Search Results for author: Hongtao Lu

Found 61 papers, 20 papers with code

Federated Multi-Task Learning on Non-IID Data Silos: An Experimental Study

no code implementations20 Feb 2024 Yuwen Yang, Yuxiang Lu, Suizhi Huang, Shalayiding Sirejiding, Hongtao Lu, Yue Ding

The innovative Federated Multi-Task Learning (FMTL) approach consolidates the benefits of Federated Learning (FL) and Multi-Task Learning (MTL), enabling collaborative model training on multi-task learning datasets.

Federated Learning Multi-Task Learning

Boosting Semi-Supervised 2D Human Pose Estimation by Revisiting Data Augmentation and Consistency Training

1 code implementation18 Feb 2024 Huayi Zhou, Mukun Luo, Fei Jiang, Yue Ding, Hongtao Lu

In this paper, we aim at boosting the accuracy of a pose estimator by excavating extra unlabeled images in a semi-supervised learning (SSL) way.

2D Human Pose Estimation Data Augmentation +1

Enhancing cross-domain detection: adaptive class-aware contrastive transformer

no code implementations24 Jan 2024 Ziru Zeng, Yue Ding, Hongtao Lu

Recently, the detection transformer has gained substantial attention for its inherent minimal post-processing requirement. However, this paradigm relies on abundant training data, yet in the context of the cross-domain adaptation, insufficient labels in the target domain exacerbate issues of class imbalance and model performance degradation. To address these challenges, we propose a novel class-aware cross domain detection transformer based on the adversarial learning and mean-teacher framework. First, considering the inconsistencies between the classification and regression tasks, we introduce an IoU-aware prediction branch and exploit the consistency of classification and location scores to filter and reweight pseudo labels. Second, we devise a dynamic category threshold refinement to adaptively manage model confidence. Third, to alleviate the class imbalance, an instance-level class-aware contrastive learning module is presented to encourage the generation of discriminative features for each class, particularly benefiting minority classes. Experimental results across diverse domain-adaptive scenarios validate our method's effectiveness in improving performance and alleviating class imbalance issues, which outperforms the state-of-the-art transformer based methods.

Contrastive Learning Domain Adaptation

PA-SAM: Prompt Adapter SAM for High-Quality Image Segmentation

1 code implementation23 Jan 2024 Zhaozhi Xie, Bochen Guan, Weihao Jiang, Muyang Yi, Yue Ding, Hongtao Lu, Lei Zhang

In this paper, we introduce a novel prompt-driven adapter into SAM, namely Prompt Adapter Segment Anything Model (PA-SAM), aiming to enhance the segmentation mask quality of the original SAM.

Image Segmentation Segmentation +1

ChangeNet: Multi-Temporal Asymmetric Change Detection Dataset

no code implementations29 Dec 2023 Deyi Ji, Siqi Gao, Mingyuan Tao, Hongtao Lu, Feng Zhao

The ChangeNet dataset is suitable for both binary change detection (BCD) and semantic change detection (SCD) tasks.

Change Detection

Towards Hetero-Client Federated Multi-Task Learning

no code implementations22 Nov 2023 Yuxiang Lu, Suizhi Huang, Yuwen Yang, Shalayiding Sirejiding, Yue Ding, Hongtao Lu

Moreover, we employ learnable Hyper Aggregation Weights for each client to customize personalized parameter updates.

Federated Learning Multi-Task Learning

Combining Past, Present and Future: A Self-Supervised Approach for Class Incremental Learning

no code implementations15 Nov 2023 Xiaoshuang Chen, Zhongyi Sun, Ke Yan, Shouhong Ding, Hongtao Lu

In detail, CPPF consists of a prototype clustering module (PC), an embedding space reserving module (ESR) and a multi-teacher distillation module (MTD).

Class Incremental Learning Incremental Learning

UNIDEAL: Curriculum Knowledge Distillation Federated Learning

no code implementations16 Sep 2023 Yuwen Yang, Chang Liu, Xun Cai, Suizhi Huang, Hongtao Lu, Yue Ding

Federated Learning (FL) has emerged as a promising approach to enable collaborative learning among multiple clients while preserving data privacy.

Federated Learning Knowledge Distillation

Prompt Guided Transformer for Multi-Task Dense Prediction

no code implementations28 Jul 2023 Yuxiang Lu, Shalayiding Sirejiding, Yue Ding, Chunlin Wang, Hongtao Lu

Task-conditional architecture offers advantage in parameter efficiency but falls short in performance compared to state-of-the-art multi-decoder methods.

Semantic Segmentation

Guided Patch-Grouping Wavelet Transformer with Spatial Congruence for Ultra-High Resolution Segmentation

no code implementations3 Jul 2023 Deyi Ji, Feng Zhao, Hongtao Lu

For the sake of high inference speed and low computation complexity, $\mathcal{T}$ partitions the original UHR image into patches and groups them dynamically, then learns the low-level local details with the lightweight multi-head Wavelet Transformer (WFormer) network.

Contrast, Stylize and Adapt: Unsupervised Contrastive Learning Framework for Domain Adaptive Semantic Segmentation

1 code implementation15 Jun 2023 Tianyu Li, Subhankar Roy, Huayi Zhou, Hongtao Lu, Stephane Lathuiliere

To address this, we present CONtrastive FEaTure and pIxel alignment (CONFETI) for bridging the domain gap at both the pixel and feature levels using a unique contrastive formulation.

Contrastive Learning Semantic Segmentation +2

Ultra-High Resolution Segmentation with Ultra-Rich Context: A Novel Benchmark

1 code implementation CVPR 2023 Deyi Ji, Feng Zhao, Hongtao Lu, Mingyuan Tao, Jieping Ye

With the increasing interest and rapid development of methods for Ultra-High Resolution (UHR) segmentation, a large-scale benchmark covering a wide range of scenes with full fine-grained dense annotations is urgently needed to facilitate the field.

Land Cover Classification Semantic Segmentation

Structural and Statistical Texture Knowledge Distillation for Semantic Segmentation

no code implementations CVPR 2022 Deyi Ji, Haoran Wang, Mingyuan Tao, Jianqiang Huang, Xian-Sheng Hua, Hongtao Lu

Existing knowledge distillation works for semantic segmentation mainly focus on transferring high-level contextual knowledge from teacher to student.

Knowledge Distillation Quantization +1

DirectMHP: Direct 2D Multi-Person Head Pose Estimation with Full-range Angles

1 code implementation2 Feb 2023 Huayi Zhou, Fei Jiang, Hongtao Lu

We present comprehensive comparisons with state-of-the-art single HPE methods on public benchmarks, as well as superior baseline results on our constructed MPHPE datasets.

Attribute Head Detection +1

Body-Part Joint Detection and Association via Extended Object Representation

1 code implementation15 Dec 2022 Huayi Zhou, Fei Jiang, Hongtao Lu

This paper focuses on the problem of joint detection of human body and its corresponding parts.

An Intuitive and Unconstrained 2D Cube Representation for Simultaneous Head Detection and Pose Estimation

no code implementations7 Dec 2022 Huayi Zhou, Fei Jiang, Lili Xiong, Hongtao Lu

Most recent head pose estimation (HPE) methods are dominated by the Euler angle representation.

Ranked #8 on Head Pose Estimation on BIWI (MAE (trained with BIWI data) metric)

Head Detection Head Pose Estimation

EDEN: A Plug-in Equivariant Distance Encoding to Beyond the 1-WL Test

no code implementations19 Nov 2022 Chang Liu, Yuwen Yang, Yue Ding, Hongtao Lu

While most existing message-passing graph neural networks (MPNNs) are permutation-invariant in graph-level representation learning and permutation-equivariant in node- and edge-level representation learning, their expressive power is commonly limited by the 1-Weisfeiler-Lehman (1-WL) graph isomorphism test.

Graph Representation Learning Test

StuArt: Individualized Classroom Observation of Students with Automatic Behavior Recognition and Tracking

1 code implementation6 Nov 2022 Huayi Zhou, Fei Jiang, Jiaxin Si, Lili Xiong, Hongtao Lu

In this paper, we present StuArt, a novel automatic system designed for the individualized classroom observation, which empowers instructors to concern the learning status of each student.

SSDA-YOLO: Semi-supervised Domain Adaptive YOLO for Cross-Domain Object Detection

1 code implementation4 Nov 2022 Huayi Zhou, Fei Jiang, Hongtao Lu

Domain adaptive object detection (DAOD) aims to alleviate transfer performance degradation caused by the cross-domain discrepancy.

Domain Adaptation Knowledge Distillation +3

Position-Aware Subgraph Neural Networks with Data-Efficient Learning

1 code implementation1 Nov 2022 Chang Liu, Yuwen Yang, Zhe Xie, Hongtao Lu, Yue Ding

2) Prevailing graph augmentation methods for GEL, including rule-based, sample-based, adaptive, and automated methods, are not suitable for augmenting subgraphs because a subgraph contains fewer nodes but richer information such as position, neighbor, and structure.

Contrastive Learning Position +1

Completely Heterogeneous Federated Learning

no code implementations28 Oct 2022 Chang Liu, Yuwen Yang, Xun Cai, Yue Ding, Hongtao Lu

Federated learning (FL) faces three major difficulties: cross-domain, heterogeneous models, and non-i. i. d.

Data-free Knowledge Distillation Federated Learning

Joint Multi-Person Body Detection and Orientation Estimation via One Unified Embedding

1 code implementation27 Oct 2022 Huayi Zhou, Fei Jiang, Jiaxin Si, Hongtao Lu

In the paper, we propose a single-stage end-to-end trainable framework for tackling the HBOE problem with multi-persons.

Autonomous Driving Body Detection +1

NoMorelization: Building Normalizer-Free Models from a Sample's Perspective

no code implementations13 Oct 2022 Chang Liu, Yuwen Yang, Yue Ding, Hongtao Lu

The normalizing layer has become one of the basic configurations of deep learning models, but it still suffers from computational inefficiency, interpretability difficulties, and low generality.

Cooperative Self-Training for Multi-Target Adaptive Semantic Segmentation

1 code implementation4 Oct 2022 Yangsong Zhang, Subhankar Roy, Hongtao Lu, Elisa Ricci, Stéphane Lathuilière

In this work we address multi-target domain adaptation (MTDA) in semantic segmentation, which consists in adapting a single model from an annotated source dataset to multiple unannotated target datasets that differ in their underlying data distributions.

Domain Adaptation Multi-target Domain Adaptation +2

Degradation-Guided Meta-Restoration Network for Blind Super-Resolution

no code implementations3 Jul 2022 Fuzhi Yang, Huan Yang, Yanhong Zeng, Jianlong Fu, Hongtao Lu

The extractor estimates the degradations in LR inputs and guides the meta-restoration modules to predict restoration parameters for different degradations on-the-fly.

Blind Super-Resolution Image Restoration +1

RAFT-MSF: Self-Supervised Monocular Scene Flow using Recurrent Optimizer

no code implementations3 May 2022 Bayram Bayramli, Junhwa Hur, Hongtao Lu

Self-supervised methods demonstrate learning scene flow estimation from unlabeled data, yet their accuracy lags behind (semi-)supervised methods.

Optical Flow Estimation Scene Flow Estimation

Reinforcing Local Feature Representation for Weakly-Supervised Dense Crowd Counting

no code implementations22 Feb 2022 Xiaoshuang Chen, Hongtao Lu

To address this problem, we propose a self-adaptive feature similarity learning (SFSL) network and a global-local consistency (GLC) loss to reinforce local feature representation.

Crowd Counting

Student Dangerous Behavior Detection in School

1 code implementation19 Feb 2022 Huayi Zhou, Fei Jiang, Hongtao Lu

Video surveillance systems have been installed to ensure the student safety in schools.

Action Recognition object-detection +1

Trimap-guided Feature Mining and Fusion Network for Natural Image Matting

1 code implementation1 Dec 2021 Weihao Jiang, Dongdong Yu, Zhaozhi Xie, Yaoyi Li, Zehuan Yuan, Hongtao Lu

For emerging content-based feature fusion, most existing matting methods only focus on local features which lack the guidance of a global feature with strong semantic information related to the interesting object.

Image Matting

FreqNet: A Frequency-domain Image Super-Resolution Network with Dicrete Cosine Transform

no code implementations21 Nov 2021 Runyuan Cai, Yue Ding, Hongtao Lu

A specialized pipeline is designed, and we further propose a frequency loss function to fit the nature of our frequency-domain task.

Image Super-Resolution

Adversarial and Contrastive Variational Autoencoder for Sequential Recommendation

1 code implementation19 Mar 2021 Zhe Xie, Chengxuan Liu, Yichi Zhang, Hongtao Lu, Dong Wang, Yue Ding

To solve the above problem, in this work, we propose a novel method called Adversarial and Contrastive Variational Autoencoder (ACVAE) for sequential recommendation.

Collaborative Filtering Sequential Recommendation

Temporal Continuity Based Unsupervised Learning for Person Re-Identification

no code implementations1 Sep 2020 Usman Ali, Bayram Bayramli, Hongtao Lu

Most existing person re-id methods generally require a large amount of identity labeled data to act as discriminative guideline for representation learning.

Clustering Person Re-Identification +1

Learning Texture Transformer Network for Image Super-Resolution

1 code implementation CVPR 2020 Fuzhi Yang, Huan Yang, Jianlong Fu, Hongtao Lu, Baining Guo

In this paper, we propose a novel Texture Transformer Network for Image Super-Resolution (TTSR), in which the LR and Ref images are formulated as queries and keys in a transformer, respectively.

Hard Attention Image Generation +2

LRNNet: A Light-Weighted Network with Efficient Reduced Non-Local Operation for Real-Time Semantic Segmentation

no code implementations4 Jun 2020 Weihao Jiang, Zhaozhi Xie, Yaoyi Li, Chang Liu, Hongtao Lu

Many of these applications need to perform a real-time and efficient prediction for semantic segmentation with a light-weighted network.

Real-Time Semantic Segmentation Segmentation

Hierarchical Opacity Propagation for Image Matting

no code implementations7 Apr 2020 Yaoyi Li, Qingyao Xu, Hongtao Lu

Natural image matting is a fundamental problem in computational photography and computer vision.

Image Matting

Natural Image Matting via Guided Contextual Attention

1 code implementation13 Jan 2020 Yaoyi Li, Hongtao Lu

Inspired by affinity-based method and the successes of contextual attention in inpainting, we develop a novel end-to-end approach for natural image matting with a guided contextual attention module, which is specifically designed for image matting.

Semantic Image Matting Transparent objects

Inductive Guided Filter: Real-time Deep Image Matting with Weakly Annotated Masks on Mobile Devices

no code implementations16 May 2019 Yaoyi Li, Jianfu Zhang, Weijie Zhao, Hongtao Lu

A high efficient image matting method based on a weakly annotated mask is in demand for mobile applications.

Image Matting

FH-GAN: Face Hallucination and Recognition using Generative Adversarial Network

no code implementations16 May 2019 Bayram Bayramli, Usman Ali, Te Qi, Hongtao Lu

One of the most important problem is low resolution face images which can result in bad performance on face recognition.

Face Hallucination Face Recognition +2

Spatial Shortcut Network for Human Pose Estimation

no code implementations5 Apr 2019 Te Qi, Bayram Bayramli, Usman Ali, Qinchuan Zhang, Hongtao Lu

Like many computer vision problems, human pose estimation is a challenging problem in that recognizing a body part requires not only information from local area but also from areas with large spatial distance.

Pose Estimation

Attend More Times for Image Captioning

no code implementations8 Dec 2018 Jiajun Du, Yu Qin, Hongtao Lu, Yonghua Zhang

Most attention-based image captioning models attend to the image once per word.

Image Captioning Test

An Adversarial Approach to Hard Triplet Generation

no code implementations ECCV 2018 Yiru Zhao, Zhongming Jin, Guo-Jun Qi, Hongtao Lu, Xian-Sheng Hua

While deep neural networks have demonstrated competitive results for many visual recognition and image retrieval tasks, the major challenge lies in distinguishing similar images from different categories (i. e., hard negative examples) while clustering images with large variations from the same category (i. e., hard positive examples).

Clustering Image Retrieval +1

Supervised Hashing based on Energy Minimization

no code implementations2 Dec 2017 Zihao Hu, Xiyi Luo, Hongtao Lu, Yong Yu

Recently, supervised hashing methods have attracted much attention since they can optimize retrieval speed and storage cost while preserving semantic information.

Retrieval

Bayesian Supervised Hashing

no code implementations CVPR 2017 Zihao Hu, Junxuan Chen, Hongtao Lu, Tongzhen Zhang

To address this problem, we present a novel fully Bayesian treatment for supervised hashing problem, named Bayesian Supervised Hashing (BSH), in which hyperparameters are automatically tuned during optimization.

Efficient Two-Dimensional Sparse Coding Using Tensor-Linear Combination

no code implementations28 Mar 2017 Fei Jiang, Xiao-Yang Liu, Hongtao Lu, Ruimin Shen

Sparse coding (SC) is an automatic feature extraction and selection technique that is widely used in unsupervised learning.

Denoising Vocal Bursts Valence Prediction

Graph Regularized Tensor Sparse Coding for Image Representation

no code implementations27 Mar 2017 Fei Jiang, Xiao-Yang Liu, Hongtao Lu, Ruimin Shen

Sparse coding (SC) is an unsupervised learning scheme that has received an increasing amount of interests in recent years.

Clustering Image Clustering

Accurate Deep Representation Quantization with Gradient Snapping Layer for Similarity Search

no code implementations30 Oct 2016 Shicong Liu, Hongtao Lu

However, how to learn deep representations that strongly preserve similarities between data pairs and can be accurately quantized via vector quantization remains a challenging task.

Quantization

Multi-View Constraint Propagation with Consensus Prior Knowledge

no code implementations21 Sep 2016 Yaoyi Li, Hongtao Lu

In this paper, we present a method dubbed Consensus Prior Constraint Propagation (CPCP), which can provide the prior knowledge of the robustness of each data instance and its neighborhood.

Clustering

Deep CTR Prediction in Display Advertising

no code implementations20 Sep 2016 Junxuan Chen, Baigui Sun, Hao Li, Hongtao Lu, Xian-Sheng Hua

Click through rate (CTR) prediction of image ads is the core task of online display advertising systems, and logistic regression (LR) has been frequently applied as the prediction model.

Click-Through Rate Prediction

Adaptive Affinity Matrix for Unsupervised Metric Learning

no code implementations13 Nov 2015 Yaoyi Li, Junxuan Chen, Hongtao Lu

In this paper, we propose a novel method, dubbed Adaptive Affinity Matrix (AdaAM), to learn an adaptive affinity matrix and derive a distance metric from the affinity.

Clustering Metric Learning

Improved Residual Vector Quantization for High-dimensional Approximate Nearest Neighbor Search

no code implementations17 Sep 2015 Shicong Liu, Hongtao Lu, Junru Shao

In this paper, we propose an improved residual vector quantization (IRVQ) method, our IRVQ learns codebook with a hybrid method of subspace clustering and warm-started k-means on each stage to prevent performance gain from dropping, and uses a multi-path encoding scheme to encode a vector with lower distortion.

Clustering Quantization +1

Accelerated Distance Computation with Encoding Tree for High Dimensional Data

no code implementations17 Sep 2015 Shicong Liu, Junru Shao, Hongtao Lu

We propose a novel distance to calculate distance between high dimensional vector pairs, utilizing vector quantization generated encodings.

Quantization Vocal Bursts Intensity Prediction

HCLAE: High Capacity Locally Aggregating Encodings for Approximate Nearest Neighbor Search

no code implementations17 Sep 2015 Shicong Liu, Junru Shao, Hongtao Lu

Further, we propose Aggregating-Tree (A-Tree), a non-exhaustive search method using HCLAE to perform efficient ANN-Search.

Quantization Vocal Bursts Intensity Prediction

Learning Better Encoding for Approximate Nearest Neighbor Search with Dictionary Annealing

no code implementations6 Jul 2015 Shicong Liu, Hongtao Lu

Jointly used with residual vector quantization, our optimized dictionaries lead to a better approximate nearest neighbor search performance compared to the state-of-the-art methods.

Dictionary Learning Quantization

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