b'Yinpeng Chen'

research

∙ 02/27/2023

Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Label-Efficient Representations

Recently, both Contrastive Learning (CL) and Mask Image Modeling (MIM) d...

0 Ziyu Jiang, et al. ∙

research

∙ 02/17/2023

Find Beauty in the Rare: Contrastive Composition Feature Clustering for Nontrivial Cropping Box Regression

Automatic image cropping algorithms aim to recompose images like human-b...

0 Zhiyu Pan, et al. ∙

research

∙ 11/23/2022

Self-Supervised Learning based on Heat Equation

This paper presents a new perspective of self-supervised learning based ...

0 Yinpeng Chen, et al. ∙

research

∙ 07/31/2022

Design What You Desire: Icon Generation from Orthogonal Application and Theme Labels

Generative adversarial networks (GANs) have been trained to be professio...

0 Yinpeng Chen, et al. ∙

research

∙ 07/07/2022

Should All Proposals be Treated Equally in Object Detection?

The complexity-precision trade-off of an object detector is a critical p...

9 Yunsheng Li, et al. ∙

research

∙ 06/07/2022

Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embedding

Leveraging large-scale data can introduce performance gains on many comp...

9 Lingchen Meng, et al. ∙

research

∙ 05/10/2022

Reduce Information Loss in Transformers for Pluralistic Image Inpainting

Transformers have achieved great success in pluralistic image inpainting...

10 Qiankun Liu, et al. ∙

research

∙ 04/28/2022

An Intriguing Property of Geophysics Inversion

Inversion techniques are widely used to reconstruct subsurface physical ...

0 Yinan Feng, et al. ∙

research

∙ 04/20/2022

Residual Mixture of Experts

Mixture of Experts (MoE) is able to scale up vision transformers effecti...

3 Lemeng Wu, et al. ∙

research

∙ 03/10/2022

The Overlooked Classifier in Human-Object Interaction Recognition

Human-Object Interaction (HOI) recognition is challenging due to two fac...

0 Ying Jin, et al. ∙

research

∙ 02/03/2022

Exploring Multi-physics with Extremely Weak Supervision

Multi-physical inversion plays a critical role in geophysics. It has bee...

0 Shihang Feng, et al. ∙

research

∙ 12/13/2021

Decoupling Object Detection from Human-Object Interaction Recognition

We propose DEFR, a DEtection-FRee method to recognize Human-Object Inter...

0 Ying Jin, et al. ∙

research

∙ 12/12/2021

Improving Vision Transformers for Incremental Learning

This paper studies using Vision Transformers (ViT) in class incremental ...

0 Pei Yu, et al. ∙

research

∙ 10/18/2021

Unsupervised Finetuning

This paper studies "unsupervised finetuning", the symmetrical problem of...

14 Suichan Li, et al. ∙

research

∙ 10/14/2021

Unsupervised Learning of Full-Waveform Inversion: Connecting CNN and Partial Differential Equation in a Loop

This paper investigates unsupervised learning of Full-Waveform Inversion...

12 Peng Jin, et al. ∙

research

∙ 08/12/2021

Mobile-Former: Bridging MobileNet and Transformer

We present Mobile-Former, a parallel design of MobileNet and Transformer...

28 Yinpeng Chen, et al. ∙

research

∙ 08/12/2021

MicroNet: Improving Image Recognition with Extremely Low FLOPs

This paper aims at addressing the problem of substantial performance deg...

19 Yunsheng Li, et al. ∙

research

∙ 07/27/2021

Is Object Detection Necessary for Human-Object Interaction Recognition?

This paper revisits human-object interaction (HOI) recognition at image ...

0 Ying Jin, et al. ∙

research

∙ 07/26/2021

Improve Unsupervised Pretraining for Few-label Transfer

Unsupervised pretraining has achieved great success and many recent work...

7 Suichan Li, et al. ∙

research

∙ 06/15/2021

Dynamic Head: Unifying Object Detection Heads with Attentions

The complex nature of combining localization and classification in objec...

3 Xiyang Dai, et al. ∙

research

∙ 03/19/2021

Dynamic Transfer for Multi-Source Domain Adaptation

Recent works of multi-source domain adaptation focus on learning a domai...

0 Yunsheng Li, et al. ∙

research

∙ 03/15/2021

Revisiting Dynamic Convolution via Matrix Decomposition

Recent research in dynamic convolution shows substantial performance boo...

18 Yunsheng Li, et al. ∙

research

∙ 02/21/2021

Weak NAS Predictors Are All You Need

Neural Architecture Search (NAS) finds the best network architecture by ...

9 Junru Wu, et al. ∙

research

∙ 12/10/2020

Are Fewer Labels Possible for Few-shot Learning?

Few-shot learning is challenging due to its very limited data and labels...

12 Suichan Li, et al. ∙

research

∙ 11/24/2020

MicroNet: Towards Image Recognition with Extremely Low FLOPs

In this paper, we present MicroNet, which is an efficient convolutional ...

5 Yunsheng Li, et al. ∙

research

∙ 03/27/2020

DA-NAS: Data Adapted Pruning for Efficient Neural Architecture Search

Efficient search is a core issue in Neural Architecture Search (NAS). It...

0 Xiyang Dai, et al. ∙

research

∙ 03/22/2020

Dynamic ReLU

Rectified linear units (ReLU) are commonly used in deep neural networks....

0 Yinpeng Chen, et al. ∙

research

∙ 12/07/2019

Dynamic Convolution: Attention over Convolution Kernels

Light-weight convolutional neural networks (CNNs) suffer performance deg...

1 Yinpeng Chen, et al. ∙

research

∙ 11/17/2019

Unsupervised Domain Adaptation for Object Detection via Cross-Domain Semi-Supervised Learning

Current state-of-the-art object detectors can have significant performan...

47 Fuxun Yu, et al. ∙

research

∙ 07/11/2019

Cross-Domain Complementary Learning with Synthetic Data for Multi-Person Part Segmentation

The success of supervised deep learning depends on the training labels. ...

1 Kevin Lin, et al. ∙

research

∙ 05/30/2019

Large Scale Incremental Learning

Modern machine learning suffers from catastrophic forgetting when learni...

0 Yue Wu, et al. ∙

research

∙ 04/13/2019

Rethinking Classification and Localization in R-CNN

Modern R-CNN based detectors share the RoI feature extractor head for bo...

0 Yue Wu, et al. ∙

research

∙ 02/02/2018

Incremental Classifier Learning with Generative Adversarial Networks

In this paper, we address the incremental classifier learning problem, w...

0 Yue Wu, et al. ∙

research

∙ 05/28/2017

Person Depth ReID: Robust Person Re-identification with Commodity Depth Sensors

This work targets person re-identification (ReID) from depth sensors suc...

0 Nikolaos Karianakis, et al. ∙

Yinpeng Chen

Featured Co-authors