Search Results for author: Xin Lu

Found 71 papers, 29 papers with code

Learning Joint ID-Textual Representation for ID-Preserving Image Synthesis

no code implementations19 Apr 2025 Zichuan Liu, Liming Jiang, Qing Yan, Yumin Jia, Hao Kang, Xin Lu

Given a reference face and a text prompt, FaceCLIP produces a unified representation that encodes both identity and text, which conditions a base diffusion model to generate images that are identity-consistent and text-aligned.

Image Generation

InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity

1 code implementation20 Mar 2025 Liming Jiang, Qing Yan, Yumin Jia, Zichuan Liu, Hao Kang, Xin Lu

Achieving flexible and high-fidelity identity-preserved image generation remains formidable, particularly with advanced Diffusion Transformers (DiTs) like FLUX.

Image Generation

Prediction Interval Construction Method for Electricity Prices

no code implementations14 Jan 2025 Xin Lu

Accurate prediction of electricity prices plays an essential role in the electricity market.

Generative Adversarial Network Prediction +1

Promoting Shared Energy Storage Aggregation among High Price-Tolerance Prosumer: An Incentive Deposit and Withdrawal Service

no code implementations9 Jan 2025 Xin Lu, Jing Qiu, Cuo Zhang, Gang Lei, Jianguo Zhu

To incentivize these high price-tolerance residential prosumers to participate in SES, a novel SES aggregation framework is proposed, which does not require prosumers to take additional actions and allows them to maintain existing energy storage patterns.

Deep Reinforcement Learning

Prompt-Guided Mask Proposal for Two-Stage Open-Vocabulary Segmentation

no code implementations13 Dec 2024 Yu-Jhe Li, Xinyang Zhang, Kun Wan, Lantao Yu, Ajinkya Kale, Xin Lu

To overcome this challenge, existing methods often use multi-modal models like CLIP, which combine image and text features in a shared embedding space to bridge the gap between limited and extensive vocabulary recognition, resulting in a two-stage approach: In the first stage, a mask generator takes an input image to generate mask proposals, and the in the second stage the target mask is picked based on the query.

Multi-object Tracking by Detection and Query: an efficient end-to-end manner

no code implementations9 Nov 2024 Shukun Jia, Yichao Cao, Feng Yang, Xin Lu, Xiaobo Lu

Multi-object tracking is advancing through two dominant paradigms: traditional tracking by detection and newly emerging tracking by query.

Multi-Object Tracking

GSpect: Spectral Filtering for Cross-Scale Graph Classification

no code implementations31 Aug 2024 XiaoYu Zhang, Wenchuan Yang, Jiawei Feng, Bitao Dai, Tianci Bu, Xin Lu

Compared with other methods, we use graph wavelet neural networks for the convolution layer of the model, which aggregates multi-scale messages to generate graph representations.

Graph Classification

PriorMapNet: Enhancing Online Vectorized HD Map Construction with Priors

no code implementations16 Aug 2024 Rongxuan Wang, Xin Lu, Xiaoyang Liu, Xiaoyi Zou, Tongyi Cao, Ying Li

To address this issue, we introduce PriorMapNet to enhance online vectorized HD map construction with priors.

Autonomous Driving Decoder +1

Intermittent Semi-working Mask: A New Masking Paradigm for LLMs

no code implementations1 Aug 2024 Mingcong Lu, Jiangcai Zhu, Wang Hao, Zheng Li, Shusheng Zhang, Kailai Shao, Chao Chen, Nan Li, Feng Wang, Xin Lu

In this way, ISM is able to maintain the high quality of prefix LLM and low generation latency of causal LLM, simultaneously.

In-Context Learning

Enhancing context models for point cloud geometry compression with context feature residuals and multi-loss

no code implementations11 Jul 2024 Chang Sun, Hui Yuan, Shuai Li, Xin Lu, Raouf Hamzaoui

In point cloud geometry compression, context models usually use the one-hot encoding of node occupancy as the label, and the cross-entropy between the one-hot encoding and the probability distribution predicted by the context model as the loss function.

Enhancing octree-based context models for point cloud geometry compression with attention-based child node number prediction

no code implementations11 Jul 2024 Chang Sun, Hui Yuan, Xiaolong Mao, Xin Lu, Raouf Hamzaoui

The proposed module can predict the number of occupied child nodes and map it into an 8- dimensional vector to assist the context model in predicting the probability distribution of the occupancy of the current node for efficient entropy coding.

SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters

1 code implementation2 Jul 2024 Yan Yang, Zeguan Xiao, Xin Lu, Hongru Wang, Xuetao Wei, Hailiang Huang, Guanhua Chen, Yun Chen

The widespread applications of large language models (LLMs) have brought about concerns regarding their potential misuse.

Red Teaming Safety Alignment

TraceNet: Segment one thing efficiently

no code implementations21 Jun 2024 Mingyuan Wu, Zichuan Liu, Haozhen Zheng, Hongpeng Guo, Bo Chen, Xin Lu, Klara Nahrstedt

To address this, we propose and formulate a one tap driven single instance segmentation task that segments a single instance selected by a user via a positive tap.

Instance Segmentation Interactive Segmentation +2

Non-autoregressive Personalized Bundle Generation

no code implementations11 Jun 2024 Wenchuan Yang, Cheng Yang, Jichao Li, Yuejin Tan, Xin Lu, Chuan Shi

The personalized bundle generation problem, which aims to create a preferred bundle for user from numerous candidate items, receives increasing attention in recommendation.

Decoder Graph Neural Network +1

Network Structure Governs Drosophila Brain Functionality

no code implementations26 Apr 2024 XiaoYu Zhang, Pengcheng Yang, Jiawei Feng, Qiang Luo, Wei Lin, Xin Lu

The results revealed that even with rudimentary neuronal activation mechanisms, models grounded in real neural network structures can generate activation patterns strikingly similar to those observed in the actual brain.

A Dual-domain Regularization Method for Ring Artifact Removal of X-ray CT

no code implementations13 Mar 2024 Hongyang Zhu, Xin Lu, Yanwei Qin, Xinran Yu, Tianjiao Sun, Yunsong Zhao

The proposed model corrects the vertical stripe artifacts on the sinogram by innovatively updating the response inconsistency compensation coefficients of detector units, which is achieved by employing the group sparse constraint and the projection-view direction sparse constraint on the stripe artifacts.

Diagnostic

How does Architecture Influence the Base Capabilities of Pre-trained Language Models? A Case Study Based on FFN-Wider and MoE Transformers

no code implementations4 Mar 2024 Xin Lu, Yanyan Zhao, Bing Qin, Liangyu Huo, Qing Yang, Dongliang Xu

Through analysis, we found the contribution ratio of Multi-Head Attention (a combination function) to pre-trained language modeling is a key factor affecting base capabilities.

Few-Shot Learning Language Modeling +3

Vanilla Transformers are Transfer Capability Teachers

no code implementations4 Mar 2024 Xin Lu, Yanyan Zhao, Bing Qin

However, studies have indicated that MoE Transformers underperform vanilla Transformers in many downstream tasks, significantly diminishing the practical value of MoE models.

Computational Efficiency Mixture-of-Experts

Dr. Bokeh: DiffeRentiable Occlusion-aware Bokeh Rendering

no code implementations CVPR 2024 Yichen Sheng, Zixun Yu, Lu Ling, Zhiwen Cao, Xuaner Zhang, Xin Lu, Ke Xian, Haiting Lin, Bedrich Benes

Dr. Bokeh then takes the layered representation and user-defined lens parameters to render photo-realistic lens blur based on the novel occlusion-aware bokeh rendering method.

Attributes Grouping and Mining Hashing for Fine-Grained Image Retrieval

no code implementations10 Nov 2023 Xin Lu, Shikun Chen, Yichao Cao, Xin Zhou, Xiaobo Lu

To handle this limitation, we substitute convolutional descriptors for attention-guided features and propose an Attributes Grouping and Mining Hashing (AGMH), which groups and embeds the category-specific visual attributes in multiple descriptors to generate a comprehensive feature representation for efficient fine-grained image retrieval.

Diversity Image Retrieval +1

Data-Centric Financial Large Language Models

no code implementations7 Oct 2023 Zhixuan Chu, Huaiyu Guo, Xinyuan Zhou, Yijia Wang, Fei Yu, Hong Chen, Wanqing Xu, Xin Lu, Qing Cui, Longfei Li, Jun Zhou, Sheng Li

Large language models (LLMs) show promise for natural language tasks but struggle when applied directly to complex domains like finance.

Financial Analysis

Text2Layer: Layered Image Generation using Latent Diffusion Model

no code implementations19 Jul 2023 Xinyang Zhang, Wentian Zhao, Xin Lu, Jeff Chien

To achieve layered image generation, we train an autoencoder that is able to reconstruct layered images and train diffusion models on the latent representation.

Image Generation Image Segmentation +2

Is ChatGPT Equipped with Emotional Dialogue Capabilities?

no code implementations19 Apr 2023 Weixiang Zhao, Yanyan Zhao, Xin Lu, Shilong Wang, Yanpeng Tong, Bing Qin

This report presents a study on the emotional dialogue capability of ChatGPT, an advanced language model developed by OpenAI.

Dialogue Understanding Language Modeling +1

Detecting Temporal shape changes with the Euler Characteristic Transform

no code implementations21 Dec 2022 Lewis Marsh, Felix Y. Zhou, Xiao Qin, Xin Lu, Helen M. Byrne, Heather A. Harrington

Organoids are multi-cellular structures which are cultured in vitro from stem cells to resemble specific organs (e. g., brain, liver) in their three-dimensional composition.

Topological Data Analysis

Boosting Binary Neural Networks via Dynamic Thresholds Learning

no code implementations4 Nov 2022 Jiehua Zhang, Xueyang Zhang, Zhuo Su, Zitong Yu, Yanghe Feng, Xin Lu, Matti Pietikäinen, Li Liu

For ViTs, DyBinaryCCT presents the superiority of the convolutional embedding layer in fully binarized ViTs and achieves 56. 1% on the ImageNet dataset, which is nearly 9% higher than the baseline.

Binarization

Improving Long-tailed Object Detection with Image-Level Supervision by Multi-Task Collaborative Learning

1 code implementation11 Oct 2022 Bo Li, Yongqiang Yao, Jingru Tan, Xin Lu, Fengwei Yu, Ye Luo, Jianwei Lu

Specifically, there are an object detection task (consisting of an instance-classification task and a localization task) and an image-classification task in our framework, responsible for utilizing the two types of supervision.

Classification Contrastive Learning +4

Don't Lose Yourself! Empathetic Response Generation via Explicit Self-Other Awareness

1 code implementation8 Oct 2022 Weixiang Zhao, Yanyan Zhao, Xin Lu, Bing Qin

As a critical step to achieve human-like chatbots, empathetic response generation has attained increasing interests.

Empathetic Response Generation Response Generation

Neighbor Regularized Bayesian Optimization for Hyperparameter Optimization

no code implementations7 Oct 2022 Lei Cui, Yangguang Li, Xin Lu, Dong An, Fenggang Liu

Bayesian Optimization (BO) is a common solution to search optimal hyperparameters based on sample observations of a machine learning model.

Bayesian Optimization Hyperparameter Optimization

Multiscale methods for signal selection in single-cell data

1 code implementation15 Jun 2022 Renee S. Hoekzema, Lewis Marsh, Otto Sumray, Thomas M. Carroll, Xin Lu, Helen M. Byrne, Heather A. Harrington

Analysis of single-cell transcriptomics often relies on clustering cells and then performing differential gene expression (DGE) to identify genes that vary between these clusters.

feature selection

A Unified Model for Multi-class Anomaly Detection

1 code implementation8 Jun 2022 Zhiyuan You, Lei Cui, Yujun Shen, Kai Yang, Xin Lu, Yu Zheng, Xinyi Le

For example, when learning a unified model for 15 categories in MVTec-AD, we surpass the second competitor on the tasks of both anomaly detection (from 88. 1% to 96. 5%) and anomaly localization (from 89. 5% to 96. 8%).

Anomaly Localization model +2

Few-shot Object Counting with Similarity-Aware Feature Enhancement

1 code implementation22 Jan 2022 Zhiyuan You, Kai Yang, Wenhan Luo, Xin Lu, Lei Cui, Xinyi Le

This work studies the problem of few-shot object counting, which counts the number of exemplar objects (i. e., described by one or several support images) occurring in the query image.

Crowd Counting Object Counting

On Efficient Transformer-Based Image Pre-training for Low-Level Vision

1 code implementation19 Dec 2021 Wenbo Li, Xin Lu, Shengju Qian, Jiangbo Lu, Xiangyu Zhang, Jiaya Jia

Pre-training has marked numerous state of the arts in high-level computer vision, while few attempts have ever been made to investigate how pre-training acts in image processing systems.

Ranked #11 on Image Super-Resolution on Set5 - 2x upscaling (using extra training data)

Denoising Image Super-Resolution

Improving Image Restoration by Revisiting Global Information Aggregation

2 code implementations8 Dec 2021 Xiaojie Chu, Liangyu Chen, Chengpeng Chen, Xin Lu

Our TLC converts global operations to local ones only during inference so that they aggregate features within local spatial regions rather than the entire large images.

Color Image Denoising Deblurring +9

Dynamic Binary Neural Network by learning channel-wise thresholds

no code implementations8 Oct 2021 Jiehua Zhang, Zhuo Su, Yanghe Feng, Xin Lu, Matti Pietikäinen, Li Liu

The experimental results prove that our method is an effective and straightforward way to reduce information loss and enhance performance of BNNs.

HINet: Half Instance Normalization Network for Image Restoration

2 code implementations13 May 2021 Liangyu Chen, Xin Lu, Jie Zhang, Xiaojie Chu, Chengpeng Chen

Specifically, we present a novel block: Half Instance Normalization Block (HIN Block), to boost the performance of image restoration networks.

Deblurring Image Deblurring +3

RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features

1 code implementation CVPR 2021 Gang Zhang, Xin Lu, Jingru Tan, Jianmin Li, Zhaoxiang Zhang, Quanquan Li, Xiaolin Hu

In this work, we propose a new method called RefineMask for high-quality instance segmentation of objects and scenes, which incorporates fine-grained features during the instance-wise segmenting process in a multi-stage manner.

Instance Segmentation Semantic Segmentation +1

A Transition-based Parser for Unscoped Episodic Logical Forms

1 code implementation IWCS (ACL) 2021 Gene Louis Kim, Viet Duong, Xin Lu, Lenhart Schubert

"Episodic Logic:Unscoped Logical Form" (EL-ULF) is a semantic representation capturing predicate-argument structure as well as more challenging aspects of language within the Episodic Logic formalism.

Interplay between charge order and superconductivity in the kagome metal KV$_3$Sb$_5$

no code implementations22 Feb 2021 Feng Du, Shuaishuai Luo, Brenden R. Ortiz, Ye Chen, Weiyin Duan, Dongting Zhang, Xin Lu, Stephen D. Wilson, Yu Song, Huiqiu Yuan

Beyond $p\approx10$ GPa, a second superconducting dome emerges with maximum $T_{\rm c}\approx1. 0$ K at $p_{\rm c2}\approx22$ GPa, which becomes fully suppressed at $p\approx28$ GPa.

Superconductivity

Growth, Electronic Structure and Superconductivity of Ultrathin Epitaxial CoSi2 Films

no code implementations21 Jan 2021 Yuan Fang, Ding Wang, Peng Li, Hang Su, Tian Le, Yi Wu, Guo-Wei Yang, Hua-Li Zhang, Zhi-Guang Xiao, Yan-Qiu Sun, Si-Yuan Hong, Yan-Wu Xie, Huan-Hua Wang, Chao Cao, Xin Lu, Hui-Qiu Yuan, Yang Liu

We report growth, electronic structure and superconductivity of ultrathin epitaxial CoSi2 films on Si(111).

Mesoscale and Nanoscale Physics

Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection

2 code implementations CVPR 2021 Jingru Tan, Xin Lu, Gang Zhang, Changqing Yin, Quanquan Li

To address the problem of imbalanced gradients, we introduce a new version of equalization loss, called equalization loss v2 (EQL v2), a novel gradient guided reweighing mechanism that re-balances the training process for each category independently and equally.

Instance Segmentation Long-tailed Object Detection +2

An Iterative Emotion Interaction Network for Emotion Recognition in Conversations

no code implementations COLING 2020 Xin Lu, Yanyan Zhao, Yang Wu, Yijian Tian, Huipeng Chen, Bing Qin

We noticed that the gold emotion labels of the context utterances can provide explicit and accurate emotion interaction, but it is impossible to input gold labels at inference time.

Emotion Recognition in Conversation

MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object Detection

no code implementations ECCV 2020 Xin Lu, Quanquan Li, Buyu Li, Junjie Yan

In this paper, we propose MimicDet, a novel and efficient framework to train a one-stage detector by directly mimic the two-stage features, aiming to bridge the accuracy gap between one-stage and two-stage detectors.

object-detection Object Detection

Dirac quantum well engineering on the surface of topological insulator

no code implementations28 Jul 2020 Xin Lu, Mark-Oliver Goerbig

We investigate possible hybridization between these interface states as a function of the width of the topological material and of the characteristic interface size.

Mesoscale and Nanoscale Physics High Energy Physics - Theory Quantum Physics

Information Mandala: Statistical Distance Matrix with Clustering

no code implementations7 Jun 2020 Xin Lu

In machine learning, observation features are measured in a metric space to obtain their distance function for optimization.

Clustering Object Recognition

Grid R-CNN Plus: Faster and Better

2 code implementations13 Jun 2019 Xin Lu, Buyu Li, Yuxin Yue, Quanquan Li, Junjie Yan

Grid R-CNN is a well-performed objection detection framework.

Object Detection regression

A deep learning framework for quality assessment and restoration in video endoscopy

no code implementations15 Apr 2019 Sharib Ali, Felix Zhou, Adam Bailey, Barbara Braden, James East, Xin Lu, Jens Rittscher

Given the widespread use of endoscopy in different clinical applications, we contend that the robust and reliable identification of such artifacts and the automated restoration of corrupted video frames is a fundamental medical imaging problem.

Deblurring Image Restoration

Foreground-aware Image Inpainting

no code implementations CVPR 2019 Wei Xiong, Jiahui Yu, Zhe Lin, Jimei Yang, Xin Lu, Connelly Barnes, Jiebo Luo

We show that by such disentanglement, the contour completion model predicts reasonable contours of objects, and further substantially improves the performance of image inpainting.

Disentanglement Image Inpainting

Grid R-CNN

2 code implementations CVPR 2019 Xin Lu, Buyu Li, Yuxin Yue, Quanquan Li, Junjie Yan

This paper proposes a novel object detection framework named Grid R-CNN, which adopts a grid guided localization mechanism for accurate object detection.

Novel Object Detection Object +3

Contemplating Visual Emotions: Understanding and Overcoming Dataset Bias

no code implementations ECCV 2018 Rameswar Panda, Jianming Zhang, Haoxiang Li, Joon-Young Lee, Xin Lu, Amit K. Roy-Chowdhury

While machine learning approaches to visual emotion recognition offer great promise, current methods consider training and testing models on small scale datasets covering limited visual emotion concepts.

Emotion Recognition

Flow-Grounded Spatial-Temporal Video Prediction from Still Images

1 code implementation ECCV 2018 Yijun Li, Chen Fang, Jimei Yang, Zhaowen Wang, Xin Lu, Ming-Hsuan Yang

Existing video prediction methods mainly rely on observing multiple historical frames or focus on predicting the next one-frame.

Diversity Prediction +1

Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers

3 code implementations ICLR 2018 Jianbo Ye, Xin Lu, Zhe Lin, James Z. Wang

Model pruning has become a useful technique that improves the computational efficiency of deep learning, making it possible to deploy solutions in resource-limited scenarios.

Computational Efficiency

Generative Image Inpainting with Contextual Attention

28 code implementations CVPR 2018 Jiahui Yu, Zhe Lin, Jimei Yang, Xiaohui Shen, Xin Lu, Thomas S. Huang

Motivated by these observations, we propose a new deep generative model-based approach which can not only synthesize novel image structures but also explicitly utilize surrounding image features as references during network training to make better predictions.

Image Inpainting

Scene Parsing with Global Context Embedding

1 code implementation ICCV 2017 Wei-Chih Hung, Yi-Hsuan Tsai, Xiaohui Shen, Zhe Lin, Kalyan Sunkavalli, Xin Lu, Ming-Hsuan Yang

We present a scene parsing method that utilizes global context information based on both the parametric and non- parametric models.

Scene Parsing

Universal Style Transfer via Feature Transforms

15 code implementations NeurIPS 2017 Yijun Li, Chen Fang, Jimei Yang, Zhaowen Wang, Xin Lu, Ming-Hsuan Yang

The whitening and coloring transforms reflect a direct matching of feature covariance of the content image to a given style image, which shares similar spirits with the optimization of Gram matrix based cost in neural style transfer.

Image Reconstruction Style Transfer

Recurrent Multimodal Interaction for Referring Image Segmentation

1 code implementation ICCV 2017 Chenxi Liu, Zhe Lin, Xiaohui Shen, Jimei Yang, Xin Lu, Alan Yuille

In this paper we are interested in the problem of image segmentation given natural language descriptions, i. e. referring expressions.

Image Segmentation multimodal interaction +2

Diversified Texture Synthesis with Feed-forward Networks

no code implementations CVPR 2017 Yijun Li, Chen Fang, Jimei Yang, Zhaowen Wang, Xin Lu, Ming-Hsuan Yang

Recent progresses on deep discriminative and generative modeling have shown promising results on texture synthesis.

Diversity Texture Synthesis

High-Resolution Image Inpainting using Multi-Scale Neural Patch Synthesis

1 code implementation CVPR 2017 Chao Yang, Xin Lu, Zhe Lin, Eli Shechtman, Oliver Wang, Hao Li

Recent advances in deep learning have shown exciting promise in filling large holes in natural images with semantically plausible and context aware details, impacting fundamental image manipulation tasks such as object removal.

Image Inpainting Image Manipulation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.