Search Results for author: Tianyi Wu

Found 23 papers, 10 papers with code

Homophily-Related: Adaptive Hybrid Graph Filter for Multi-View Graph Clustering

1 code implementation5 Jan 2024 Zichen Wen, Yawen Ling, Yazhou Ren, Tianyi Wu, Jianpeng Chen, Xiaorong Pu, Zhifeng Hao, Lifang He

Then we design an adaptive hybrid graph filter that is related to the homophily degree, which learns the node embedding based on the graph joint aggregation matrix.

Clustering Graph Clustering

Rotation-Constrained Cross-View Feature Fusion for Multi-View Appearance-based Gaze Estimation

1 code implementation22 May 2023 Yoichiro Hisadome, Tianyi Wu, Jiawei Qin, Yusuke Sugano

This work proposes a generalizable multi-view gaze estimation task and a cross-view feature fusion method to address this issue.

Domain Generalization Gaze Estimation

Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention

1 code implementation28 Sep 2022 Xiangcheng Liu, Tianyi Wu, Guodong Guo

The learnable thresholds are optimized in budget-aware training to balance accuracy and complexity, performing the corresponding pruning configurations for different input instances.

Efficient ViTs Informativeness

Multi-band oscillations emerge from a simple spiking network

no code implementations29 Jun 2022 Tianyi Wu, Yuhang Cai, Ruilin Zhang, Zhongyi Wang, Louis Tao, Zhuo-Cheng Xiao

These results suggest a simple geometric mechanism behind the emergence of multi-band oscillations without appealing to oscillatory inputs or multiple synaptic or neuronal timescales.

IGN : Implicit Generative Networks

1 code implementation13 Jun 2022 Haozheng Luo, Tianyi Wu, Feiyu Han, Zhijun Yan, Jianfen Zhang

In this work, we build recent advances in distributional reinforcement learning to give a state-of-art distributional variant of the model based on the IQN.

Atari Games Distributional Reinforcement Learning +3

Deeply Supervised Skin Lesions Diagnosis with Stage and Branch Attention

2 code implementations9 May 2022 Wei Dai, Rui Liu, Tianyi Wu, Min Wang, Jianqin Yin, Jun Liu

Visual features of skin lesions vary significantly because the images are collected from patients with different lesion colours and morphologies by using dissimilar imaging equipment.


Region-level Contrastive and Consistency Learning for Semi-Supervised Semantic Segmentation

no code implementations28 Apr 2022 Jianrong Zhang, Tianyi Wu, Chuanghao Ding, Hongwei Zhao, Guodong Guo

Specifically, we first propose a Region Mask Contrastive (RMC) loss and a Region Feature Contrastive (RFC) loss to accomplish region-level contrastive property.

Segmentation Semi-Supervised Semantic Segmentation

CATrans: Context and Affinity Transformer for Few-Shot Segmentation

no code implementations27 Apr 2022 Shan Zhang, Tianyi Wu, Sitong Wu, Guodong Guo

In this work, we effectively integrate the context and affinity information via the proposed novel Context and Affinity Transformer (CATrans) in a hierarchical architecture.

Relation Transfer Learning

Feature Selective Transformer for Semantic Image Segmentation

no code implementations26 Mar 2022 Fangjian Lin, Tianyi Wu, Sitong Wu, Shengwei Tian, Guodong Guo

In this work, we focus on fusing multi-scale features from Transformer-based backbones for semantic segmentation, and propose a Feature Selective Transformer (FeSeFormer), which aggregates features from all scales (or levels) for each query feature.

feature selection Image Segmentation +2

Dynamic Group Transformer: A General Vision Transformer Backbone with Dynamic Group Attention

no code implementations8 Mar 2022 Kai Liu, Tianyi Wu, Cong Liu, Guodong Guo

To reduce the quadratic computation complexity caused by each query attending to all keys/values, various methods have constrained the range of attention within local regions, where each query only attends to keys/values within a hand-crafted window.

Image Classification Instance Segmentation +3

Pale Transformer: A General Vision Transformer Backbone with Pale-Shaped Attention

2 code implementations28 Dec 2021 Sitong Wu, Tianyi Wu, Haoru Tan, Guodong Guo

To reduce the quadratic computation complexity caused by the global self-attention, various methods constrain the range of attention within a local region to improve its efficiency.

Instance Segmentation object-detection +2

Sparse to Dense Motion Transfer for Face Image Animation

no code implementations1 Sep 2021 Ruiqi Zhao, Tianyi Wu, Guodong Guo

Given a source face image and a sequence of sparse face landmarks, our goal is to generate a video of the face imitating the motion of landmarks.

Image Animation Motion Estimation +1

Fully Transformer Networks for Semantic Image Segmentation

1 code implementation8 Jun 2021 Sitong Wu, Tianyi Wu, Fangjian Lin, Shengwei Tian, Guodong Guo

Transformers have shown impressive performance in various natural language processing and computer vision tasks, due to the capability of modeling long-range dependencies.

Decoder Face Parsing +3

Model Reduction Captures Stochastic Gamma Oscillations on Low-Dimensional Manifolds

no code implementations5 Jan 2021 Yuhang Cai, Tianyi Wu, Louis Tao, Zhuo-Cheng Xiao

Here we propose a suite of Markovian model reduction methods with varying levels of complexity and applied it to spiking network models exhibiting heterogeneous dynamical regimes, ranging from homogeneous firing to strong synchrony in the gamma band.

Adam with Bandit Sampling for Deep Learning

no code implementations NeurIPS 2020 Rui Liu, Tianyi Wu, Barzan Mozafari

In this paper, we propose a generalization of Adam, called Adambs, that allows us to also adapt to different training examples based on their importance in the model's convergence.

GINet: Graph Interaction Network for Scene Parsing

1 code implementation ECCV 2020 Tianyi Wu, Yu Lu, Yu Zhu, Chuang Zhang, Ming Wu, Zhanyu Ma, Guodong Guo

GI unit is further improved by the SC-loss to enhance the semantic representations over the exemplar-based semantic graph.

Scene Parsing

Learning to Recognize the Unseen Visual Predicates

no code implementations25 Sep 2019 Defa Zhu, Si Liu, Wentao Jiang, Guanbin Li, Tianyi Wu, Guodong Guo

Visual relationship recognition models are limited in the ability to generalize from finite seen predicates to unseen ones.

Question Answering Visual Question Answering +1

Consensus Feature Network for Scene Parsing

no code implementations29 Jul 2019 Tianyi Wu, Sheng Tang, Rui Zhang, Guodong Guo, Yongdong Zhang

However, classification networks are dominated by the discriminative portion, so directly applying classification networks to scene parsing will result in inconsistent parsing predictions within one instance and among instances of the same category.

General Classification Scene Parsing

UGAN: Untraceable GAN for Multi-Domain Face Translation

no code implementations26 Jul 2019 Defa Zhu, Si Liu, Wentao Jiang, Chen Gao, Tianyi Wu, Qaingchang Wang, Guodong Guo

To address this issue, we propose a method called Untraceable GAN, which has a novel source classifier to differentiate which domain an image is translated from, and determines whether the translated image still retains the characteristics of the source domain.

Image-to-Image Translation Translation

A Bandit Approach to Maximum Inner Product Search

no code implementations15 Dec 2018 Rui Liu, Tianyi Wu, Barzan Mozafari

There has been substantial research on sub-linear time approximate algorithms for Maximum Inner Product Search (MIPS).

Tree-structured Kronecker Convolutional Network for Semantic Segmentation

no code implementations12 Dec 2018 Tianyi Wu, Sheng Tang, Rui Zhang, Juan Cao, Jintao Li

Therefore, it can capture partial information and enlarge the receptive field of filters simultaneously without introducing extra parameters.

Semantic Segmentation

CGNet: A Light-weight Context Guided Network for Semantic Segmentation

4 code implementations20 Nov 2018 Tianyi Wu, Sheng Tang, Rui Zhang, Yongdong Zhang

To tackle this problem, we propose a novel Context Guided Network (CGNet), which is a light-weight and efficient network for semantic segmentation.

Segmentation Semantic Segmentation

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