arXiv subjects

Ke Li

Publications and source records attributed to Ke Li.

At least 199 records · Page 11Linked to original sources

arXiv2024

FD2-Net: Frequency-Driven Feature Decomposition Network for Infrared-Visible Object Detection

Infrared-visible object detection (IVOD) seeks to harness the complementary information in infrared and visible images, thereby enhancing the performance of detectors in complex environments. However, existing methods often neglect the frequency characteristics of complementary information, such as the abundant high-frequency details in visible images and the valuable low-frequency thermal information in infrared images, thus constraining detection performance. To solve this problem, we introduce a novel Frequency-Driven Feature Decomposition Network for IVOD, called FD2-Net, which effectively captures the unique frequency representations of complementary information across multimodal visual spaces. Specifically, we propose a feature decomposition encoder, wherein the high-frequency unit (HFU) utilizes discrete cosine transform to capture representative high-frequency features, while the low-frequency unit (LFU) employs dynamic receptive fields to model the multi-scale context of diverse objects. Next, we adopt a parameter-free complementary strengths strategy to enhance multimodal features through seamless inter-frequency recoupling. Furthermore, we innovatively design a multimodal reconstruction mechanism that recovers image details lost during feature extraction, further leveraging the complementary information from infrared and visible images to enhance overall representational capacity. Extensive experiments demonstrate that FD2-Net outperforms state-of-the-art (SOTA) models across various IVOD benchmarks, i.e. LLVIP (96.2% mAP), FLIR (82.9% mAP), and M3FD (83.5% mAP).

cs.CV↗

arXiv2024

Woodpecker: Hallucination Correction for Multimodal Large Language Models

Hallucination is a big shadow hanging over the rapidly evolving Multimodal Large Language Models (MLLMs), referring to the phenomenon that the generated text is inconsistent with the image content. In order to mitigate hallucinations, existing studies mainly resort to an instruction-tuning manner that requires retraining the models with specific data. In this paper, we pave a different way, introducing a training-free method named Woodpecker. Like a woodpecker heals trees, it picks out and corrects hallucinations from the generated text. Concretely, Woodpecker consists of five stages: key concept extraction, question formulation, visual knowledge validation, visual claim generation, and hallucination correction. Implemented in a post-remedy manner, Woodpecker can easily serve different MLLMs, while being interpretable by accessing intermediate outputs of the five stages. We evaluate Woodpecker both quantitatively and qualitatively and show the huge potential of this new paradigm. On the POPE benchmark, our method obtains a 30.66%/24.33% improvement in accuracy over the baseline MiniGPT-4/mPLUG-Owl. The source code is released at https://github.com/BradyFU/Woodpecker.

cs.CV↗

arXiv2024

Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM

Rapidly developing large language models (LLMs) have brought tremendous intelligent applications. Especially, the GPT-4o's excellent duplex speech interaction ability has brought impressive experience to users. Researchers have recently proposed several multi-modal LLMs in this direction that can achieve user-agent speech-to-speech conversations. This paper proposes a novel speech-text multimodal LLM architecture called Freeze-Omni. Our main contribution is that the speech input and output modalities can be easily connected to a textual LLM while keeping the LLM's parameters frozen throughout the training process. We design a three-stage training strategy for modeling both the speech input and output, enabling Freeze-Omni to obtain speech-to-speech conversation ability using text-speech paired data (such as ASR and TTS data) and only 60,000 multi-round text Q&A data on 8 GPUs. Moreover, we can effectively ensure that the intelligence of the Freeze-Omni in the speech modality is at the same level compared with that in the text modality of its backbone LLM, while achieving low latency end-to-end spoken response. In addition, we also designed a method to achieve duplex dialogue ability through multi-task training, giving Freeze-Omni a more natural style of dialogue ability between users and agents. In summary, Freeze-Omni holds great potential to conduct speech-to-speech dialogue based on a multimodal LLM under the condition of a frozen LLM, avoiding the catastrophic forgetting problem caused by limited data and training resources.

cs.SD↗

arXiv2024

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression

Despite a big leap forward in capability, multimodal large language models (MLLMs) tend to behave like a sloth in practical use, i.e., slow response and large latency. Recent efforts are devoted to building tiny MLLMs for better efficiency, but the plethora of visual tokens still used limit their actual speedup. In this paper, we propose a powerful and fast tiny MLLM called FlashSloth. Different from previous efforts, FlashSloth focuses on improving the descriptive power of visual tokens in the process of compressing their redundant semantics. In particular, FlashSloth introduces embedded visual compression designs to capture both visually salient and instruction-related image information, so as to achieving superior multimodal performance with fewer visual tokens. Extensive experiments are conducted to validate the proposed FlashSloth, and a bunch of tiny but strong MLLMs are also comprehensively compared, e.g., InternVL2, MiniCPM-V2 and Qwen2-VL. The experimental results show that compared with these advanced tiny MLLMs, our FlashSloth can greatly reduce the number of visual tokens, training memory and computation complexity while retaining high performance on various VL tasks.

cs.CV↗

arXiv2024

Adaptive Basis-inspired Deep Neural Network for Solving Partial Differential Equations with Localized Features

This paper proposes an Adaptive Basis-inspired Deep Neural Network (ABI-DNN) for solving partial differential equations with localized phenomena such as sharp gradients and singularities. Like the adaptive finite element method, ABI-DNN incorporates an iteration of "solve, estimate, mark, enhancement", which automatically identifies challenging regions and adds new neurons to enhance its capability. A key challenge is to force new neurons to focus on identified regions with limited understanding of their roles in approximation. To address this, we draw inspiration from the finite element basis function and construct the novel Basis-inspired Block (BI-block), to help understand the contribution of each block. With the help of the BI-block and the famous Kolmogorov Superposition Theorem, we first develop a novel fixed network architecture named the Basis-inspired Deep Neural Network (BI-DNN), and then integrate it into the aforementioned adaptive framework to propose the ABI-DNN. Extensive numerical experiments demonstrate that both BI-DNN and ABI-DNN can effectively capture the challenging singularities in target functions. Compared to PINN, BI-DNN attains significantly lower relative errors with a similar number of trainable parameters. When a specified tolerance is set, ABI-DNN can adaptively learn an appropriate architecture that achieves an error comparable to that of BI-DNN with the same structure.

math.NA↗

arXiv2024

A Survey on Multimodal Large Language Models

Recently, Multimodal Large Language Model (MLLM) represented by GPT-4V has been a new rising research hotspot, which uses powerful Large Language Models (LLMs) as a brain to perform multimodal tasks. The surprising emergent capabilities of MLLM, such as writing stories based on images and OCR-free math reasoning, are rare in traditional multimodal methods, suggesting a potential path to artificial general intelligence. To this end, both academia and industry have endeavored to develop MLLMs that can compete with or even better than GPT-4V, pushing the limit of research at a surprising speed. In this paper, we aim to trace and summarize the recent progress of MLLMs. First of all, we present the basic formulation of MLLM and delineate its related concepts, including architecture, training strategy and data, as well as evaluation. Then, we introduce research topics about how MLLMs can be extended to support more granularity, modalities, languages, and scenarios. We continue with multimodal hallucination and extended techniques, including Multimodal ICL (M-ICL), Multimodal CoT (M-CoT), and LLM-Aided Visual Reasoning (LAVR). To conclude the paper, we discuss existing challenges and point out promising research directions. In light of the fact that the era of MLLM has only just begun, we will keep updating this survey and hope it can inspire more research. An associated GitHub link collecting the latest papers is available at https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models.

cs.CV↗

arXiv2024

ActSonic: Recognizing Everyday Activities from Inaudible Acoustic Wave Around the Body

We present ActSonic, an intelligent, low-power active acoustic sensing system integrated into eyeglasses that can recognize 27 different everyday activities (e.g., eating, drinking, toothbrushing) from inaudible acoustic waves around the body. It requires only a pair of miniature speakers and microphones mounted on each hinge of the eyeglasses to emit ultrasonic waves, creating an acoustic aura around the body. The acoustic signals are reflected based on the position and motion of various body parts, captured by the microphones, and analyzed by a customized self-supervised deep learning framework to infer the performed activities on a remote device such as a mobile phone or cloud server. ActSonic was evaluated in user studies with 19 participants across 19 households to track its efficacy in everyday activity recognition. Without requiring any training data from new users (leave-one-participant-out evaluation), ActSonic detected 27 activities, achieving an average F1-score of 86.6% in fully unconstrained scenarios and 93.4% in prompted settings at participants' homes.

cs.HC↗

arXiv2024

Show Me What and Where has Changed? Question Answering and Grounding for Remote Sensing Change Detection

Remote sensing change detection aims to perceive changes occurring on the Earth's surface from remote sensing data in different periods, and feed these changes back to humans. However, most existing methods only focus on detecting change regions, lacking the capability to interact with users to identify changes that the users expect. In this paper, we introduce a new task named Change Detection Question Answering and Grounding (CDQAG), which extends the traditional change detection task by providing interpretable textual answers and intuitive visual evidence. To this end, we construct the first CDQAG benchmark dataset, termed QAG-360K, comprising over 360K triplets of questions, textual answers, and corresponding high-quality visual masks. It encompasses 10 essential land-cover categories and 8 comprehensive question types, which provides a valuable and diverse dataset for remote sensing applications. Furthermore, we present VisTA, a simple yet effective baseline method that unifies the tasks of question answering and grounding by delivering both visual and textual answers. Our method achieves state-of-the-art results on both the classic change detection-based visual question answering (CDVQA) and the proposed CDQAG datasets. Extensive qualitative and quantitative experimental results provide useful insights for developing better CDQAG models, and we hope that our work can inspire further research in this important yet underexplored research field. The proposed benchmark dataset and method are available at https://github.com/like413/VisTA.

cs.CV↗

arXiv2024

Ring-a-Pose: A Ring for Continuous Hand Pose Tracking

We present Ring-a-Pose, a single untethered ring that tracks continuous 3D hand poses. Located in the center of the hand, the ring emits an inaudible acoustic signal that each hand pose reflects differently. Ring-a-Pose imposes minimal obtrusions on the hand, unlike multi-ring or glove systems. It is not affected by the choice of clothing that may cover wrist-worn systems. In a series of three user studies with a total of 30 participants, we evaluate Ring-a-Pose's performance on pose tracking and micro-finger gesture recognition. Without collecting any training data from a user, Ring-a-Pose tracks continuous hand poses with a joint error of 14.1mm. The joint error decreases to 10.3mm for fine-tuned user-dependent models. Ring-a-Pose recognizes 7-class micro-gestures with a 90.60% and 99.27% accuracy for user-independent and user-dependent models, respectively. Furthermore, the ring exhibits promising performance when worn on any finger. Ring-a-Pose enables the future of smart rings to track and recognize hand poses using relatively low-power acoustic sensing.

cs.HC↗

arXiv2024

PediatricsGPT: Large Language Models as Chinese Medical Assistants for Pediatric Applications

Developing intelligent pediatric consultation systems offers promising prospects for improving diagnostic efficiency, especially in China, where healthcare resources are scarce. Despite recent advances in Large Language Models (LLMs) for Chinese medicine, their performance is sub-optimal in pediatric applications due to inadequate instruction data and vulnerable training procedures. To address the above issues, this paper builds PedCorpus, a high-quality dataset of over 300,000 multi-task instructions from pediatric textbooks, guidelines, and knowledge graph resources to fulfil diverse diagnostic demands. Upon well-designed PedCorpus, we propose PediatricsGPT, the first Chinese pediatric LLM assistant built on a systematic and robust training pipeline. In the continuous pre-training phase, we introduce a hybrid instruction pre-training mechanism to mitigate the internal-injected knowledge inconsistency of LLMs for medical domain adaptation. Immediately, the full-parameter Supervised Fine-Tuning (SFT) is utilized to incorporate the general medical knowledge schema into the models. After that, we devise a direct following preference optimization to enhance the generation of pediatrician-like humanistic responses. In the parameter-efficient secondary SFT phase, a mixture of universal-specific experts strategy is presented to resolve the competency conflict between medical generalist and pediatric expertise mastery. Extensive results based on the metrics, GPT-4, and doctor evaluations on distinct doctor downstream tasks show that PediatricsGPT consistently outperforms previous Chinese medical LLMs. Our model and dataset will be open-source for community development.

cs.CL↗

arXiv2024

MBL-CPDP: A Multi-objective Bilevel Method for Cross-Project Defect Prediction via Automated Machine Learning

Cross-project defect prediction (CPDP) leverages machine learning (ML) techniques to proactively identify software defects, especially where project-specific data is scarce. However, developing a robust ML pipeline with optimal hyperparameters that effectively use cross-project information and yield satisfactory performance remains challenging. In this paper, we resolve this bottleneck by formulating CPDP as a multi-objective bilevel optimization (MBLO) method, dubbed MBL-CPDP. It comprises two nested problems: the upper-level, a multi-objective combinatorial optimization problem, enhances robustness and efficiency in optimizing ML pipelines, while the lower-level problem is an expensive optimization problem that focuses on tuning their optimal hyperparameters. Due to the high-dimensional search space characterized by feature redundancy and inconsistent data distributions, the upper-level problem combines feature selection, transfer learning, and classification to leverage limited and heterogeneous historical data. Meanwhile, an ensemble learning method is proposed to capture differences in cross-project distribution and generalize across diverse datasets. Finally, a MBLO algorithm is presented to solve this problem while achieving high adaptability effectively. To evaluate the performance of MBL-CPDP, we compare it with five automated ML tools and $50$ CPDP techniques across $20$ projects. Extensive empirical results show that MBL-CPDPoutperforms the comparison methods, demonstrating its superior adaptability and comprehensive performance evaluation capability.

cs.NE↗

arXiv2024

A conditional normalizing flow for domain decomposed uncertainty quantification

In this paper we present a conditional KRnet (cKRnet) based domain decomposed uncertainty quantification (CKR-DDUQ) approach to propagate uncertainties across different physical domains in models governed by partial differential equations (PDEs) with random inputs. This approach is based on the domain decomposed uncertainty quantification (DDUQ) method presented in [Q. Liao and K. Willcox, SIAM J. Sci. Comput., 37 (2015), pp. A103--A133], which suffers a bottleneck of density estimation for local joint input distributions in practice. In this work, we reformulate the required joint distributions as conditional distributions, and propose a new conditional normalizing flow model, called cKRnet, to efficiently estimate the conditional probability density functions. We present the general framework of CKR-DDUQ, conduct its convergence analysis, validate its accuracy and demonstrate its efficiency with numerical experiments.

math.NA↗

arXiv2024

ProvNeRF: Modeling per Point Provenance in NeRFs as a Stochastic Field

Neural radiance fields (NeRFs) have gained popularity with multiple works showing promising results across various applications. However, to the best of our knowledge, existing works do not explicitly model the distribution of training camera poses, or consequently the triangulation quality, a key factor affecting reconstruction quality dating back to classical vision literature. We close this gap with ProvNeRF, an approach that models the \textbf{provenance} for each point -- i.e., the locations where it is likely visible -- of NeRFs as a stochastic field. We achieve this by extending implicit maximum likelihood estimation (IMLE) to functional space with an optimizable objective. We show that modeling per-point provenance during the NeRF optimization enriches the model with information on triangulation leading to improvements in novel view synthesis and uncertainty estimation under the challenging sparse, unconstrained view setting against competitive baselines.

cs.CV↗

arXiv2024

A high order unfitted finite element method for time-Harmonic Maxwell interface problems

We propose a high order unfitted finite element method for solving timeharmonic Maxwell interface problems. The unfitted finite element method is based on a mixed formulation in the discontinuous Galerkin framework on a Cartesian mesh with possible hanging nodes. The $H^2$ regularity of the solution to Maxwell interface problems with $C^2$ interfaces in each subdomain is proved. Practical interface-resolving mesh conditions are introduced under which the hp inverse estimates on three-dimensional curved domains are proved. Stability and hp a priori error estimate of the unfitted finite element method are proved. Numerical results are included to illustrate the performance of the method.

math.NA↗

arXiv2024

SonicID: User Identification on Smart Glasses with Acoustic Sensing

Smart glasses have become more prevalent as they provide an increasing number of applications for users. They store various types of private information or can access it via connections established with other devices. Therefore, there is a growing need for user identification on smart glasses. In this paper, we introduce a low-power and minimally-obtrusive system called SonicID, designed to authenticate users on glasses. SonicID extracts unique biometric information from users by scanning their faces with ultrasonic waves and utilizes this information to distinguish between different users, powered by a customized binary classifier with the ResNet-18 architecture. SonicID can authenticate users by scanning their face for 0.06 seconds. A user study involving 40 participants confirms that SonicID achieves a true positive rate of 97.4%, a false positive rate of 4.3%, and a balanced accuracy of 96.6% using just 1 minute of training data collected for each new user. This performance is relatively consistent across different remounting sessions and days. Given this promising performance, we further discuss the potential applications of SonicID and methods to improve its performance in the future.

cs.HC↗

arXiv2024

A Survey of Decomposition-Based Evolutionary Multi-Objective Optimization: Part I-Past and Future

Decomposition has been the mainstream approach in classic mathematical programming for multi-objective optimization and multi-criterion decision-making. However, it was not properly studied in the context of evolutionary multi-objective optimization (EMO) until the development of multi-objective evolutionary algorithm based on decomposition (MOEA/D). In this two-part survey series, we use MOEA/D as the representative of decomposition-based EMO to review the up-to-date development in this area, and systematically and comprehensively analyze its research landscape. In the first part, we present a comprehensive survey of the development of MOEA/D from its origin to the current state-of-the-art approaches. In order to be self-contained, we start with a step-by-step tutorial that aims to help a novice quickly get onto the working mechanism of MOEA/D. Then, selected major developments of MOEA/D are reviewed according to its core design components including weight vector settings, subproblem formulations, selection mechanisms and reproduction operators. Besides, we also overview some selected advanced topics for constraint handling, optimization in dynamic and uncertain environments, computationally expensive objective functions, and preference incorporation. In the final part, we shed some light on emerging directions for future developments.

cs.NE↗

arXiv2024

READ: Recurrent Adaptation of Large Transformers

Fine-tuning large-scale Transformers has led to the explosion of many AI applications across Natural Language Processing and Computer Vision tasks. However, fine-tuning all pre-trained model parameters becomes impractical as the model size and number of tasks increase. Parameter-efficient transfer learning (PETL) methods aim to address these challenges. While effective in reducing the number of trainable parameters, PETL methods still require significant energy and computational resources to fine-tune. In this paper, we introduce \textbf{RE}current \textbf{AD}aption (READ) -- a lightweight and memory-efficient fine-tuning method -- to overcome the limitations of the current PETL approaches. Specifically, READ inserts a small RNN network alongside the backbone model so that the model does not have to back-propagate through the large backbone network. Through comprehensive empirical evaluation of the GLUE benchmark, we demonstrate READ can achieve a $56\%$ reduction in the training memory consumption and an $84\%$ reduction in the GPU energy usage while retraining high model quality compared to full-tuning. Additionally, the model size of READ does not grow with the backbone model size, making it a highly scalable solution for fine-tuning large Transformers.

cs.LG↗

arXiv2024

OmniGenBench: Automating Large-scale in-silico Benchmarking for Genomic Foundation Models

The advancements in artificial intelligence in recent years, such as Large Language Models (LLMs), have fueled expectations for breakthroughs in genomic foundation models (GFMs). The code of nature, hidden in diverse genomes since the very beginning of life's evolution, holds immense potential for impacting humans and ecosystems through genome modeling. Recent breakthroughs in GFMs, such as Evo, have attracted significant investment and attention to genomic modeling, as they address long-standing challenges and transform in-silico genomic studies into automated, reliable, and efficient paradigms. In the context of this flourishing era of consecutive technological revolutions in genomics, GFM studies face two major challenges: the lack of GFM benchmarking tools and the absence of open-source software for diverse genomics. These challenges hinder the rapid evolution of GFMs and their wide application in tasks such as understanding and synthesizing genomes, problems that have persisted for decades. To address these challenges, we introduce GFMBench, a framework dedicated to GFM-oriented benchmarking. GFMBench standardizes benchmark suites and automates benchmarking for a wide range of open-source GFMs. It integrates millions of genomic sequences across hundreds of genomic tasks from four large-scale benchmarks, democratizing GFMs for a wide range of in-silico genomic applications. Additionally, GFMBench is released as open-source software, offering user-friendly interfaces and diverse tutorials, applicable for AutoBench and complex tasks like RNA design and structure prediction. To facilitate further advancements in genome modeling, we have launched a public leaderboard showcasing the benchmark performance derived from AutoBench. GFMBench represents a step toward standardizing GFM benchmarking and democratizing GFM applications.

q-bio.GN↗