Picture for Zhong-Yu Li

Zhong-Yu Li

Enhancing Representations through Heterogeneous Self-Supervised Learning

Add code
Oct 08, 2023
Figure 1 for Enhancing Representations through Heterogeneous Self-Supervised Learning
Figure 2 for Enhancing Representations through Heterogeneous Self-Supervised Learning
Figure 3 for Enhancing Representations through Heterogeneous Self-Supervised Learning
Figure 4 for Enhancing Representations through Heterogeneous Self-Supervised Learning
Viaarxiv icon

RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks

Add code
Jun 15, 2022
Figure 1 for RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks
Figure 2 for RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks
Figure 3 for RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks
Figure 4 for RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks
Viaarxiv icon

Exploring Feature Self-relation for Self-supervised Transformer

Add code
Jun 10, 2022
Figure 1 for Exploring Feature Self-relation for Self-supervised Transformer
Figure 2 for Exploring Feature Self-relation for Self-supervised Transformer
Figure 3 for Exploring Feature Self-relation for Self-supervised Transformer
Figure 4 for Exploring Feature Self-relation for Self-supervised Transformer
Viaarxiv icon

Large-scale Unsupervised Semantic Segmentation

Add code
Jun 06, 2021
Figure 1 for Large-scale Unsupervised Semantic Segmentation
Figure 2 for Large-scale Unsupervised Semantic Segmentation
Figure 3 for Large-scale Unsupervised Semantic Segmentation
Figure 4 for Large-scale Unsupervised Semantic Segmentation
Viaarxiv icon

Global2Local: Efficient Structure Search for Video Action Segmentation

Add code
Jan 04, 2021
Figure 1 for Global2Local: Efficient Structure Search for Video Action Segmentation
Figure 2 for Global2Local: Efficient Structure Search for Video Action Segmentation
Figure 3 for Global2Local: Efficient Structure Search for Video Action Segmentation
Figure 4 for Global2Local: Efficient Structure Search for Video Action Segmentation
Viaarxiv icon