arXiv subjects

Xin Jin

Publications and source records attributed to Xin Jin.

At least 235 records · Page 13Linked to original sources

arXiv2024

Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models

Disentangled representation learning (DRL) aims to identify and decompose underlying factors behind observations, thus facilitating data perception and generation. However, current DRL approaches often rely on the unrealistic assumption that semantic factors are statistically independent. In reality, these factors may exhibit correlations, which off-the-shelf solutions have yet to properly address. To tackle this challenge, we introduce a bidirectional weighted graph-based framework, to learn factorized attributes and their interrelations within complex data. Specifically, we propose a $β$-VAE based module to extract factors as the initial nodes of the graph, and leverage the multimodal large language model (MLLM) to discover and rank latent correlations, thereby updating the weighted edges. By integrating these complementary modules, our model successfully achieves fine-grained, practical and unsupervised disentanglement. Experiments demonstrate our method's superior performance in disentanglement and reconstruction. Furthermore, the model inherits enhanced interpretability and generalizability from MLLMs.

cs.CV↗

arXiv2024

Rethinking Domain Adaptation and Generalization in the Era of CLIP

In recent studies on domain adaptation, significant emphasis has been placed on the advancement of learning shared knowledge from a source domain to a target domain. Recently, the large vision-language pre-trained model, i.e., CLIP has shown strong ability on zero-shot recognition, and parameter efficient tuning can further improve its performance on specific tasks. This work demonstrates that a simple domain prior boosts CLIP's zero-shot recognition in a specific domain. Besides, CLIP's adaptation relies less on source domain data due to its diverse pre-training dataset. Furthermore, we create a benchmark for zero-shot adaptation and pseudo-labeling based self-training with CLIP. Last but not least, we propose to improve the task generalization ability of CLIP from multiple unlabeled domains, which is a more practical and unique scenario. We believe our findings motivate a rethinking of domain adaptation benchmarks and the associated role of related algorithms in the era of CLIP.

cs.CV↗

arXiv2024

Rate-Distortion-Cognition Controllable Versatile Neural Image Compression

Recently, the field of Image Coding for Machines (ICM) has garnered heightened interest and significant advances thanks to the rapid progress of learning-based techniques for image compression and analysis. Previous studies often require training separate codecs to support various bitrate levels, machine tasks, and networks, thus lacking both flexibility and practicality. To address these challenges, we propose a rate-distortion-cognition controllable versatile image compression, which method allows the users to adjust the bitrate (i.e., Rate), image reconstruction quality (i.e., Distortion), and machine task accuracy (i.e., Cognition) with a single neural model, achieving ultra-controllability. Specifically, we first introduce a cognition-oriented loss in the primary compression branch to train a codec for diverse machine tasks. This branch attains variable bitrate by regulating quantization degree through the latent code channels. To further enhance the quality of the reconstructed images, we employ an auxiliary branch to supplement residual information with a scalable bitstream. Ultimately, two branches use a `$βx + (1 - β) y$' interpolation strategy to achieve a balanced cognition-distortion trade-off. Extensive experiments demonstrate that our method yields satisfactory ICM performance and flexible Rate-Distortion-Cognition controlling.

cs.CV↗

arXiv2024

DiffRetouch: Using Diffusion to Retouch on the Shoulder of Experts

Image retouching aims to enhance the visual quality of photos. Considering the different aesthetic preferences of users, the target of retouching is subjective. However, current retouching methods mostly adopt deterministic models, which not only neglects the style diversity in the expert-retouched results and tends to learn an average style during training, but also lacks sample diversity during inference. In this paper, we propose a diffusion-based method, named DiffRetouch. Thanks to the excellent distribution modeling ability of diffusion, our method can capture the complex fine-retouched distribution covering various visual-pleasing styles in the training data. Moreover, four image attributes are made adjustable to provide a user-friendly editing mechanism. By adjusting these attributes in specified ranges, users are allowed to customize preferred styles within the learned fine-retouched distribution. Additionally, the affine bilateral grid and contrastive learning scheme are introduced to handle the problem of texture distortion and control insensitivity respectively. Extensive experiments have demonstrated the superior performance of our method on visually appealing and sample diversity. The code will be made available to the community.

cs.CV↗

arXiv2024

LoongTrain: Efficient Training of Long-Sequence LLMs with Head-Context Parallelism

Efficiently training LLMs with long sequences is important yet challenged by the massive computation and memory requirements. Sequence parallelism has been proposed to tackle these problems, but existing methods suffer from scalability or efficiency issues. We propose LoongTrain, a novel system to efficiently train LLMs with long sequences at scale. The core of LoongTrain is the 2D-Attention mechanism, which combines both head-parallel and context-parallel techniques to break the scalability constraints while maintaining efficiency. We introduce Double-Ring-Attention and analyze the performance of device placement strategies to further speed up training. We implement LoongTrain with the hybrid ZeRO and Selective Checkpoint++ techniques. Experiment results show that LoongTrain outperforms state-of-the-art baselines, i.e., DeepSpeed-Ulysses and Megatron Context Parallelism, in both end-to-end training speed and scalability, and improves Model FLOPs Utilization (MFU) by up to 2.88x.

cs.DC↗

arXiv2024

DARTS: Diffusion Approximated Residual Time Sampling for Time-of-flight Rendering in Homogeneous Scattering Media

Time-of-flight (ToF) devices have greatly propelled the advancement of various multi-modal perception applications. However, achieving accurate rendering of time-resolved information remains a challenge, particularly in scenes involving complex geometries, diverse materials and participating media. Existing ToF rendering works have demonstrated notable results, yet they struggle with scenes involving scattering media and camera-warped settings. Other steady-state volumetric rendering methods exhibit significant bias or variance when directly applied to ToF rendering tasks. To address these challenges, we integrate transient diffusion theory into path construction and propose novel sampling methods for free-path distance and scattering direction, via resampled importance sampling and offline tabulation. An elliptical sampling method is further adapted to provide controllable vertex connection satisfying any required photon traversal time. In contrast to the existing temporal uniform sampling strategy, our method is the first to consider the contribution of transient radiance to importance-sample the full path, and thus enables improved temporal path construction under multiple scattering settings. The proposed method can be integrated into both path tracing and photon-based frameworks, delivering significant improvements in quality and efficiency with at least a 5x MSE reduction versus SOTA methods in equal rendering time.

cs.GR↗

arXiv2024

MIPI 2024 Challenge on Few-shot RAW Image Denoising: Methods and Results

The increasing demand for computational photography and imaging on mobile platforms has led to the widespread development and integration of advanced image sensors with novel algorithms in camera systems. However, the scarcity of high-quality data for research and the rare opportunity for in-depth exchange of views from industry and academia constrain the development of mobile intelligent photography and imaging (MIPI). Building on the achievements of the previous MIPI Workshops held at ECCV 2022 and CVPR 2023, we introduce our third MIPI challenge including three tracks focusing on novel image sensors and imaging algorithms. In this paper, we summarize and review the Few-shot RAW Image Denoising track on MIPI 2024. In total, 165 participants were successfully registered, and 7 teams submitted results in the final testing phase. The developed solutions in this challenge achieved state-of-the-art erformance on Few-shot RAW Image Denoising. More details of this challenge and the link to the dataset can be found at https://mipichallenge.org/MIPI2024.

cs.CV↗

arXiv2024

Lighting Every Darkness with 3DGS: Fast Training and Real-Time Rendering for HDR View Synthesis

Volumetric rendering based methods, like NeRF, excel in HDR view synthesis from RAWimages, especially for nighttime scenes. While, they suffer from long training times and cannot perform real-time rendering due to dense sampling requirements. The advent of 3D Gaussian Splatting (3DGS) enables real-time rendering and faster training. However, implementing RAW image-based view synthesis directly using 3DGS is challenging due to its inherent drawbacks: 1) in nighttime scenes, extremely low SNR leads to poor structure-from-motion (SfM) estimation in distant views; 2) the limited representation capacity of spherical harmonics (SH) function is unsuitable for RAW linear color space; and 3) inaccurate scene structure hampers downstream tasks such as refocusing. To address these issues, we propose LE3D (Lighting Every darkness with 3DGS). Our method proposes Cone Scatter Initialization to enrich the estimation of SfM, and replaces SH with a Color MLP to represent the RAW linear color space. Additionally, we introduce depth distortion and near-far regularizations to improve the accuracy of scene structure for downstream tasks. These designs enable LE3D to perform real-time novel view synthesis, HDR rendering, refocusing, and tone-mapping changes. Compared to previous volumetric rendering based methods, LE3D reduces training time to 1% and improves rendering speed by up to 4,000 times for 2K resolution images in terms of FPS. Code and viewer can be found in https://github.com/Srameo/LE3D .

cs.CV↗

arXiv2024

DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving

DistServe improves the performance of large language models (LLMs) serving by disaggregating the prefill and decoding computation. Existing LLM serving systems colocate the two phases and batch the computation of prefill and decoding across all users and requests. We find that this strategy not only leads to strong prefill-decoding interferences but also couples the resource allocation and parallelism plans for both phases. LLM applications often emphasize individual latency for each phase: time to first token (TTFT) for the prefill phase and time per output token (TPOT) of each request for the decoding phase. In the presence of stringent latency requirements, existing systems have to prioritize one latency over the other, or over-provision compute resources to meet both. DistServe assigns prefill and decoding computation to different GPUs, hence eliminating prefill-decoding interferences. Given the application's TTFT and TPOT requirements, DistServe co-optimizes the resource allocation and parallelism strategy tailored for each phase. DistServe also places the two phases according to the serving cluster's bandwidth to minimize the communication caused by disaggregation. As a result, DistServe significantly improves LLM serving performance in terms of the maximum rate that can be served within both TTFT and TPOT constraints on each GPU. Our evaluations show that on various popular LLMs, applications, and latency requirements, DistServe can serve 7.4x more requests or 12.6x tighter SLO, compared to state-of-the-art systems, while staying within latency constraints for > 90% of requests.

cs.DC↗

arXiv2024

StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization

Single domain generalization (single DG) aims at learning a robust model generalizable to unseen domains from only one training domain, making it a highly ambitious and challenging task. State-of-the-art approaches have mostly relied on data augmentations, such as adversarial perturbation and style enhancement, to synthesize new data and thus increase robustness. Nevertheless, they have largely overlooked the underlying coherence between the augmented domains, which in turn leads to inferior results in real-world scenarios. In this paper, we propose a simple yet effective scheme, termed as \emph{StyDeSty}, to explicitly account for the alignment of the source and pseudo domains in the process of data augmentation, enabling them to interact with each other in a self-consistent manner and further giving rise to a latent domain with strong generalization power. The heart of StyDeSty lies in the interaction between a \emph{stylization} module for generating novel stylized samples using the source domain, and a \emph{destylization} module for transferring stylized and source samples to a latent domain to learn content-invariant features. The stylization and destylization modules work adversarially and reinforce each other. During inference, the destylization module transforms the input sample with an arbitrary style shift to the latent domain, in which the downstream tasks are carried out. Specifically, the location of the destylization layer within the backbone network is determined by a dedicated neural architecture search (NAS) strategy. We evaluate StyDeSty on multiple benchmarks and demonstrate that it yields encouraging results, outperforming the state of the art by up to {13.44%} on classification accuracy. Codes are available here: https://github.com/Huage001/StyDeSty.

cs.CV↗

arXiv2024

Deciphering Human Mobility: Inferring Semantics of Trajectories with Large Language Models

Understanding human mobility patterns is essential for various applications, from urban planning to public safety. The individual trajectory such as mobile phone location data, while rich in spatio-temporal information, often lacks semantic detail, limiting its utility for in-depth mobility analysis. Existing methods can infer basic routine activity sequences from this data, lacking depth in understanding complex human behaviors and users' characteristics. Additionally, they struggle with the dependency on hard-to-obtain auxiliary datasets like travel surveys. To address these limitations, this paper defines trajectory semantic inference through three key dimensions: user occupation category, activity sequence, and trajectory description, and proposes the Trajectory Semantic Inference with Large Language Models (TSI-LLM) framework to leverage LLMs infer trajectory semantics comprehensively and deeply. We adopt spatio-temporal attributes enhanced data formatting (STFormat) and design a context-inclusive prompt, enabling LLMs to more effectively interpret and infer the semantics of trajectory data. Experimental validation on real-world trajectory datasets demonstrates the efficacy of TSI-LLM in deciphering complex human mobility patterns. This study explores the potential of LLMs in enhancing the semantic analysis of trajectory data, paving the way for more sophisticated and accessible human mobility research.

cs.AI↗

arXiv2024

Diff-BGM: A Diffusion Model for Video Background Music Generation

When editing a video, a piece of attractive background music is indispensable. However, video background music generation tasks face several challenges, for example, the lack of suitable training datasets, and the difficulties in flexibly controlling the music generation process and sequentially aligning the video and music. In this work, we first propose a high-quality music-video dataset BGM909 with detailed annotation and shot detection to provide multi-modal information about the video and music. We then present evaluation metrics to assess music quality, including music diversity and alignment between music and video with retrieval precision metrics. Finally, we propose the Diff-BGM framework to automatically generate the background music for a given video, which uses different signals to control different aspects of the music during the generation process, i.e., uses dynamic video features to control music rhythm and semantic features to control the melody and atmosphere. We propose to align the video and music sequentially by introducing a segment-aware cross-attention layer. Experiments verify the effectiveness of our proposed method. The code and models are available at https://github.com/sizhelee/Diff-BGM.

cs.CV↗

arXiv2024

Trajectory Planning and Tracking of Hybrid Flying-Crawling Quadrotors

Hybrid Flying-Crawling Quadrotors (HyFCQs) are transformable robots with the ability of terrestrial and aerial hybrid motion. This article presents a trajectory planning and tracking framework designed for HyFCQs. In this framework, a terrestrial-aerial path-searching method with the crawling limitation of HyFCQs is proposed to guarantee the dynamical feasibility of trajectories. Additionally, a trajectory tracking method is proposed to address the challenges associated with the deformation time required by HyFCQs, which makes tracking hybrid trajectories at the junction between terrestrial and aerial segments difficult. Simulations and real-world experiments in diverse scenarios validate the exceptional performance of the proposed approach.

cs.RO↗

arXiv2024

Enhanced Terahertz Spectroscopy of a Monolayer Transition Metal Dichalcogenide

Two-dimensional materials, including transition metal dichalcogenides, are attractive for a variety of applications in electronics as well as photonics and have recently been envisioned as an appealing platform for phonon polaritonics. However, their direct characterization in the terahertz spectral region, of interest for retrieving, e.g., their phonon response, represents a major challenge, due to the limited sensitivity of typical terahertz spectroscopic tools and the weak interaction of such long-wavelength radiation with sub-nanometer systems. In this work, by exploiting an ad-hoc engineered metallic surface enabling a ten-thousand-fold local absorption boost, we perform enhanced terahertz spectroscopy of a monolayer transition metal dichalcogenide (tungsten diselenide) and extract its dipole-active phonon resonance features. In addition, we use these data to obtain the monolayer effective permittivity around its phonon resonance. Via the direct terahertz characterization of the phonon response of such two-dimensional systems, this method opens the path to the rational design of phonon polariton devices exploiting monolayer transition metal dichalcogenides.

physics.optics↗

arXiv2024

EmMixformer: Mix transformer for eye movement recognition

Eye movement (EM) is a new highly secure biometric behavioral modality that has received increasing attention in recent years. Although deep neural networks, such as convolutional neural network (CNN), have recently achieved promising performance, current solutions fail to capture local and global temporal dependencies within eye movement data. To overcome this problem, we propose in this paper a mixed transformer termed EmMixformer to extract time and frequency domain information for eye movement recognition. To this end, we propose a mixed block consisting of three modules, transformer, attention Long short-term memory (attention LSTM), and Fourier transformer. We are the first to attempt leveraging transformer to learn long temporal dependencies within eye movement. Second, we incorporate the attention mechanism into LSTM to propose attention LSTM with the aim to learn short temporal dependencies. Third, we perform self attention in the frequency domain to learn global features. As the three modules provide complementary feature representations in terms of local and global dependencies, the proposed EmMixformer is capable of improving recognition accuracy. The experimental results on our eye movement dataset and two public eye movement datasets show that the proposed EmMixformer outperforms the state of the art by achieving the lowest verification error.

cs.CV↗

arXiv2024

Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completion

3D semantic scene completion (SSC) is an ill-posed perception task that requires inferring a dense 3D scene from limited observations. Previous camera-based methods struggle to predict accurate semantic scenes due to inherent geometric ambiguity and incomplete observations. In this paper, we resort to stereo matching technique and bird's-eye-view (BEV) representation learning to address such issues in SSC. Complementary to each other, stereo matching mitigates geometric ambiguity with epipolar constraint while BEV representation enhances the hallucination ability for invisible regions with global semantic context. However, due to the inherent representation gap between stereo geometry and BEV features, it is non-trivial to bridge them for dense prediction task of SSC. Therefore, we further develop a unified occupancy-based framework dubbed BRGScene, which effectively bridges these two representations with dense 3D volumes for reliable semantic scene completion. Specifically, we design a novel Mutual Interactive Ensemble (MIE) block for pixel-level reliable aggregation of stereo geometry and BEV features. Within the MIE block, a Bi-directional Reliable Interaction (BRI) module, enhanced with confidence re-weighting, is employed to encourage fine-grained interaction through mutual guidance. Besides, a Dual Volume Ensemble (DVE) module is introduced to facilitate complementary aggregation through channel-wise recalibration and multi-group voting. Our method outperforms all published camera-based methods on SemanticKITTI for semantic scene completion. Our code is available on https://github.com/Arlo0o/StereoScene.

cs.CV↗

arXiv2024

Paintings and Drawings Aesthetics Assessment with Rich Attributes for Various Artistic Categories

Image aesthetic evaluation is a highly prominent research domain in the field of computer vision. In recent years, there has been a proliferation of datasets and corresponding evaluation methodologies for assessing the aesthetic quality of photographic works, leading to the establishment of a relatively mature research environment. However, in contrast to the extensive research in photographic aesthetics, the field of aesthetic evaluation for paintings and Drawings has seen limited attention until the introduction of the BAID dataset in March 2023. This dataset solely comprises overall scores for high-quality artistic images. Our research marks the pioneering introduction of a multi-attribute, multi-category dataset specifically tailored to the field of painting: Aesthetics of Paintings and Drawings Dataset (APDD). The construction of APDD received active participation from 28 professional artists worldwide, along with dozens of students specializing in the field of art. This dataset encompasses 24 distinct artistic categories and 10 different aesthetic attributes. Each image in APDD has been evaluated by six professionally trained experts in the field of art, including assessments for both total aesthetic scores and aesthetic attribute scores. The final APDD dataset comprises a total of 4985 images, with an annotation count exceeding 31100 entries. Concurrently, we propose an innovative approach: Art Assessment Network for Specific Painting Styles (AANSPS), designed for the assessment of aesthetic attributes in mixed-attribute art datasets. Through this research, our goal is to catalyze advancements in the field of aesthetic evaluation for paintings and drawings, while enriching the available resources and methodologies for its further development and application.

cs.CV↗

arXiv2024

Graphene: Infrastructure Security Posture Analysis with AI-generated Attack Graphs

The rampant occurrence of cybersecurity breaches imposes substantial limitations on the progress of network infrastructures, leading to compromised data, financial losses, potential harm to individuals, and disruptions in essential services. The current security landscape demands the urgent development of a holistic security assessment solution that encompasses vulnerability analysis and investigates the potential exploitation of these vulnerabilities as attack paths. In this paper, we propose Graphene, an advanced system designed to provide a detailed analysis of the security posture of computing infrastructures. Using user-provided information, such as device details and software versions, Graphene performs a comprehensive security assessment. This assessment includes identifying associated vulnerabilities and constructing potential attack graphs that adversaries can exploit. Furthermore, Graphene evaluates the exploitability of these attack paths and quantifies the overall security posture through a scoring mechanism. The system takes a holistic approach by analyzing security layers encompassing hardware, system, network, and cryptography. Furthermore, Graphene delves into the interconnections between these layers, exploring how vulnerabilities in one layer can be leveraged to exploit vulnerabilities in others. In this paper, we present the end-to-end pipeline implemented in Graphene, showcasing the systematic approach adopted for conducting this thorough security analysis.

cs.CR↗