Search Results for author:
Found 17 papers, 8 papers with code
SwiftAvatar: Efficient Auto-Creation of Parameterized Stylized Character on Arbitrary Avatar Engines
To this end, we propose SwiftAvatar, a novel avatar auto-creation framework that is evidently superior to previous works.
Privileged Prior Information Distillation for Image Matting
Performance of trimap-free image matting methods is limited when trying to decouple the deterministic and undetermined regions, especially in the scenes where foregrounds are semantically ambiguous, chromaless, or high transmittance.
Mix-Teaching: A Simple, Unified and Effective Semi-Supervised Learning Framework for Monocular 3D Object Detection
Besides, by leveraging full training set and the additional 48K raw images of KITTI, it can further improve the MonoFlex by +4. 65% improvement on AP@0. 7 for car detection, reaching 18. 54% AP@0. 7, which ranks the 1st place among all monocular based methods on KITTI test leaderboard.
Towards Harnessing Feature Embedding for Robust Learning with Noisy Labels
To exploit this effect, the model prediction-based methods have been widely adopted, which aim to exploit the outputs of DNNs in the early stage of learning to correct noisy labels.
CLTS+: A New Chinese Long Text Summarization Dataset with Abstractive Summaries
In order to solve this problem, we paraphrase the reference summaries in CLTS, the Chinese Long Text Summarization dataset, correct errors of factual inconsistencies, and propose the first Chinese Long Text Summarization dataset with a high level of abstractiveness, CLTS+, which contains more than 180K article-summary pairs and is available online.
Multi-class Label Noise Learning via Loss Decomposition and Centroid Estimation
Further, by defining a new form of data centroid, we transform the recovery problem of a label-dependent part to a centroid estimation problem.
Lawin Transformer: Improving Semantic Segmentation Transformer with Multi-Scale Representations via Large Window Attention
In this paper, we succeed in introducing multi-scale representations into semantic segmentation ViT via window attention mechanism and further improves the performance and efficiency.
Ranked #3 on
Semantic Segmentation
on Cityscapes test
Self-Supervised Modality-Aware Multiple Granularity Pre-Training for RGB-Infrared Person Re-Identification
Much of that is due to the notorious modality bias training issue brought by the single-modality ImageNet pre-training, which might yield RGB-biased representations that severely hinder the cross-modality image retrieval.
Contrastive Learning
Cross-Modality Person Re-identification
+3
SamplingAug: On the Importance of Patch Sampling Augmentation for Single Image Super-Resolution
However, existing methods mostly train the DNNs on uniformly sampled LR-HR patch pairs, which makes them fail to fully exploit informative patches within the image.
Overfitting the Data: Compact Neural Video Delivery via Content-aware Feature Modulation
Internet video delivery has undergone a tremendous explosion of growth over the past few years.
ConTNet: Why not use convolution and transformer at the same time?
It is also worth pointing that, given identical strong data augmentations, the performance improvement of ConTNet is more remarkable than that of ResNet.
Contextual Graph Reasoning Networks
Graph Reasoning has shown great potential recently in modeling long-range dependencies, which are crucial for various computer vision tasks.
GINet: Graph Interaction Network for Scene Parsing
GI unit is further improved by the SC-loss to enhance the semantic representations over the exemplar-based semantic graph.
FGSD: A Dataset for Fine-Grained Ship Detection in High Resolution Satellite Images
To further promote the research of ship detection, we introduced a new fine-grained ship detection datasets, which is named as FGSD.
C-DLinkNet: considering multi-level semantic features for human parsing
Human parsing is an essential branch of semantic segmentation, which is a fine-grained semantic segmentation task to identify the constituent parts of human.
Improving Abstractive Text Summarization with History Aggregation
Recent neural sequence to sequence models have provided feasible solutions for abstractive summarization.
D-LinkNet: LinkNet with Pretrained Encoder and Dilated Convolution for High Resolution Satellite Imagery Road Extraction
Road extraction is a fundamental task in the field of remote sensing which has been a hot research topic in the past decade.
