b'Han Hu'

research

∙ 05/25/2023

VanillaKD: Revisit the Power of Vanilla Knowledge Distillation from Small Scale to Large Scale

The tremendous success of large models trained on extensive datasets dem...

0 Zhiwei Hao, et al. ∙

research

∙ 05/23/2023

Improving Heterogeneous Model Reuse by Density Estimation

This paper studies multiparty learning, aiming to learn a model using th...

0 Anke Tang, et al. ∙

research

∙ 05/11/2023

EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention

Vision transformers have shown great success due to their high model cap...

0 Xinyu Liu, et al. ∙

research

∙ 04/27/2023

SeqTrack: Sequence to Sequence Learning for Visual Object Tracking

In this paper, we present a new sequence-to-sequence learning framework ...

7 Xin Chen, et al. ∙

research

∙ 04/14/2023

BCE-Net: Reliable Building Footprints Change Extraction based on Historical Map and Up-to-Date Images using Contrastive Learning

Automatic and periodic recompiling of building databases with up-to-date...

0 Cheng Liao, et al. ∙

research

∙ 04/12/2023

SuperpixelGraph: Semi-automatic generation of building footprint through semantic-sensitive superpixel and neural graph networks

Most urban applications necessitate building footprints in the form of c...

0 Haojia Yu, et al. ∙

research

∙ 03/30/2023

Semantic Image Translation for Repairing the Texture Defects of Building Models

The accurate representation of 3D building models in urban environments ...

0 Qisen Shang, et al. ∙

research

∙ 03/21/2023

Human Pose as Compositional Tokens

Human pose is typically represented by a coordinate vector of body joint...

0 Zigang Geng, et al. ∙

research

∙ 03/18/2023

Pseudo Supervised Metrics: Evaluating Unsupervised Image to Image Translation Models In Unsupervised Cross-Domain Classification Frameworks

The ability to classify images accurately and efficiently is dependent o...

0 Firas Al-Hindawi, et al. ∙

research

∙ 03/16/2023

Efficient Diffusion Training via Min-SNR Weighting Strategy

Denoising diffusion models have been a mainstream approach for image gen...

0 Tiankai Hang, et al. ∙

research

∙ 03/15/2023

DeepMIM: Deep Supervision for Masked Image Modeling

Deep supervision, which involves extra supervisions to the intermediate ...

0 Sucheng Ren, et al. ∙

research

∙ 03/07/2023

SGDA: Towards 3D Universal Pulmonary Nodule Detection via Slice Grouped Domain Attention

Lung cancer is the leading cause of cancer death worldwide. The best sol...

0 Rui Xu, et al. ∙

research

∙ 02/24/2023

Subspace based Federated Unlearning

Federated learning (FL) enables multiple clients to train a machine lear...

0 Guanghao Li, et al. ∙

research

∙ 02/23/2023

Side Adapter Network for Open-Vocabulary Semantic Segmentation

This paper presents a new framework for open-vocabulary semantic segment...

0 Mengde Xu, et al. ∙

research

∙ 02/15/2023

FedABC: Targeting Fair Competition in Personalized Federated Learning

Federated learning aims to collaboratively train models without accessin...

0 Dui Wang, et al. ∙

research

∙ 02/08/2023

Training-free Lexical Backdoor Attacks on Language Models

Large-scale language models have achieved tremendous success across vari...

0 Yujin Huang, et al. ∙

research

∙ 01/05/2023

All in Tokens: Unifying Output Space of Visual Tasks via Soft Token

Unlike language tasks, where the output space is usually limited to a se...

13 Jia Ning, et al. ∙

research

∙ 01/03/2023

TinyMIM: An Empirical Study of Distilling MIM Pre-trained Models

Masked image modeling (MIM) performs strongly in pre-training large visi...

0 Sucheng Ren, et al. ∙

research

∙ 12/18/2022

A Generalized Framework for Critical Heat Flux Detection Using Unsupervised Image-to-Image Translation

This work proposes a framework developed to generalize Critical Heat Flu...

0 Firas Al-Hindawi, et al. ∙

research

∙ 12/16/2022

Attentive Mask CLIP

Image token removal is an efficient augmentation strategy for reducing t...

0 Yifan Yang, et al. ∙

research

∙ 12/01/2022

ResFormer: Scaling ViTs with Multi-Resolution Training

Vision Transformers (ViTs) have achieved overwhelming success, yet they ...

0 Rui Tian, et al. ∙

research

∙ 11/23/2022

SVFormer: Semi-supervised Video Transformer for Action Recognition

Semi-supervised action recognition is a challenging but critical task du...

0 Zhen Xing, et al. ∙

research

∙ 11/21/2022

Exploring Discrete Diffusion Models for Image Captioning

The image captioning task is typically realized by an auto-regressive me...

0 Zixin Zhu, et al. ∙

research

∙ 11/03/2022

Could Giant Pretrained Image Models Extract Universal Representations?

Frozen pretrained models have become a viable alternative to the pretrai...

0 Yutong Lin, et al. ∙

research

∙ 09/20/2022

One-to-Many Semantic Communication Systems: Design, Implementation, Performance Evaluation

Semantic communication in the 6G era has been deemed a promising communi...

3 Han Hu, et al. ∙

research

∙ 09/07/2022

Not All Instances Contribute Equally: Instance-adaptive Class Representation Learning for Few-Shot Visual Recognition

Few-shot visual recognition refers to recognize novel visual concepts fr...

3 Mengya Han, et al. ∙

research

∙ 07/27/2022

Leveraging GAN Priors for Few-Shot Part Segmentation

Few-shot part segmentation aims to separate different parts of an object...

7 Mengya Han, et al. ∙

research

∙ 07/26/2022

Lifelong DP: Consistently Bounded Differential Privacy in Lifelong Machine Learning

In this paper, we show that the process of continually learning new task...

1 Phung Lai, et al. ∙

research

∙ 06/09/2022

On Data Scaling in Masked Image Modeling

An important goal of self-supervised learning is to enable model pre-tra...

29 Zhenda Xie, et al. ∙

research

∙ 05/27/2022

Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillation

Masked image modeling (MIM) learns representations with remarkably good ...

4 Yixuan Wei, et al. ∙

research

∙ 05/26/2022

Revealing the Dark Secrets of Masked Image Modeling

Masked image modeling (MIM) as pre-training is shown to be effective for...

0 Zhenda Xie, et al. ∙

research

∙ 05/24/2022

Multi-Agent Collaborative Inference via DNN Decoupling: Intermediate Feature Compression and Edge Learning

Recently, deploying deep neural network (DNN) models via collaborative i...

10 Zhiwei Hao, et al. ∙

research

∙ 05/24/2022

CDFKD-MFS: Collaborative Data-free Knowledge Distillation via Multi-level Feature Sharing

Recently, the compression and deployment of powerful deep neural network...

6 Zhiwei Hao, et al. ∙

research

∙ 04/26/2022

Deeper Insights into ViTs Robustness towards Common Corruptions

Recent literature have shown design strategies from Convolutions Neural ...

1 Rui Tian, et al. ∙

research

∙ 04/22/2022

iCAR: Bridging Image Classification and Image-text Alignment for Visual Recognition

Image classification, which classifies images by pre-defined categories,...

2 Yixuan Wei, et al. ∙

research

∙ 04/10/2022

Enhancing the Robustness, Efficiency, and Diversity of Differentiable Architecture Search

Differentiable architecture search (DARTS) has attracted much attention ...

6 Chao Li, et al. ∙

research

∙ 02/10/2022

Intelligent Resource Allocations for IRS-Assisted OFDM Communications: A Hybrid MDQN-DDPG Approach

In this paper, we study the resource allocation problem for an intellige...

0 Wei Wu, et al. ∙

research

∙ 01/22/2022

Semi-Supervised Adversarial Recognition of Refined Window Structures for Inverse Procedural Façade Modeling

Deep learning methods are notoriously data-hungry, which requires a larg...

2 Han Hu, et al. ∙

research

∙ 12/29/2021

A Simple Baseline for Zero-shot Semantic Segmentation with Pre-trained Vision-language Model

Recently, zero-shot image classification by vision-language pre-training...

10 Mengde Xu, et al. ∙

research

∙ 11/18/2021

SimMIM: A Simple Framework for Masked Image Modeling

This paper presents SimMIM, a simple framework for masked image modeling...

0 Zhenda Xie, et al. ∙

research

∙ 11/18/2021

Swin Transformer V2: Scaling Up Capacity and Resolution

We present techniques for scaling Swin Transformer up to 3 billion param...

0 Ze Liu, et al. ∙

research

∙ 11/17/2021

FLSys: Toward an Open Ecosystem for Federated Learning Mobile Apps

This paper presents the design, implementation, and evaluation of FLSys,...

0 Han Hu, et al. ∙

research

∙ 11/04/2021

Bootstrap Your Object Detector via Mixed Training

We introduce MixTraining, a new training paradigm for object detection t...

29 Mengde Xu, et al. ∙

research

∙ 10/27/2021

Spatial Constraint Generation for Motion Planning in Dynamic Environments

This paper presents a novel method to generate spatial constraints for m...

0 Han Hu, et al. ∙

research

∙ 10/15/2021

Carbon Neutrality in Data Center

Data centers are carbon-intensive enterprises due to their massive energ...

0 Zhiwei Cao, et al. ∙

research

∙ 10/11/2021

Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning

Due to the limited and even imbalanced data, semi-supervised semantic se...

0 Hanzhe Hu, et al. ∙

research

∙ 06/24/2021

Video Swin Transformer

The vision community is witnessing a modeling shift from CNNs to Transfo...

0 Ze Liu, et al. ∙

research

∙ 06/16/2021

End-to-End Semi-Supervised Object Detection with Soft Teacher

This paper presents an end-to-end semi-supervised object detection appro...

0 Mengde Xu, et al. ∙

research

∙ 06/04/2021

Aligning Pretraining for Detection via Object-Level Contrastive Learning

Image-level contrastive representation learning has proven to be highly ...

0 Fangyun Wei, et al. ∙

research

∙ 05/10/2021

Self-Supervised Learning with Swin Transformers

We are witnessing a modeling shift from CNN to Transformers in computer ...

0 Zhenda Xie, et al. ∙

Han Hu

Featured Co-authors