Shanghang Zhang

research

∙ 08/21/2023

QD-BEV : Quantization-aware View-guided Distillation for Multi-view 3D Object Detection

Multi-view 3D detection based on BEV (bird-eye-view) has recently achiev...

0 Yifan Zhang, et al. ∙

research

∙ 08/14/2023

ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate

Text evaluation has historically posed significant challenges, often dem...

0 Chi-Min Chan, et al. ∙

research

∙ 05/26/2023

HUB: Guiding Learned Optimizers with Continuous Prompt Tuning

Learned optimizers are a crucial component of meta-learning. Recent adva...

7 Gaole Dai, et al. ∙

research

∙ 05/21/2023

Integer or Floating Point? New Outlooks for Low-Bit Quantization on Large Language Models

Efficient deployment of large language models (LLMs) necessitates low-bi...

0 Yijia Zhang, et al. ∙

research

∙ 04/03/2023

Open-Vocabulary Point-Cloud Object Detection without 3D Annotation

The goal of open-vocabulary detection is to identify novel objects based...

0 Yuheng Lu, et al. ∙

research

∙ 03/24/2023

MoWE: Mixture of Weather Experts for Multiple Adverse Weather Removal

Currently, most adverse weather removal tasks are handled independently,...

0 Yulin Luo, et al. ∙

research

∙ 03/14/2023

PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection

Masked Autoencoders learn strong visual representations and achieve stat...

0 Anthony Chen, et al. ∙

research

∙ 02/08/2023

Q-Diffusion: Quantizing Diffusion Models

Diffusion models have achieved great success in synthesizing diverse and...

0 Xiuyu Li, et al. ∙

research

∙ 12/06/2022

CSQ: Growing Mixed-Precision Quantization Scheme with Bi-level Continuous Sparsification

Mixed-precision quantization has been widely applied on deep neural netw...

0 Lirui Xiao, et al. ∙

research

∙ 11/29/2022

NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers

The complicated architecture and high training cost of vision transforme...

0 Yijiang Liu, et al. ∙

research

∙ 11/21/2022

PointCLIP V2: Adapting CLIP for Powerful 3D Open-world Learning

Contrastive Language-Image Pre-training (CLIP) has shown promising open-...

0 Xiangyang Zhu, et al. ∙

research

∙ 09/27/2022

Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models

Transformer architecture has become the fundamental element of the wides...

0 Xiuying Wei, et al. ∙

research

∙ 09/15/2022

BadRes: Reveal the Backdoors through Residual Connection

Generally, residual connections are indispensable network components in ...

0 Mingrui He, et al. ∙

research

∙ 07/05/2022

Open-Vocabulary 3D Detection via Image-level Class and Debiased Cross-modal Contrastive Learning

Current point-cloud detection methods have difficulty detecting the open...

0 Yuheng Lu, et al. ∙

research

∙ 06/20/2022

Domain-Adaptive Text Classification with Structured Knowledge from Unlabeled Data

Domain adaptive text classification is a challenging problem for the lar...

0 Tian Li, et al. ∙

research

∙ 10/27/2021

2nd Place Solution for VisDA 2021 Challenge – Universally Domain Adaptive Image Recognition

The Visual Domain Adaptation (VisDA) 2021 Challenge calls for unsupervis...

0 Haojin Liao, et al. ∙

research

∙ 07/23/2021

Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency

Deep learning-based 3D object detection has achieved unprecedented succe...

0 Zhipeng Luo, et al. ∙

research

∙ 07/06/2021

Contrastive Multimodal Fusion with TupleInfoNCE

This paper proposes a method for representation learning of multimodal d...

7 Yunze Liu, et al. ∙

research

∙ 06/11/2021

Online Continual Adaptation with Active Self-Training

Models trained with offline data often suffer from continual distributio...

0 Shiji Zhou, et al. ∙

research

∙ 03/23/2021

Self-Supervised Pretraining Improves Self-Supervised Pretraining

While self-supervised pretraining has proven beneficial for many compute...

45 Colorado J. Reed, et al. ∙

research

∙ 12/24/2020

P4Contrast: Contrastive Learning with Pairs of Point-Pixel Pairs for RGB-D Scene Understanding

Self-supervised representation learning is a critical problem in compute...

2 Yunze Liu, et al. ∙

research

∙ 12/14/2020

Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting

Many real-world applications require the prediction of long sequence tim...

0 Haoyi Zhou, et al. ∙

research

∙ 12/05/2020

Cross-Domain Sentiment Classification with In-Domain Contrastive Learning

Contrastive learning (CL) has been successful as a powerful representati...

0 Tian Li, et al. ∙

research

∙ 11/30/2020

Annotation-Efficient Untrimmed Video Action Recognition

Deep learning has achieved great success in recognizing video actions, b...

0 Yixiong Zou, et al. ∙

research

∙ 10/30/2020

Cross-Domain Sentiment Classification With Contrastive Learning and Mutual Information Maximization

Contrastive learning (CL) has been successful as a powerful representati...

0 Tian Li, et al. ∙

research

∙ 10/09/2020

Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation

The success of supervised learning hinges on the assumption that the tra...

5 Bo Li, et al. ∙

research

∙ 09/01/2020

A Review of Single-Source Deep Unsupervised Visual Domain Adaptation

Large-scale labeled training datasets have enabled deep neural networks ...

7 Sicheng Zhao, et al. ∙

research

∙ 08/27/2020

Instance Adaptive Self-Training for Unsupervised Domain Adaptation

The divergence between labeled training data and unlabeled testing data ...

0 Ke Mei, et al. ∙

research

∙ 08/07/2020

Revisiting Mid-Level Patterns for Distant-Domain Few-Shot Recognition

Cross-domain few-shot learning (FSL) is proposed recently to transfer kn...

10 Yixiong Zou, et al. ∙

research

∙ 07/14/2020

TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality Learning

Fusing data from multiple modalities provides more information to train ...

18 Xinwei Sun, et al. ∙

research

∙ 06/23/2020

Rethinking Distributional Matching Based Domain Adaptation

Domain adaptation (DA) is a technique that transfers predictive models t...

16 Bo Li, et al. ∙

research

∙ 05/12/2020

Compositional Few-Shot Recognition with Primitive Discovery and Enhancing

Few-shot learning (FSL) aims at recognizing novel classes given only few...

11 Yixiong Zou, et al. ∙

research

∙ 11/26/2019

Decoupling Features and Coordinates for Few-shot RGB Relocalization

Cross-scene model adaption is a crucial feature for camera relocalizatio...

12 Siyan Dong, et al. ∙

research

∙ 11/22/2019

Multi-source Distilling Domain Adaptation

Deep neural networks suffer from performance decay when there is domain ...

8 Sicheng Zhao, et al. ∙

research

∙ 09/28/2019

Generalized Zero-shot ICD Coding

The International Classification of Diseases (ICD) is a list of classifi...

0 Congzheng Song, et al. ∙

research

∙ 07/12/2019

Dual Adversarial Semantics-Consistent Network for Generalized Zero-Shot Learning

Generalized zero-shot learning (GZSL) is a challenging class of vision a...

0 Jian Ni, et al. ∙

research

∙ 10/14/2018

Hierarchical Attention Networks for Knowledge Base Completion via Joint Adversarial Training

Knowledge Base (KB) completion, which aims to determine missing relation...

0 Chen Li, et al. ∙

research

∙ 10/28/2017

Topology Adaptive Graph Convolutional Networks

Convolution acts as a local feature extractor in convolutional neural ne...

0 Jian Du, et al. ∙

research

∙ 07/29/2017

FCN-rLSTM: Deep Spatio-Temporal Neural Networks for Vehicle Counting in City Cameras

In this paper, we develop deep spatio-temporal neural networks to sequen...

0 Shanghang Zhang, et al. ∙

research

∙ 05/26/2017

Multiple Source Domain Adaptation with Adversarial Training of Neural Networks

While domain adaptation has been actively researched in recent years, mo...

0 Han Zhao, et al. ∙

research

∙ 03/17/2017

Understanding Traffic Density from Large-Scale Web Camera Data

Understanding traffic density from large-scale web camera (webcam) video...

0 Shanghang Zhang, et al. ∙

Shanghang Zhang

Featured Co-authors