Search Results for author: Shu Zhao

Found 19 papers, 8 papers with code

Reconstruct before Query: Continual Missing Modality Learning with Decomposed Prompt Collaboration

1 code implementation17 Mar 2024 Shu Zhao, Xiaohan Zou, Tan Yu, Huijuan Xu

Meanwhile, our RebQ leverages extensive multi-modal knowledge from pre-trained LMMs to reconstruct the data of missing modality.

Continual Learning

Why are hyperbolic neural networks effective? A study on hierarchical representation capability

1 code implementation4 Feb 2024 Shicheng Tan, Huanjing Zhao, Shu Zhao, Yanping Zhang

Inspired by the analysis results, we propose several pre-training strategies to enhance HRC and improve the performance of downstream tasks, further validating the reliability of the analysis.

NEUCORE: Neural Concept Reasoning for Composed Image Retrieval

no code implementations2 Oct 2023 Shu Zhao, Huijuan Xu

Specifically, considering that text modifier may refer to semantic concepts not existing in the reference image and requiring to be added into the target image, we learn the multi-modal concept alignment between the text modifier and the concatenation of reference and target images, under multiple-instance learning framework with image and sentence level weak supervision.

Concept Alignment Image Retrieval +3

Are Intermediate Layers and Labels Really Necessary? A General Language Model Distillation Method

1 code implementation11 Jun 2023 Shicheng Tan, Weng Lam Tam, Yuanchun Wang, Wenwen Gong, Shu Zhao, Peng Zhang, Jie Tang

To address these problems, we propose a general language model distillation (GLMD) method that performs two-stage word prediction distillation and vocabulary compression, which is simple and surprisingly shows extremely strong performance.

Knowledge Distillation Language Modelling

GKD: A General Knowledge Distillation Framework for Large-scale Pre-trained Language Model

1 code implementation11 Jun 2023 Shicheng Tan, Weng Lam Tam, Yuanchun Wang, Wenwen Gong, Yang Yang, Hongyin Tang, Keqing He, Jiahao Liu, Jingang Wang, Shu Zhao, Peng Zhang, Jie Tang

Currently, the reduction in the parameter scale of large-scale pre-trained language models (PLMs) through knowledge distillation has greatly facilitated their widespread deployment on various devices.

General Knowledge Knowledge Distillation +1

Understanding the Robustness of 3D Object Detection with Bird's-Eye-View Representations in Autonomous Driving

1 code implementation CVPR 2023 Zijian Zhu, Yichi Zhang, Hai Chen, Yinpeng Dong, Shu Zhao, Wenbo Ding, Jiachen Zhong, Shibao Zheng

However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems.

3D Object Detection Adversarial Robustness +2

Automatic Analysis of Human Body Representations in Western Art

1 code implementation17 Oct 2022 Shu Zhao, Almıla Akdağ Salah, Albert Ali Salah

The way the human body is depicted in classical and modern paintings is relevant for art historical analyses.

Pose Estimation

Aesthetic Visual Question Answering of Photographs

no code implementations10 Aug 2022 Xin Jin, Wu Zhou, Xinghui Zhou, Shuai Cui, Le Zhang, Jianwen Lv, Shu Zhao

In this paper, we propose a new task of aesthetic language assessment: aesthetic visual question and answering (AVQA) of images.

Question Answering Sentiment Analysis +1

Attribute Controllable Beautiful Caucasian Face Generation by Aesthetics Driven Reinforcement Learning

no code implementations9 Aug 2022 Xin Jin, Shu Zhao, Le Zhang, Xin Zhao, Qiang Deng, Chaoen Xiao

In recent years, image generation has made great strides in improving the quality of images, producing high-fidelity ones.

Attribute Face Generation +3

Hyperbolic Hierarchical Knowledge Graph Embeddings for Link Prediction in Low Dimensions

no code implementations28 Apr 2022 Wenjie Zheng, Wenxue Wang, Shu Zhao, Fulan Qian

Knowledge graph embeddings (KGE) have been validated as powerful methods for inferring missing links in knowledge graphs (KGs) that they typically map entities into Euclidean space and treat relations as transformations of entities.

Knowledge Graph Embeddings Knowledge Graphs +1

Coherence-Based Distributed Document Representation Learning for Scientific Documents

1 code implementation8 Jan 2022 Shicheng Tan, Shu Zhao, Yanping Zhang

In this paper, we propose a coupled text pair embedding (CTPE) model to learn the representation of scientific documents, which maintains the coherence of the document with coupled text pairs formed by segmenting the document.

Information Retrieval Representation Learning +1

JAS-GAN: Generative Adversarial Network Based Joint Atrium and Scar Segmentations on Unbalanced Atrial Targets

no code implementations1 May 2021 Jun Chen, Guang Yang, Habib Khan, Heye Zhang, Yanping Zhang, Shu Zhao, Raad Mohiaddin, Tom Wong, David Firmin, Jennifer Keegan

In this paper, we propose an inter-cascade generative adversarial network, namely JAS-GAN, to segment the unbalanced atrial targets from LGE CMR images automatically and accurately in an end-to-end way.

Generative Adversarial Network Segmentation

Rescuing Deep Hashing from Dead Bits Problem

no code implementations1 Feb 2021 Shu Zhao, Dayan Wu, Yucan Zhou, Bo Li, Weiping Wang

The proposed gradient amplifier and error-aware quantization loss are compatible with a variety of deep hashing methods.

Deep Hashing Image Retrieval +1

Discriminative Consistent Domain Generation for Semi-supervised Learning

no code implementations24 Jul 2019 Jun Chen, Heye Zhang, Yanping Zhang, Shu Zhao, Raad Mohiaddin, Tom Wong, David Firmin, Guang Yang, Jennifer Keegan

Based on the generated discriminative consistent domain, we can use the unlabeled data to learn the task model along with the labeled data via a consistent image generation.

Anatomy Domain Adaptation +1

Direct Quantification for Coronary Artery Stenosis Using Multiview Learning

no code implementations20 Jul 2019 Dong Zhang, Guang Yang, Shu Zhao, Yanping Zhang, Heye Zhang, Shuo Li

The proposed DMQCA model consists of a multiview module with two attention mechanisms, a key-frame module, and a regression module, to achieve direct accurate multiple-index estimation.

Multiview Learning regression

Direct detection of pixel-level myocardial infarction areas via a deep-learning algorithm

no code implementations10 Jun 2017 Chenchu Xu, Lei Xu, Zhifan Gao, Shen zhao, Heye Zhang, Yanping Zhang, Xiuquan Du, Shu Zhao, Dhanjoo Ghista, Shuo Li

Accurate detection of the myocardial infarction (MI) area is crucial for early diagnosis planning and follow-up management.

Management Time Series Analysis

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