Search Results for author: Jianwei Niu

Found 31 papers, 12 papers with code

Explore Better Relative Position Embeddings from Encoding Perspective for Transformer Models

1 code implementation EMNLP 2021 Anlin Qu, Jianwei Niu, Shasha Mo

Relative position embedding (RPE) is a successful method to explicitly and efficaciously encode position information into Transformer models.


Fine-grained Factual Consistency Assessment for Abstractive Summarization Models

no code implementations EMNLP 2021 Sen Zhang, Jianwei Niu, Chuyuan Wei

Fact consistency assessment requires the reasoning capability to find subtle clues to identify whether a model-generated summary is consistent with the original document.

Abstractive Text Summarization Sentence

CETA: A Consensus Enhanced Training Approach for Denoising in Distantly Supervised Relation Extraction

1 code implementation COLING 2022 Ruri Liu, Shasha Mo, Jianwei Niu, Shengda Fan

This paper proposes a sentence-level DSRE method beyond typical instance selection approaches by preventing samples from falling into the wrong classification space on the feature space.

Classification Denoising +4

Key Mention Pairs Guided Document-Level Relation Extraction

no code implementations COLING 2022 Feng Jiang, Jianwei Niu, Shasha Mo, Shengda Fan

To this end, we propose a novel DocRE model called Key Mention pairs Guided Relation Extractor (KMGRE) to directly model mention-level relations, containing two modules: a mention-level relation extractor and a key instance classifier.

Document-level Relation Extraction Relation

A Physical Model-Guided Framework for Underwater Image Enhancement and Depth Estimation

no code implementations5 Jul 2024 Dazhao Du, Enhan Li, Lingyu Si, Fanjiang Xu, Jianwei Niu, Fuchun Sun

DDM includes three well-designed sub-networks to accurately estimate various imaging parameters: a veiling light estimation sub-network, a factors estimation sub-network, and a depth estimation sub-network.

Depth Estimation UIE

Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-Rank Decomposition

no code implementations28 Jun 2024 Xinghao Wu, Xuefeng Liu, Jianwei Niu, Haolin Wang, Shaojie Tang, Guogang Zhu, Hao Su

To address data heterogeneity, the key strategy of Personalized Federated Learning (PFL) is to decouple general knowledge (shared among clients) and client-specific knowledge, as the latter can have a negative impact on collaboration if not removed.

General Knowledge Personalized Federated Learning

Estimating before Debiasing: A Bayesian Approach to Detaching Prior Bias in Federated Semi-Supervised Learning

1 code implementation30 May 2024 Guogang Zhu, Xuefeng Liu, Xinghao Wu, Shaojie Tang, Chao Tang, Jianwei Niu, Hao Su

Federated Semi-Supervised Learning (FSSL) leverages both labeled and unlabeled data on clients to collaboratively train a model. In FSSL, the heterogeneous data can introduce prediction bias into the model, causing the model's prediction to skew towards some certain classes.

Temporal Scaling Law for Large Language Models

no code implementations27 Apr 2024 Yizhe Xiong, Xiansheng Chen, Xin Ye, Hui Chen, Zijia Lin, Haoran Lian, Zhenpeng Su, Jianwei Niu, Guiguang Ding

In this paper, we propose the novel concept of Temporal Scaling Law, studying how the test loss of an LLM evolves as the training steps scale up.


End-To-End Underwater Video Enhancement: Dataset and Model

no code implementations18 Mar 2024 Dazhao Du, Enhan Li, Lingyu Si, Fanjiang Xu, Jianwei Niu

To fill this gap, we construct the Synthetic Underwater Video Enhancement (SUVE) dataset, comprising 840 diverse underwater-style videos paired with ground-truth reference videos.

Image Enhancement Video Enhancement

Joint Attention-Guided Feature Fusion Network for Saliency Detection of Surface Defects

no code implementations5 Feb 2024 Xiaoheng Jiang, Feng Yan, Yang Lu, Ke Wang, Shuai Guo, Tianzhu Zhang, Yanwei Pang, Jianwei Niu, Mingliang Xu

To address these issues, we propose a joint attention-guided feature fusion network (JAFFNet) for saliency detection of surface defects based on the encoder-decoder network.

Defect Detection Saliency Detection

NID-SLAM: Neural Implicit Representation-based RGB-D SLAM in dynamic environments

no code implementations2 Jan 2024 Ziheng Xu, Jianwei Niu, Qingfeng Li, Tao Ren, Chen Chen

In this paper we present NID-SLAM, which significantly improves the performance of neural SLAM in dynamic environments.

UIEDP:Underwater Image Enhancement with Diffusion Prior

no code implementations11 Dec 2023 Dazhao Du, Enhan Li, Lingyu Si, Fanjiang Xu, Jianwei Niu, Fuchun Sun

To address this issue, we propose UIE with Diffusion Prior (UIEDP), a novel framework treating UIE as a posterior distribution sampling process of clear images conditioned on degraded underwater inputs.

Image Generation No-Reference Image Quality Assessment +1

Bold but Cautious: Unlocking the Potential of Personalized Federated Learning through Cautiously Aggressive Collaboration

1 code implementation ICCV 2023 Xinghao Wu, Xuefeng Liu, Jianwei Niu, Guogang Zhu, Shaojie Tang

The reasoning behind this approach is understandable, as localizing parameters that are easily influenced by non-IID data can prevent the potential negative effect of collaboration.

Personalized Federated Learning

Take Your Pick: Enabling Effective Personalized Federated Learning within Low-dimensional Feature Space

no code implementations26 Jul 2023 Guogang Zhu, Xuefeng Liu, Shaojie Tang, Jianwei Niu, Xinghao Wu, Jiaxing Shen

FedPick achieves PFL in the low-dimensional feature space by selecting task-relevant features adaptively for each client from the features generated by the global encoder based on its local data distribution.

Personalized Federated Learning

3Deformer: A Common Framework for Image-Guided Mesh Deformation

no code implementations19 Jul 2023 Hao Su, Xuefeng Liu, Jianwei Niu, Ji Wan, Xinghao Wu

Unlike these studies, our 3Deformer is a non-training and common framework, which only requires supervision of readily-available semantic images, and is compatible with editing various objects unlimited by datasets.

Unlocking the Potential of Federated Learning for Deeper Models

no code implementations5 Jun 2023 Haolin Wang, Xuefeng Liu, Jianwei Niu, Shaojie Tang, Jiaxing Shen

Our further investigation shows that the decline is due to the continuous accumulation of dissimilarities among client models during the layer-by-layer back-propagation process, which we refer to as "divergence accumulation."

Federated Learning

Convex Augmentation for Total Variation Based Phase Retrieval

no code implementations21 Apr 2022 Jianwei Niu, Hok Shing Wong, Tieyong Zeng

Phase retrieval is an important problem with significant physical and industrial applications.


WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit

3 code implementations29 Mar 2022 BinBin Zhang, Di wu, Zhendong Peng, Xingchen Song, Zhuoyuan Yao, Hang Lv, Lei Xie, Chao Yang, Fuping Pan, Jianwei Niu

Recently, we made available WeNet, a production-oriented end-to-end speech recognition toolkit, which introduces a unified two-pass (U2) framework and a built-in runtime to address the streaming and non-streaming decoding modes in a single model.

Decoder Language Modelling +2

MARVEL: Raster Manga Vectorization via Primitive-wise Deep Reinforcement Learning

1 code implementation10 Oct 2021 Hao Su, Jianwei Niu, Xuefeng Liu, Jiahe Cui, Ji Wan

Manga is a fashionable Japanese-style comic form that is composed of black-and-white strokes and is generally displayed as raster images on digital devices.

reinforcement-learning Reinforcement Learning (RL) +1

You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection

2 code implementations NeurIPS 2021 Yuxin Fang, Bencheng Liao, Xinggang Wang, Jiemin Fang, Jiyang Qi, Rui Wu, Jianwei Niu, Wenyu Liu

Can Transformer perform 2D object- and region-level recognition from a pure sequence-to-sequence perspective with minimal knowledge about the 2D spatial structure?

Object object-detection +1

Visformer: The Vision-friendly Transformer

5 code implementations ICCV 2021 Zhengsu Chen, Lingxi Xie, Jianwei Niu, Xuefeng Liu, Longhui Wei, Qi Tian

The past year has witnessed the rapid development of applying the Transformer module to vision problems.

Image Classification

SelectScale: Mining More Patterns from Images via Selective and Soft Dropout

no code implementations30 Nov 2020 Zhengsu Chen, Jianwei Niu, Xuefeng Liu, Shaojie Tang

Instead of randomly dropping units, SelectScale selects the important features in networks and adjusts them during training.

ACSC: Automatic Calibration for Non-repetitive Scanning Solid-State LiDAR and Camera Systems

1 code implementation17 Nov 2020 Jiahe Cui, Jianwei Niu, Zhenchao Ouyang, Yunxiang He, Dian Liu

Recently, the rapid development of Solid-State LiDAR (SSL) enables low-cost and efficient obtainment of 3D point clouds from the environment, which has inspired a large quantity of studies and applications.

3D Geometry Perception Camera Auto-Calibration

An End-to-end Method for Producing Scanning-robust Stylized QR Codes

no code implementations16 Nov 2020 Hao Su, Jianwei Niu, Xuefeng Liu, Qingfeng Li, Ji Wan, Mingliang Xu, Tao Ren

Quick Response (QR) code is one of the most worldwide used two-dimensional codes.~Traditional QR codes appear as random collections of black-and-white modules that lack visual semantics and aesthetic elements, which inspires the recent works to beautify the appearances of QR codes.

Style Transfer

A Survey on Incorporating Domain Knowledge into Deep Learning for Medical Image Analysis

no code implementations25 Apr 2020 Xiaozheng Xie, Jianwei Niu, Xuefeng Liu, Zhengsu Chen, Shaojie Tang, Shui Yu

Although deep learning models like CNNs have achieved great success in medical image analysis, the small size of medical datasets remains a major bottleneck in this area.

Anomaly Detection Organ Segmentation +1

MangaGAN: Unpaired Photo-to-Manga Translation Based on The Methodology of Manga Drawing

no code implementations22 Apr 2020 Hao Su, Jianwei Niu, Xuefeng Liu, Qingfeng Li, Jiahe Cui, Ji Wan

Manga is a world popular comic form originated in Japan, which typically employs black-and-white stroke lines and geometric exaggeration to describe humans' appearances, poses, and actions.


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