arXiv subjects

Dong Liu

Publications and source records attributed to Dong Liu.

At least 163 records · Page 9Linked to original sources

arXiv2025

The Gap Between Principle and Practice of Lossy Image Coding

Lossy image coding is the art of computing that is principally bounded by the image's rate-distortion function. This bound, though never accurately characterized, has been approached practically via deep learning technologies in recent years. Indeed, learned image coding schemes allow direct optimization of the joint rate-distortion cost, thereby outperforming the handcrafted image coding schemes by a large margin. Still, it is observed that there is room for further improvement in the rate-distortion performance of learned image coding. In this article, we identify the gap between the ideal rate-distortion function forecasted by Shannon's information theory and the empirical rate-distortion function achieved by the state-of-the-art learned image coding schemes, revealing that the gap is incurred by five different effects: modeling effect, approximation effect, amortization effect, digitization effect, and asymptotic effect. We design simulations and experiments to quantitively evaluate the last three effects, which demonstrates the high potential of future lossy image coding technologies.

cs.IT↗

arXiv2025

Bi-Directional Deep Contextual Video Compression

Deep video compression has made remarkable process in recent years, with the majority of advancements concentrated on P-frame coding. Although efforts to enhance B-frame coding are ongoing, their compression performance is still far behind that of traditional bi-directional video codecs. In this paper, we introduce a bi-directional deep contextual video compression scheme tailored for B-frames, termed DCVC-B, to improve the compression performance of deep B-frame coding. Our scheme mainly has three key innovations. First, we develop a bi-directional motion difference context propagation method for effective motion difference coding, which significantly reduces the bit cost of bi-directional motions. Second, we propose a bi-directional contextual compression model and a corresponding bi-directional temporal entropy model, to make better use of the multi-scale temporal contexts. Third, we propose a hierarchical quality structure-based training strategy, leading to an effective bit allocation across large groups of pictures (GOP). Experimental results show that our DCVC-B achieves an average reduction of 26.6% in BD-Rate compared to the reference software for H.265/HEVC under random access conditions. Remarkably, it surpasses the performance of the H.266/VVC reference software on certain test datasets under the same configuration. We anticipate our work can provide valuable insights and bring up deep B-frame coding to the next level.

cs.CV↗

arXiv2025

Few-Shot Domain Adaptation for Learned Image Compression

Learned image compression (LIC) has achieved state-of-the-art rate-distortion performance, deemed promising for next-generation image compression techniques. However, pre-trained LIC models usually suffer from significant performance degradation when applied to out-of-training-domain images, implying their poor generalization capabilities. To tackle this problem, we propose a few-shot domain adaptation method for LIC by integrating plug-and-play adapters into pre-trained models. Drawing inspiration from the analogy between latent channels and frequency components, we examine domain gaps in LIC and observe that out-of-training-domain images disrupt pre-trained channel-wise decomposition. Consequently, we introduce a method for channel-wise re-allocation using convolution-based adapters and low-rank adapters, which are lightweight and compatible to mainstream LIC schemes. Extensive experiments across multiple domains and multiple representative LIC schemes demonstrate that our method significantly enhances pre-trained models, achieving comparable performance to H.266/VVC intra coding with merely 25 target-domain samples. Additionally, our method matches the performance of full-model finetune while transmitting fewer than $2\%$ of the parameters.

eess.IV↗

arXiv2025

Primary Breadth-First Development (PBFD): An Approach to Full Stack Software Development

Full stack software applications are often simplified to basic CRUD operations, which can overlook the intricate principles of computer science necessary for addressing complex development challenges. Current methodologies frequently fall short in efficiency when managing these complexities. This paper presents an innovative approach that leverages foundational computer science principles, specifically using Directed Acyclic Graphs (DAGs), to model sophisticated business problems. We introduce Breadth-First Development (BFD), Depth-First Development (DFD), Cyclic Directed Development (CDD), Directed Acyclic Development (DAD), Primary BFD (PBFD), and Primary DFD (PDFD), to enhance application development. By employing bitmaps, this approach eliminates junction tables, resulting in more compact and efficient data processing within relational databases. Rigorous testing and over eight years of production deployment for tens of thousands of users have yielded remarkable results: zero bugs, development speed improvements of up to twenty times, performance gains of seven to eight times, and storage requirements reduced to one-eleventh compared to traditional methods.

cs.SE↗

arXiv2025

GraphSnapShot: Caching Local Structure for Fast Graph Learning

In our recent research, we have developed a framework called GraphSnapShot, which has been proven an useful tool for graph learning acceleration. GraphSnapShot is a framework for fast cache, storage, retrieval and computation for graph learning. It can quickly store and update the local topology of graph structure and allows us to track patterns in the structure of graph networks, just like take snapshots of the graphs. In experiments, GraphSnapShot shows efficiency, it can achieve up to 30% training acceleration and 73% memory reduction for lossless graph ML training compared to current baselines such as dgl.This technique is particular useful for large dynamic graph learning tasks such as social media analysis and recommendation systems to process complex relationships between entities. The code for GraphSnapShot is publicly available at https://github.com/NoakLiu/GraphSnapShot.

cs.LG↗

arXiv2025

Visual Large Language Models for Generalized and Specialized Applications

Visual-language models (VLM) have emerged as a powerful tool for learning a unified embedding space for vision and language. Inspired by large language models, which have demonstrated strong reasoning and multi-task capabilities, visual large language models (VLLMs) are gaining increasing attention for building general-purpose VLMs. Despite the significant progress made in VLLMs, the related literature remains limited, particularly from a comprehensive application perspective, encompassing generalized and specialized applications across vision (image, video, depth), action, and language modalities. In this survey, we focus on the diverse applications of VLLMs, examining their using scenarios, identifying ethics consideration and challenges, and discussing future directions for their development. By synthesizing these contents, we aim to provide a comprehensive guide that will pave the way for future innovations and broader applications of VLLMs. The paper list repository is available: https://github.com/JackYFL/awesome-VLLMs.

cs.CV↗

arXiv2024

Singular vectors, characters, and composition series for the N=1 BMS superalgebra

This paper investigates the structure of Verma modules over the N=1 BMS superalgebra. We provide a detailed classification of singular vectors, establish necessary and sufficient conditions for the existence of subsingular vectors, uncover the structure of maximal submodules, present the composition series of Verma modules, and derive character formulas for irreducible highest weight modules. As a byproduct, we also explicitly determine all singular vectors, subsingular vectors, and the composition series of Verma modules over the algebra W(2,2).

math.RT↗

arXiv2024

Sparse Point Clouds Assisted Learned Image Compression

In the field of autonomous driving, a variety of sensor data types exist, each representing different modalities of the same scene. Therefore, it is feasible to utilize data from other sensors to facilitate image compression. However, few techniques have explored the potential benefits of utilizing inter-modality correlations to enhance the image compression performance. In this paper, motivated by the recent success of learned image compression, we propose a new framework that uses sparse point clouds to assist in learned image compression in the autonomous driving scenario. We first project the 3D sparse point cloud onto a 2D plane, resulting in a sparse depth map. Utilizing this depth map, we proceed to predict camera images. Subsequently, we use these predicted images to extract multi-scale structural features. These features are then incorporated into learned image compression pipeline as additional information to improve the compression performance. Our proposed framework is compatible with various mainstream learned image compression models, and we validate our approach using different existing image compression methods. The experimental results show that incorporating point cloud assistance into the compression pipeline consistently enhances the performance.

cs.CV↗

arXiv2024

Representational Transfer Learning for Matrix Completion

We propose to transfer representational knowledge from multiple sources to a target noisy matrix completion task by aggregating singular subspaces information. Under our representational similarity framework, we first integrate linear representation information by solving a two-way principal component analysis problem based on a properly debiased matrix-valued dataset. After acquiring better column and row representation estimators from the sources, the original high-dimensional target matrix completion problem is then transformed into a low-dimensional linear regression, of which the statistical efficiency is guaranteed. A variety of extensional arguments, including post-transfer statistical inference and robustness against negative transfer, are also discussed alongside. Finally, extensive simulation results and a number of real data cases are reported to support our claims.

stat.ML↗

arXiv2024

An Improved Dung Beetle Optimizer for Random Forest Optimization

To improve the convergence speed and optimization accuracy of the Dung Beetle Optimizer (DBO), this paper proposes an improved algorithm based on circle mapping and longitudinal-horizontal crossover strategy (CICRDBO). First, the Circle method is used to map the initial population to increase diversity. Second, the longitudinal-horizontal crossover strategy is applied to enhance the global search ability by ensuring the position updates of the dung beetle. Simulations were conducted on 10 benchmark test functions, and the results demonstrate that the improved algorithm performs well in both convergence speed and optimization accuracy. The improved algorithm is further applied to the hyperparameter selection of the Random Forest classification algorithm for binary classification prediction in the retail industry. Various combination comparisons prove the practicality of the improved algorithm, followed by SHapley Additive exPlanations (SHAP) analysis.

math.OC↗

arXiv2024

NeRF Inpainting with Geometric Diffusion Prior and Balanced Score Distillation

Recent advances in NeRF inpainting have leveraged pretrained diffusion models to enhance performance. However, these methods often yield suboptimal results due to their ineffective utilization of 2D diffusion priors. The limitations manifest in two critical aspects: the inadequate capture of geometric information by pretrained diffusion models and the suboptimal guidance provided by existing Score Distillation Sampling (SDS) methods. To address these problems, we introduce GB-NeRF, a novel framework that enhances NeRF inpainting through improved utilization of 2D diffusion priors. Our approach incorporates two key innovations: a fine-tuning strategy that simultaneously learns appearance and geometric priors and a specialized normal distillation loss that integrates these geometric priors into NeRF inpainting. We propose a technique called Balanced Score Distillation (BSD) that surpasses existing methods such as Score Distillation (SDS) and the improved version, Conditional Score Distillation (CSD). BSD offers improved inpainting quality in appearance and geometric aspects. Extensive experiments show that our method provides superior appearance fidelity and geometric consistency compared to existing approaches.

cs.CV↗

arXiv2024

StableV2V: Stablizing Shape Consistency in Video-to-Video Editing

Recent advancements of generative AI have significantly promoted content creation and editing, where prevailing studies further extend this exciting progress to video editing. In doing so, these studies mainly transfer the inherent motion patterns from the source videos to the edited ones, where results with inferior consistency to user prompts are often observed, due to the lack of particular alignments between the delivered motions and edited contents. To address this limitation, we present a shape-consistent video editing method, namely StableV2V, in this paper. Our method decomposes the entire editing pipeline into several sequential procedures, where it edits the first video frame, then establishes an alignment between the delivered motions and user prompts, and eventually propagates the edited contents to all other frames based on such alignment. Furthermore, we curate a testing benchmark, namely DAVIS-Edit, for a comprehensive evaluation of video editing, considering various types of prompts and difficulties. Experimental results and analyses illustrate the outperforming performance, visual consistency, and inference efficiency of our method compared to existing state-of-the-art studies.

cs.CV↗

arXiv2024

Simultaneous Estimation and Dataset Selection for Transfer Learning in High Dimensions by a Non-convex Penalty

In this paper, we propose to estimate model parameters and identify informative source datasets simultaneously for high-dimensional transfer learning problems with the aid of a non-convex penalty, in contrast to the separate useful dataset selection and transfer learning procedures in the existing literature. To numerically solve the non-convex problem with respect to two specific statistical models, namely the sparse linear regression and the generalized low-rank trace regression models, we adopt the difference of convex (DC) programming with the alternating direction method of multipliers (ADMM) procedures. We theoretically justify the proposed algorithm from both statistical and computational perspectives. Extensive numerical results are reported alongside to validate the theoretical assertions. An \texttt{R} package \texttt{MHDTL} is developed to implement the proposed methods.

stat.ME↗

arXiv2024

Wafer-scale Semiconductor Grafting: Enabling High-Performance, Lattice-Mismatched Heterojunctions

Semiconductor heterojunctions are foundational to many advanced electronic and optoelectronic devices. However, achieving high-quality, lattice-mismatched interfaces remains challenging, limiting both scalability and device performance. Semiconductor grafting offers a promising solution by directly forming electrically active, lattice-mismatched heterojunctions between dissimilar materials. However, its scalability and uniformity at the wafer level have yet to be demonstrated. This work demonstrates the achievement of highly uniform, reproducible results across silicon, sapphire, and gallium nitride (GaN) substrates using wafer-scale semiconductor grafting. To illustrate this scalability, we conducted an in-depth study of a grafted Si/GaN heterojunction, examining band alignment through X-ray photoelectron spectroscopy and confirming crystallinity and interfacial integrity with scanning transmission electron microscopy. The resulting p-n diodes exhibit significantly enhanced electrical performance and wafer-scale uniformity compared to conventional approaches. This work establishes wafer-scale semiconductor grafting as a versatile and scalable technology, bridging the gap between laboratory-scale research and industrial manufacturing for heterogeneous semiconductor integration, and paving the way for novel, high-performance electronic and optoelectronic devices.

physics.app-ph↗

arXiv2024

Si/AlN p-n heterojunction interfaced with ultrathin SiO2

Ultra-wide bandgap (UWBG) materials hold immense potential for high-power RF electronics and deep ultraviolet photonics. Among these, AlGaN emerges as a promising candidate, offering a tunable bandgap from 3.4 eV (GaN) to 6.1 eV (AlN) and remarkable material characteristics. However, achieving efficient p-type doping in high aluminum composition AlGaN remains a formidable challenge. This study presents an alternative approach to address this issue by fabricating a p+ Si/n-AlN/n+ AlGaN heterojunction structure by following the semiconductor grafting technique. Atomic force microscopy (AFM) analysis revealed that the AlN and the nanomembrane surface exhibited a smooth topography with a roughness of 1.96 nm and 0.545 nm, respectively. High-angle annular dark field scanning transmission electron microscopy (HAADF-STEM) confirmed a sharp and well-defined Si/AlN interface, with minimal defects and strong chemical bonding, crucial for efficient carrier transport. X-ray photoelectron spectroscopy (XPS) measurements demonstrated a type-I heterojunction with a valence band offset of 2.73 eV-2.84 eV and a conduction band offset of 2.22 eV -2.11 eV. The pn diode devices exhibited a linear current-voltage (I-V) characteristic, an ideality factor of 1.92, and a rectification ratio of 3.3E4, with a turn-on voltage of indicating effective p-n heterojunction. Temperature-dependent I-V measurements showed stable operation up to 90 C. The heterojunction's high-quality interface and electrical performance showcase its potential for advanced AlGaN-based optoelectronic and electronic devices.

physics.app-ph↗

arXiv2024

Grafted AlGaAs/GeSn Optical Pumping Laser Operating up to 130 K

Group IV GeSn double-heterostructure (DHS) lasers offer unique advantages of a direct bandgap and CMOS compatibility. However, further improvements in laser performance have been bottlenecked by limited junction properties of GeSn through conventional epitaxy and wafer bonding. This work leverages semiconductor grafting to synthesize and characterize optically pumped ridge edge-emitting lasers (EELs) with an AlGaAs nanomembrane (NM) transfer-printed onto an epitaxially grown GeSn substrate, interfaced by an ultrathin Al2O3 layer. The grafted AlGaAs/GeSn DHS lasers show a lasing threshold of 11.06 mW at 77 K and a maximum lasing temperature of 130 K. These results highlight the potential of the grafting technique for enhancing charge carrier and optical field confinements, paving the way for room-temperature electrically injected GeSn lasers.

physics.optics↗

arXiv2024

SCEP: a Cosmic Magnetic Monopole Search Experiment

Magnetic monopole is a well-motivated class of beyond-Standard-Model particles that could provide insights into the long-standing puzzle of the quantization of electric charge. These hypothetical particles are likely to be super heavy ($\sim$10$^{15}$ GeV) and be produced in the very early stages of the Universe's evolution. We propose a novel detection scenario for the search of such cosmic magnetic monopoles, utilizing a hybrid approach that combines radio-frequency atomic magnetometers and plastic scintillators. Such setup allows for the collection of both the induction and scintillation signals generated by the passage of a magnetic monopole, which provides acceptance to the magnetic monopoles with their velocities larger than about 10$^{-6}$ light speed (assuming a signal-to-noise ratio of $\sim$4) and their masses larger than approximately 10$^7$ GeV (at $β\sim10^{-3}$). The proposed detector design has the potential to scale up to large area, enabling the exploration of the parameter space of the cosmic magnetic monopole beyond the current experimental and astrophysical constraints. It is estimated that such detector can reach current most stringent limits of the flux set by previous searches, with a signal-to-noise ratio of the induction signal larger than about 4.5, assuming an effective exposure being 20000 year$\cdot$m$^2$ and coil layer of 3.

hep-ex↗

arXiv2024

Object Segmentation-Assisted Inter Prediction for Versatile Video Coding

In modern video coding standards, block-based inter prediction is widely adopted, which brings high compression efficiency. However, in natural videos, there are usually multiple moving objects of arbitrary shapes, resulting in complex motion fields that are difficult to represent compactly. This problem has been tackled by more flexible block partitioning methods in the Versatile Video Coding (VVC) standard, but the more flexible partitions require more overhead bits to signal and still cannot be made arbitrarily shaped. To address this limitation, we propose an object segmentation-assisted inter prediction method (SAIP), where objects in the reference frames are segmented by some advanced technologies. With a proper indication, the object segmentation mask is translated from the reference frame to the current frame as the arbitrary-shaped partition of different regions without any extra signal. Using the segmentation mask, motion compensation is separately performed for different regions, achieving higher prediction accuracy. The segmentation mask is further used to code the motion vectors of different regions more efficiently. Moreover, the segmentation mask is considered in the joint rate-distortion optimization for motion estimation and partition estimation to derive the motion vector of different regions and partition more accurately. The proposed method is implemented into the VVC reference software, VTM version 12.0. Experimental results show that the proposed method achieves up to 1.98%, 1.14%, 0.79%, and on average 0.82%, 0.49%, 0.37% BD-rate reduction for common test sequences, under the Low-delay P, Low-delay B, and Random Access configurations, respectively.

eess.IV↗