Picture for Haohang Xu

Haohang Xu

Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation

Add code
Nov 29, 2023
Viaarxiv icon

Masked Autoencoders are Robust Data Augmentors

Add code
Jun 10, 2022
Figure 1 for Masked Autoencoders are Robust Data Augmentors
Figure 2 for Masked Autoencoders are Robust Data Augmentors
Figure 3 for Masked Autoencoders are Robust Data Augmentors
Figure 4 for Masked Autoencoders are Robust Data Augmentors
Viaarxiv icon

Semantic-Aware Generation for Self-Supervised Visual Representation Learning

Add code
Nov 25, 2021
Figure 1 for Semantic-Aware Generation for Self-Supervised Visual Representation Learning
Figure 2 for Semantic-Aware Generation for Self-Supervised Visual Representation Learning
Figure 3 for Semantic-Aware Generation for Self-Supervised Visual Representation Learning
Figure 4 for Semantic-Aware Generation for Self-Supervised Visual Representation Learning
Viaarxiv icon

Motion-aware Self-supervised Video Representation Learning via Foreground-background Merging

Add code
Sep 30, 2021
Figure 1 for Motion-aware Self-supervised Video Representation Learning via Foreground-background Merging
Figure 2 for Motion-aware Self-supervised Video Representation Learning via Foreground-background Merging
Figure 3 for Motion-aware Self-supervised Video Representation Learning via Foreground-background Merging
Figure 4 for Motion-aware Self-supervised Video Representation Learning via Foreground-background Merging
Viaarxiv icon

Bag of Instances Aggregation Boosts Self-supervised Learning

Add code
Jul 04, 2021
Figure 1 for Bag of Instances Aggregation Boosts Self-supervised Learning
Figure 2 for Bag of Instances Aggregation Boosts Self-supervised Learning
Figure 3 for Bag of Instances Aggregation Boosts Self-supervised Learning
Figure 4 for Bag of Instances Aggregation Boosts Self-supervised Learning
Viaarxiv icon

Multi-dataset Pretraining: A Unified Model for Semantic Segmentation

Add code
Jun 08, 2021
Figure 1 for Multi-dataset Pretraining: A Unified Model for Semantic Segmentation
Figure 2 for Multi-dataset Pretraining: A Unified Model for Semantic Segmentation
Figure 3 for Multi-dataset Pretraining: A Unified Model for Semantic Segmentation
Figure 4 for Multi-dataset Pretraining: A Unified Model for Semantic Segmentation
Viaarxiv icon

Semi-supervised Contrastive Learning with Similarity Co-calibration

Add code
May 16, 2021
Figure 1 for Semi-supervised Contrastive Learning with Similarity Co-calibration
Figure 2 for Semi-supervised Contrastive Learning with Similarity Co-calibration
Figure 3 for Semi-supervised Contrastive Learning with Similarity Co-calibration
Figure 4 for Semi-supervised Contrastive Learning with Similarity Co-calibration
Viaarxiv icon

Hierarchical Semantic Aggregation for Contrastive Representation Learning

Add code
Dec 04, 2020
Figure 1 for Hierarchical Semantic Aggregation for Contrastive Representation Learning
Figure 2 for Hierarchical Semantic Aggregation for Contrastive Representation Learning
Figure 3 for Hierarchical Semantic Aggregation for Contrastive Representation Learning
Figure 4 for Hierarchical Semantic Aggregation for Contrastive Representation Learning
Viaarxiv icon

K-Shot Contrastive Learning of Visual Features with Multiple Instance Augmentations

Add code
Jul 27, 2020
Figure 1 for K-Shot Contrastive Learning of Visual Features with Multiple Instance Augmentations
Figure 2 for K-Shot Contrastive Learning of Visual Features with Multiple Instance Augmentations
Figure 3 for K-Shot Contrastive Learning of Visual Features with Multiple Instance Augmentations
Figure 4 for K-Shot Contrastive Learning of Visual Features with Multiple Instance Augmentations
Viaarxiv icon

FLAT: Few-Shot Learning via Autoencoding Transformation Regularizers

Add code
Dec 29, 2019
Figure 1 for FLAT: Few-Shot Learning via Autoencoding Transformation Regularizers
Figure 2 for FLAT: Few-Shot Learning via Autoencoding Transformation Regularizers
Figure 3 for FLAT: Few-Shot Learning via Autoencoding Transformation Regularizers
Figure 4 for FLAT: Few-Shot Learning via Autoencoding Transformation Regularizers
Viaarxiv icon