in hybrid meetings.

eess.AS↗
arXiv2023

Hybrid AHS: A Hybrid of Kalman Filter and Deep Learning for Acoustic Howling Suppression

Deep learning has been recently introduced for efficient acoustic howling suppression (AHS). However, the recurrent nature of howling creates a mismatch between offline training and streaming inference, limiting the quality of enhanced speech. To address this limitation, we propose a hybrid method that combines a Kalman filter with a self-attentive recurrent neural network (SARNN) to leverage their respective advantages for robust AHS. During offline training, a pre-processed signal obtained from the Kalman filter and an ideal microphone signal generated via teacher-forced training strategy are used to train the deep neural network (DNN). During streaming inference, the DNN's parameters are fixed while its output serves as a reference signal for updating the Kalman filter. Evaluation in both offline and streaming inference scenarios using simulated and real-recorded data shows that the proposed method efficiently suppresses howling and consistently outperforms baselines.

eess.AS↗
arXiv2023

A Strong and Reproducible Object Detector with Only Public Datasets

This work presents Focal-Stable-DINO, a strong and reproducible object detection model which achieves 64.6 AP on COCO val2017 and 64.8 AP on COCO test-dev using only 700M parameters without any test time augmentation. It explores the combination of the powerful FocalNet-Huge backbone with the effective Stable-DINO detector. Different from existing SOTA models that utilize an extensive number of parameters and complex training techniques on large-scale private data or merged data, our model is exclusively trained on the publicly available dataset Objects365, which ensures the reproducibility of our approach.

cs.CV↗