Search Results for author: Lechao Cheng

Found 30 papers, 13 papers with code

ScrollTimes: Tracing the Provenance of Paintings as a Window into History

no code implementations15 Jun 2023 Wei zhang, Jason K. Wong, Yitian Chen, Ailing Jia, Luwei Wang, Jian-Wei Zhang, Lechao Cheng, Wei Chen

We collaborated with art historians to examine handscrolls, a form of traditional Chinese painting which offers a wealth of data for historical analysis and provides a unique opportunity for understanding history through artwork.

Improving Knowledge Distillation via Regularizing Feature Norm and Direction

1 code implementation26 May 2023 Yuzhu Wang, Lechao Cheng, Manni Duan, Yongheng Wang, Zunlei Feng, Shu Kong

Finally, we propose a rather simple loss term (dubbed ND loss) to simultaneously (1) encourage student to produce large-\emph{norm} features, and (2) align the \emph{direction} of student features and teacher class-means.

Domain Adaptation Knowledge Distillation

Masked Collaborative Contrast for Weakly Supervised Semantic Segmentation

1 code implementation15 May 2023 Fangwen Wu, Jingxuan He, Yufei Yin, Yanbin Hao, Gang Huang, Lechao Cheng

This study introduces an efficacious approach, Masked Collaborative Contrast (MCC), to highlight semantic regions in weakly supervised semantic segmentation.

Contrastive Learning Weakly supervised Semantic Segmentation +1

Life Regression based Patch Slimming for Vision Transformers

no code implementations11 Apr 2023 Jiawei Chen, Lin Chen, Jiang Yang, Tianqi Shi, Lechao Cheng, Zunlei Feng, Mingli Song

In this study, we tackle the patch slimming problem from a different perspective by proposing a life regression module that determines the lifespan of each image patch in one go.


ViT-Calibrator: Decision Stream Calibration for Vision Transformer

no code implementations10 Apr 2023 Lin Chen, Zhijie Jia, Tian Qiu, Lechao Cheng, Jie Lei, Zunlei Feng, Mingli Song

In this work, we propose a new paradigm dubbed Decision Stream Calibration that boosts the performance of general Vision Transformers.

Propheter: Prophetic Teacher Guided Long-Tailed Distribution Learning

no code implementations9 Apr 2023 Wenxiang Xu, Linyun Zhou, Lin Chen, Lechao Cheng, Jie Lei, Zunlei Feng, Mingli Song

This is specifically achieved by devising an elaborated ``prophetic'' teacher, termed as ``Propheter'', that aims to learn the potential class distributions.

Data Augmentation

Generalization Matters: Loss Minima Flattening via Parameter Hybridization for Efficient Online Knowledge Distillation

1 code implementation CVPR 2023 Tianli Zhang, Mengqi Xue, Jiangtao Zhang, Haofei Zhang, Yu Wang, Lechao Cheng, Jie Song, Mingli Song

Most existing online knowledge distillation(OKD) techniques typically require sophisticated modules to produce diverse knowledge for improving students' generalization ability.

Knowledge Distillation

Model Doctor for Diagnosing and Treating Segmentation Error

1 code implementation17 Feb 2023 Zhijie Jia, Lin Chen, Kaiwen Hu, Lechao Cheng, Zunlei Feng, Mingli Song

Despite the remarkable progress in semantic segmentation tasks with the advancement of deep neural networks, existing U-shaped hierarchical typical segmentation networks still suffer from local misclassification of categories and inaccurate target boundaries.

Semantic Segmentation

Team DETR: Guide Queries as a Professional Team in Detection Transformers

1 code implementation14 Feb 2023 Tian Qiu, Linyun Zhou, Wenxiang Xu, Lechao Cheng, Zunlei Feng, Mingli Song

Recent proposed DETR variants have made tremendous progress in various scenarios due to their streamlined processes and remarkable performance.

Boosting Low-Data Instance Segmentation by Unsupervised Pre-training with Saliency Prompt

no code implementations CVPR 2023 Hao Li, Dingwen Zhang, Nian Liu, Lechao Cheng, Yalun Dai, Chao Zhang, Xinggang Wang, Junwei Han

Inspired by the recent success of the Prompting technique, we introduce a new pre-training method that boosts QEIS models by giving Saliency Prompt for queries/kernels.

Instance Segmentation Semantic Segmentation +1

Text-Guided Mask-free Local Image Retouching

no code implementations15 Dec 2022 Zerun Liu, Fan Zhang, Jingxuan He, Jin Wang, Zhangye Wang, Lechao Cheng

In the realm of multi-modality, text-guided image retouching techniques emerged with the advent of deep learning.

Image Retouching

SASFormer: Transformers for Sparsely Annotated Semantic Segmentation

1 code implementation5 Dec 2022 Hui Su, Yue Ye, Wei Hua, Lechao Cheng, Mingli Song

In this work, we propose a simple yet effective sparse annotated semantic segmentation framework based on segformer, dubbed SASFormer, that achieves remarkable performance.

Semantic Segmentation Weakly supervised Semantic Segmentation

Transferability Estimation Based On Principal Gradient Expectation

no code implementations29 Nov 2022 Huiyan Qi, Lechao Cheng, Jingjing Chen, Yue Yu, Xue Song, Zunlei Feng, Yu-Gang Jiang

Transfer learning aims to improve the performance of target tasks by transferring knowledge acquired in source tasks.

Transfer Learning

A Survey of Neural Trees

1 code implementation7 Sep 2022 Haoling Li, Jie Song, Mengqi Xue, Haofei Zhang, Jingwen Ye, Lechao Cheng, Mingli Song

This survey aims to present a comprehensive review of NTs and attempts to identify how they enhance the model interpretability.

Combating Noisy Labels in Long-Tailed Image Classification

no code implementations1 Sep 2022 Chaowei Fang, Lechao Cheng, Huiyan Qi, Dingwen Zhang

Most existing methods that cope with noisy labels usually assume that the class distributions are well balanced, which has insufficient capacity to deal with the practical scenarios where training samples have imbalanced distributions.

Classification Image Classification

ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognition

1 code implementation22 Aug 2022 Mengqi Xue, Qihan Huang, Haofei Zhang, Lechao Cheng, Jie Song, Minghui Wu, Mingli Song

The global prototypes are adopted to provide the global view of objects to guide local prototypes to concentrate on the foreground while eliminating the influence of the background.

Decision Making Explainable artificial intelligence +1

Re-Attention Transformer for Weakly Supervised Object Localization

1 code implementation3 Aug 2022 Hui Su, Yue Ye, Zhiwei Chen, Mingli Song, Lechao Cheng

Weakly supervised object localization is a challenging task which aims to localize objects with coarse annotations such as image categories.

Weakly-Supervised Object Localization

Long-term Leap Attention, Short-term Periodic Shift for Video Classification

1 code implementation12 Jul 2022 Hao Zhang, Lechao Cheng, Yanbin Hao, Chong-Wah Ngo

By replacing a vanilla 2D attention with the LAPS, we could adapt a static transformer into a video one, with zero extra parameters and neglectable computation overhead ($\sim$2. 6\%).

Video Classification

KE-RCNN: Unifying Knowledge based Reasoning into Part-level Attribute Parsing

1 code implementation21 Jun 2022 Xuanhan Wang, Jingkuan Song, Xiaojia Chen, Lechao Cheng, Lianli Gao, Heng Tao Shen

In this article, we propose a Knowledge Embedded RCNN (KE-RCNN) to identify attributes by leveraging rich knowledges, including implicit knowledge (e. g., the attribute ``above-the-hip'' for a shirt requires visual/geometry relations of shirt-hip) and explicit knowledge (e. g., the part of ``shorts'' cannot have the attribute of ``hoodie'' or ``lining'').

Cross-Modality High-Frequency Transformer for MR Image Super-Resolution

no code implementations29 Mar 2022 Chaowei Fang, Dingwen Zhang, Liang Wang, Yulun Zhang, Lechao Cheng, Junwei Han

Improving the resolution of magnetic resonance (MR) image data is critical to computer-aided diagnosis and brain function analysis.

Image Super-Resolution Vocal Bursts Intensity Prediction

Weakly Supervised Semantic Segmentation via Alternative Self-Dual Teaching

no code implementations17 Dec 2021 Dingwen Zhang, Wenyuan Zeng, Guangyu Guo, Chaowei Fang, Lechao Cheng, Ming-Ming Cheng, Junwei Han

Current weakly supervised semantic segmentation (WSSS) frameworks usually contain the separated mask-refinement model and the main semantic region mining model.

Knowledge Distillation Weakly supervised Semantic Segmentation +1

Edge-competing Pathological Liver Vessel Segmentation with Limited Labels

1 code implementation1 Aug 2021 Zunlei Feng, Zhonghua Wang, Xinchao Wang, Xiuming Zhang, Lechao Cheng, Jie Lei, Yuexuan Wang, Mingli Song

The diagnosis of MVI needs discovering the vessels that contain hepatocellular carcinoma cells and counting their number in each vessel, which depends heavily on experiences of the doctor, is largely subjective and time-consuming.

whole slide images

Visual Boundary Knowledge Translation for Foreground Segmentation

1 code implementation1 Aug 2021 Zunlei Feng, Lechao Cheng, Xinchao Wang, Xiang Wang, Yajie Liu, Xiangtong Du, Mingli Song

To this end, we propose a Translation Segmentation Network (Trans-Net), which comprises a segmentation network and two boundary discriminators.

Foreground Segmentation Image Segmentation +2

Boundary Knowledge Translation based Reference Semantic Segmentation

no code implementations1 Aug 2021 Lechao Cheng, Zunlei Feng, Xinchao Wang, Ya Jie Liu, Jie Lei, Mingli Song

In this paper, we introduce a novel Reference semantic segmentation Network (Ref-Net) to conduct visual boundary knowledge translation.

Semantic Segmentation Translation

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