Search Results for author:
Found 12 papers, 10 papers with code
Tackling Ambiguity from Perspective of Uncertainty Inference and Affinity Diversification for Weakly Supervised Semantic Segmentation
When activating class objects, we argue that the false activation stems from the bias to the ambiguous regions during the feature extraction.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentation
In this work, we devise a 'Separate and Conquer' scheme SeCo to tackle this issue from dimensions of image space and feature space.
PointMBF: A Multi-scale Bidirectional Fusion Network for Unsupervised RGB-D Point Cloud Registration
Point cloud registration is a task to estimate the rigid transformation between two unaligned scans, which plays an important role in many computer vision applications.
The Rise of AI Language Pathologists: Exploring Two-level Prompt Learning for Few-shot Weakly-supervised Whole Slide Image Classification
Our approach incorporates the utilization of GPT-4 in a question-and-answer mode to obtain language prior knowledge at both the instance and bag levels, which are then integrated into the instance and bag level language prompts.
Robust Point Cloud Registration Framework Based on Deep Graph Matching(TPAMI Version)
In this paper, we propose a novel deep graph matching-based framework for point cloud registration.
Boosting Point-BERT by Multi-choice Tokens
Masked language modeling (MLM) has become one of the most successful self-supervised pre-training task.
POS-BERT: Point Cloud One-Stage BERT Pre-Training
We propose to use the dynamically updated momentum encoder as the tokenizer, which is updated and outputs the dynamic supervision signal along with the training process.
Distillation with Contrast is All You Need for Self-Supervised Point Cloud Representation Learning
Especially, we develop a variant of ViT for 3D point cloud feature extraction, which also achieves comparable results with existing backbones when combined with our framework, and visualization of the attention maps show that our model does understand the point cloud by combining the global shape information and multiple local structural information, which is consistent with the inspiration of our representation learning method.
Multi-View Partial (MVP) Point Cloud Challenge 2021 on Completion and Registration: Methods and Results
Based on the MVP dataset, this paper reports methods and results in the Multi-View Partial Point Cloud Challenge 2021 on Completion and Registration.
DSPoint: Dual-scale Point Cloud Recognition with High-frequency Fusion
We reverse the conventional design of applying convolution on voxels and attention to points.
Ranked #36 on
3D Part Segmentation
on ShapeNet-Part
A Learnable Self-supervised Task for Unsupervised Domain Adaptation on Point Clouds
In the UDA architecture, an encoder is shared between the networks for the self-supervised task and the main task of point cloud classification or segmentation, so that the encoder can be trained to extract features suitable for both the source and the target domain data.
Robust Point Cloud Registration Framework Based on Deep Graph Matching
In this paper, we propose a novel deep graph matchingbased framework for point cloud registration.
