arXiv subjects

Weiping Li

Publications and source records attributed to Weiping Li.

At least 37 records · Page 2Linked to original sources

arXiv2025

Mitigating Hallucinations on Object Attributes using Multiview Images and Negative Instructions

Current popular Large Vision-Language Models (LVLMs) are suffering from Hallucinations on Object Attributes (HoOA), leading to incorrect determination of fine-grained attributes in the input images. Leveraging significant advancements in 3D generation from a single image, this paper proposes a novel method to mitigate HoOA in LVLMs. This method utilizes multiview images sampled from generated 3D representations as visual prompts for LVLMs, thereby providing more visual information from other viewpoints. Furthermore, we observe the input order of multiple multiview images significantly affects the performance of LVLMs. Consequently, we have devised Multiview Image Augmented VLM (MIAVLM), incorporating a Multiview Attributes Perceiver (MAP) submodule capable of simultaneously eliminating the influence of input image order and aligning visual information from multiview images with Large Language Models (LLMs). Besides, we designed and employed negative instructions to mitigate LVLMs' bias towards ``Yes" responses. Comprehensive experiments demonstrate the effectiveness of our method.

cs.CV↗

arXiv2024

Order Matters: Exploring Order Sensitivity in Multimodal Large Language Models

Multimodal Large Language Models (MLLMs) utilize multimodal contexts consisting of text, images, or videos to solve various multimodal tasks. However, we find that changing the order of multimodal input can cause the model's performance to fluctuate between advanced performance and random guessing. This phenomenon exists in both single-modality (text-only or image-only) and mixed-modality (image-text-pair) contexts. Furthermore, we demonstrate that popular MLLMs pay special attention to certain multimodal context positions, particularly the beginning and end. Leveraging this special attention, we place key video frames and important image/text content in special positions within the context and submit them to the MLLM for inference. This method results in average performance gains of 14.7% for video-caption matching and 17.8% for visual question answering tasks. Additionally, we propose a new metric, Position-Invariant Accuracy (PIA), to address order bias in MLLM evaluation. Our research findings contribute to a better understanding of Multi-Modal In-Context Learning (MMICL) and provide practical strategies for enhancing MLLM performance without increasing computational costs.

cs.AI↗

arXiv2024

Supportiveness-based Knowledge Rewriting for Retrieval-augmented Language Modeling

Retrieval-augmented language models (RALMs) have recently shown great potential in mitigating the limitations of implicit knowledge in LLMs, such as untimely updating of the latest expertise and unreliable retention of long-tail knowledge. However, since the external knowledge base, as well as the retriever, can not guarantee reliability, potentially leading to the knowledge retrieved not being helpful or even misleading for LLM generation. In this paper, we introduce Supportiveness-based Knowledge Rewriting (SKR), a robust and pluggable knowledge rewriter inherently optimized for LLM generation. Specifically, we introduce the novel concept of "supportiveness"--which represents how effectively a knowledge piece facilitates downstream tasks--by considering the perplexity impact of augmented knowledge on the response text of a white-box LLM. Based on knowledge supportiveness, we first design a training data curation strategy for our rewriter model, effectively identifying and filtering out poor or irrelevant rewrites (e.g., with low supportiveness scores) to improve data efficacy. We then introduce the direct preference optimization (DPO) algorithm to align the generated rewrites to optimal supportiveness, guiding the rewriter model to summarize augmented content that better improves the final response. Comprehensive evaluations across six popular knowledge-intensive tasks and four LLMs have demonstrated the effectiveness and superiority of SKR. With only 7B parameters, SKR has shown better knowledge rewriting capability over GPT-4, the current state-of-the-art general-purpose LLM.

cs.CL↗

arXiv2023

Joint Event Extraction via Structural Semantic Matching

Event Extraction (EE) is one of the essential tasks in information extraction, which aims to detect event mentions from text and find the corresponding argument roles. The EE task can be abstracted as a process of matching the semantic definitions and argument structures of event types with the target text. This paper encodes the semantic features of event types and makes structural matching with target text. Specifically, Semantic Type Embedding (STE) and Dynamic Structure Encoder (DSE) modules are proposed. Also, the Joint Structural Semantic Matching (JSSM) model is built to jointly perform event detection and argument extraction tasks through a bidirectional attention layer. The experimental results on the ACE2005 dataset indicate that our model achieves a significant performance improvement

cs.CL↗

arXiv2023

NVTC: Nonlinear Vector Transform Coding

In theory, vector quantization (VQ) is always better than scalar quantization (SQ) in terms of rate-distortion (R-D) performance. Recent state-of-the-art methods for neural image compression are mainly based on nonlinear transform coding (NTC) with uniform scalar quantization, overlooking the benefits of VQ due to its exponentially increased complexity. In this paper, we first investigate on some toy sources, demonstrating that even if modern neural networks considerably enhance the compression performance of SQ with nonlinear transform, there is still an insurmountable chasm between SQ and VQ. Therefore, revolving around VQ, we propose a novel framework for neural image compression named Nonlinear Vector Transform Coding (NVTC). NVTC solves the critical complexity issue of VQ through (1) a multi-stage quantization strategy and (2) nonlinear vector transforms. In addition, we apply entropy-constrained VQ in latent space to adaptively determine the quantization boundaries for joint rate-distortion optimization, which improves the performance both theoretically and experimentally. Compared to previous NTC approaches, NVTC demonstrates superior rate-distortion performance, faster decoding speed, and smaller model size. Our code is available at https://github.com/USTC-IMCL/NVTC

cs.CV↗

arXiv2023

Region Normalization for Image Inpainting

Feature Normalization (FN) is an important technique to help neural network training, which typically normalizes features across spatial dimensions. Most previous image inpainting methods apply FN in their networks without considering the impact of the corrupted regions of the input image on normalization, e.g. mean and variance shifts. In this work, we show that the mean and variance shifts caused by full-spatial FN limit the image inpainting network training and we propose a spatial region-wise normalization named Region Normalization (RN) to overcome the limitation. RN divides spatial pixels into different regions according to the input mask, and computes the mean and variance in each region for normalization. We develop two kinds of RN for our image inpainting network: (1) Basic RN (RN-B), which normalizes pixels from the corrupted and uncorrupted regions separately based on the original inpainting mask to solve the mean and variance shift problem; (2) Learnable RN (RN-L), which automatically detects potentially corrupted and uncorrupted regions for separate normalization, and performs global affine transformation to enhance their fusion. We apply RN-B in the early layers and RN-L in the latter layers of the network respectively. Experiments show that our method outperforms current state-of-the-art methods quantitatively and qualitatively. We further generalize RN to other inpainting networks and achieve consistent performance improvements. Our code is available at https://github.com/geekyutao/RN.

cs.CV↗

arXiv2023

Building a Modal-balanced BlockChain with Semantic Reconstruction

The current large blockchain systems (BTC Lightning network, Ethereum, etc.) are generally facing the problems of low persistence rates and high storage costs. Therefore, users tend to store single modal (textual) information on the existing blockchain systems. Inspired by semantic communication algorithms, this paper presents a new algorithm to solve the serious imbalance between textual and visual modals on blockchains. After semantic sampling of the original visual image, the resulting semantic text will be stored on the chain, and the end users can reconstruct a semantically similar image using the \textbf{R}elative \textbf{O}ptimal \textbf{S}emantic \textbf{I}sotope \textbf{S}election algorithm. Experiments on the DIV2K dataset show that the blockchain with our algorithm can achieve 430,000 times the storage capacity and 550,000 times the persistence rate for the original visual data with acceptable semantic information loss.

cs.MM↗

arXiv2022

High fusion computers: The IoTs, edges, data centers, and humans-in-the-loop as a computer

Emerging and future applications rely heavily upon systems consisting of Internet of Things (IoT), edges, data centers, and humans-in-the-loop. Significantly different from warehouse-scale computers that serve independent concurrent user requests, this new class of computer systems directly interacts with the physical world, considering humans an essential part and performing safety-critical and mission-critical operations; their computations have intertwined dependencies between not only adjacent execution loops but also actions or decisions triggered by IoTs, edge, datacenters, or humans-in-the-loop; the systems must first satisfy the accuracy metric in predicting, interpreting, or taking action before meeting the performance goal under different cases. This article argues we need a paradigm shift to reconstruct the IoTs, edges, data centers, and humans-in-the-loop as a computer rather than a distributed system. We coin a new term, high fusion computers (HFCs), to describe this class of systems. The fusion in the term has two implications: fusing IoTs, edges, data centers, and humans-in-the-loop as a computer, fusing the physical and digital worlds through HFC systems. HFC is a pivotal case of the open-source computer systems initiative. We laid out the challenges, plan, and call for uniting our community's wisdom and actions to address the HFC challenges. Everything, including the source code, will be publicly available from the project homepage: https://www.computercouncil.org/HFC/.

cs.DC↗

arXiv2022

Exploiting Hybrid Semantics of Relation Paths for Multi-hop Question Answering Over Knowledge Graphs

Answering natural language questions on knowledge graphs (KGQA) remains a great challenge in terms of understanding complex questions via multi-hop reasoning. Previous efforts usually exploit large-scale entity-related text corpora or knowledge graph (KG) embeddings as auxiliary information to facilitate answer selection. However, the rich semantics implied in off-the-shelf relation paths between entities is far from well explored. This paper proposes improving multi-hop KGQA by exploiting relation paths' hybrid semantics. Specifically, we integrate explicit textual information and implicit KG structural features of relation paths based on a novel rotate-and-scale entity link prediction framework. Extensive experiments on three existing KGQA datasets demonstrate the superiority of our method, especially in multi-hop scenarios. Further investigation confirms our method's systematical coordination between questions and relation paths to identify answer entities.

cs.CL↗

arXiv2022

Eliciting Knowledge from Pretrained Language Models for Prototypical Prompt Verbalizer

Recent advances on prompt-tuning cast few-shot classification tasks as a masked language modeling problem. By wrapping input into a template and using a verbalizer which constructs a mapping between label space and label word space, prompt-tuning can achieve excellent results in zero-shot and few-shot scenarios. However, typical prompt-tuning needs a manually designed verbalizer which requires domain expertise and human efforts. And the insufficient label space may introduce considerable bias into the results. In this paper, we focus on eliciting knowledge from pretrained language models and propose a prototypical prompt verbalizer for prompt-tuning. Labels are represented by prototypical embeddings in the feature space rather than by discrete words. The distances between the embedding at the masked position of input and prototypical embeddings are used as classification criterion. For zero-shot settings, knowledge is elicited from pretrained language models by a manually designed template to form initial prototypical embeddings. For few-shot settings, models are tuned to learn meaningful and interpretable prototypical embeddings. Our method optimizes models by contrastive learning. Extensive experimental results on several many-class text classification datasets with low-resource settings demonstrate the effectiveness of our approach compared with other verbalizer construction methods. Our implementation is available at https://github.com/Ydongd/prototypical-prompt-verbalizer.

cs.CL↗

arXiv2021

The Parameter Sensitivities of a Jump-diffusion Process in Basic Credit Risk Analysis

We detect the parameter sensitivities of bond pricing which is driven by a Brownian motion and a compound Poisson process as the discontinuous case in credit risk research. The strict mathematical deductions are given theoretically due to the explicit call price formula. Furthermore, we illustrate Matlab simulation to verify these conclusions.

q-fin.MF↗

arXiv2021

Pricing S&P 500 Index Options with Lévy Jumps

We analyze various jumps for Heston model, non-IID model and three Lévy jump models for S&P 500 index options. The Lévy jump for the S&P 500 index options is inevitable from empirical studies. We estimate parameters from in-sample pricing through SSE for the BS, SV, SVJ, non-IID and Lévy (GH, NIG, CGMY) models by the method of Bakshi et al. (1997), and utilize them for out-of-sample pricing and compare these models. The sensitivities of the call option pricing for the Lévy models with respect to parameters are presented. Empirically, we show that the NIG model, SV and SVJ models with estimated volatilities outperform other models for both in-sample and out-of-sample periods. Using the in-sample optimized parameters, we find that the NIG model has the least SSE and outperforms the rest models on one-day prediction.

q-fin.MF↗

arXiv2021

The number of solutions of diagonal cubic equations over finite fields

Let $\mathbb{F}_q$ be a finite field of $q=p^k$ elements. For any $z\in \mathbb{F}_q$, let $A_n(z)$ and $B_n(z)$ denote the number of solutions of the equations $x_1^3+x_2^3+\cdots+x_n^3=z$ and $x_1^3+x_2^3+\cdots+x_n^3+zx_{n+1}^3=0$ respectively. Recently, using the generator of $\mathbb{F}^{\ast}_q$, Hong and Zhu gave the generating functions $\sum_{n=1}^{\infty}A_n(z)x^n$ and $\sum_{n=1}^{\infty}B_n(z)x^n$. In this paper, we give the generating functions $\sum_{n=1}^{\infty}A_n(z)x^n$ and $\sum_{n=1}^{\infty}B_n(z)x^n$ immediately by the coefficient $z$. Moreover, we gave the formulas of the number of solutions of equation $a_1x_1^3+a_2x_2^3+a_3x_3^3=0$ and our formulas are immediately determined by the coefficients $a_1,a_2$ and $a_3$. These extend and improve earlier results.

math.NT↗

arXiv2020

Sequential Reinforced 360-Degree Video Adaptive Streaming with Cross-user Attentive Network

In the tile-based 360-degree video streaming, predicting user's future viewpoints and developing adaptive bitrate (ABR) algorithms are essential for optimizing user's quality of experience (QoE). Traditional single-user based viewpoint prediction methods fail to achieve good performance in long-term prediction, and the recently proposed reinforcement learning (RL) based ABR schemes applied in traditional video streaming can not be directly applied in the tile-based 360-degree video streaming due to the exponential action space. Therefore, we propose a sequential reinforced 360-degree video streaming scheme with cross-user attentive network. Firstly, considering different users may have the similar viewing preference on the same video, we propose a cross-user attentive network (CUAN), boosting the performance of long-term viewpoint prediction by selectively utilizing cross-user information. Secondly, we propose a sequential RL-based (360SRL) ABR approach, transforming action space size of each decision step from exponential to linear via introducing a sequential decision structure. We evaluate the proposed CUAN and 360SRL using trace-driven experiments and experimental results demonstrate that CUAN and 360SRL outperform existing viewpoint prediction and ABR approaches with a noticeable margin.

cs.MM↗

arXiv2020

Blind Quality Assessment for Image Superresolution Using Deep Two-Stream Convolutional Networks

Numerous image superresolution (SR) algorithms have been proposed for reconstructing high-resolution (HR) images from input images with lower spatial resolutions. However, effectively evaluating the perceptual quality of SR images remains a challenging research problem. In this paper, we propose a no-reference/blind deep neural network-based SR image quality assessor (DeepSRQ). To learn more discriminative feature representations of various distorted SR images, the proposed DeepSRQ is a two-stream convolutional network including two subcomponents for distorted structure and texture SR images. Different from traditional image distortions, the artifacts of SR images cause both image structure and texture quality degradation. Therefore, we choose the two-stream scheme that captures different properties of SR inputs instead of directly learning features from one image stream. Considering the human visual system (HVS) characteristics, the structure stream focuses on extracting features in structural degradations, while the texture stream focuses on the change in textural distributions. In addition, to augment the training data and ensure the category balance, we propose a stride-based adaptive cropping approach for further improvement. Experimental results on three publicly available SR image quality databases demonstrate the effectiveness and generalization ability of our proposed DeepSRQ method compared with state-of-the-art image quality assessment algorithms.

eess.IV↗

arXiv2020

Prior-enlightened and Motion-robust Video Deblurring

Various blur distortions in video will cause negative impact on both human viewing and video-based applications, which makes motion-robust deblurring methods urgently needed. Most existing works have strong dataset dependency and limited generalization ability in handling challenging scenarios, like blur in low contrast or severe motion areas, and non-uniform blur. Therefore, we propose a PRiOr-enlightened and MOTION-robust video deblurring model (PROMOTION) suitable for challenging blurs. On the one hand, we use 3D group convolution to efficiently encode heterogeneous prior information, explicitly enhancing the scenes' perception while mitigating the output's artifacts. On the other hand, we design the priors representing blur distribution, to better handle non-uniform blur in spatio-temporal domain. Besides the classical camera shake caused global blurry, we also prove the generalization for the downstream task suffering from local blur. Extensive experiments demonstrate we can achieve the state-of-the-art performance on well-known REDS and GoPro datasets, and bring machine task gain.

cs.CV↗

arXiv2020

Learned Fast HEVC Intra Coding

In High Efficiency Video Coding (HEVC), excellent rate-distortion (RD) performance is achieved in part by having a flexible quadtree coding unit (CU) partition and a large number of intra-prediction modes. Such an excellent RD performance is achieved at the expense of much higher computational complexity. In this paper, we propose a learned fast HEVC intra coding (LFHI) framework taking into account the comprehensive factors of fast intra coding to reach an improved configurable tradeoff between coding performance and computational complexity. First, we design a low-complex shallow asymmetric-kernel CNN (AK-CNN) to efficiently extract the local directional texture features of each block for both fast CU partition and fast intra-mode decision. Second, we introduce the concept of the minimum number of RDO candidates (MNRC) into fast mode decision, which utilizes AK-CNN to predict the minimum number of best candidates for RDO calculation to further reduce the computation of intra-mode selection. Third, an evolution optimized threshold decision (EOTD) scheme is designed to achieve configurable complexity-efficiency tradeoffs. Finally, we propose an interpolation-based prediction scheme that allows for our framework to be generalized to all quantization parameters (QPs) without the need for training the network on each QP. The experimental results demonstrate that the LFHI framework has a high degree of parallelism and achieves a much better complexity-efficiency tradeoff, achieving up to 75.2% intra-mode encoding complexity reduction with negligible rate-distortion performance degradation, superior to the existing fast intra-coding schemes.

eess.IV↗

arXiv2019

Learned Scalable Image Compression with Bidirectional Context Disentanglement Network

In this paper, we propose a learned scalable/progressive image compression scheme based on deep neural networks (DNN), named Bidirectional Context Disentanglement Network (BCD-Net). For learning hierarchical representations, we first adopt bit-plane decomposition to decompose the information coarsely before the deep-learning-based transformation. However, the information carried by different bit-planes is not only unequal in entropy but also of different importance for reconstruction. We thus take the hidden features corresponding to different bit-planes as the context and design a network topology with bidirectional flows to disentangle the contextual information for more effective compressed representations. Our proposed scheme enables us to obtain the compressed codes with scalable rates via a one-pass encoding-decoding. Experiment results demonstrate that our proposed model outperforms the state-of-the-art DNN-based scalable image compression methods in both PSNR and MS-SSIM metrics. In addition, our proposed model achieves higher performance in MS-SSIM metric than conventional scalable image codecs. Effectiveness of our technical components is also verified through sufficient ablation experiments.

cs.MM↗