Baohua Lai
YOU?
Author Swipe
View article: HICL: Hashtag-Driven In-Context Learning for Social Media Natural Language Understanding
HICL: Hashtag-Driven In-Context Learning for Social Media Natural Language Understanding Open
Natural language understanding (NLU) is integral to various social media applications. However, existing NLU models rely heavily on context for semantic learning, resulting in compromised performance when faced with short and noisy social …
View article: RAIS: Robust and Accurate Interactive Segmentation via Continual Learning
RAIS: Robust and Accurate Interactive Segmentation via Continual Learning Open
Interactive image segmentation aims at segmenting a target region through a way of human-computer interaction. Recent works based on deep learning have achieved excellent performance, while most of them focus on improving the accuracy of t…
View article: EISeg: An Efficient Interactive Segmentation Tool based on PaddlePaddle
EISeg: An Efficient Interactive Segmentation Tool based on PaddlePaddle Open
In recent years, the rapid development of deep learning has brought great advancements to image and video segmentation methods based on neural networks. However, to unleash the full potential of such models, large numbers of high-quality a…
View article: PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System
PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System Open
Optical character recognition (OCR) technology has been widely used in various scenes, as shown in Figure 1. Designing a practical OCR system is still a meaningful but challenging task. In previous work, considering the efficiency and accu…
View article: PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model
PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model Open
Real-world applications have high demands for semantic segmentation methods. Although semantic segmentation has made remarkable leap-forwards with deep learning, the performance of real-time methods is not satisfactory. In this work, we pr…
View article: PP-YOLOE: An evolved version of YOLO
PP-YOLOE: An evolved version of YOLO Open
In this report, we present PP-YOLOE, an industrial state-of-the-art object detector with high performance and friendly deployment. We optimize on the basis of the previous PP-YOLOv2, using anchor-free paradigm, more powerful backbone and n…
View article: PP-HumanSeg: Connectivity-Aware Portrait Segmentation with a Large-Scale Teleconferencing Video Dataset
PP-HumanSeg: Connectivity-Aware Portrait Segmentation with a Large-Scale Teleconferencing Video Dataset Open
As the COVID-19 pandemic rampages across the world, the demands of video conferencing surge. To this end, real-time portrait segmentation becomes a popular feature to replace backgrounds of conferencing participants. While feature-rich dat…
View article: PP-MSVSR: Multi-Stage Video Super-Resolution
PP-MSVSR: Multi-Stage Video Super-Resolution Open
Different from the Single Image Super-Resolution(SISR) task, the key for Video Super-Resolution(VSR) task is to make full use of complementary information across frames to reconstruct the high-resolution sequence. Since images from differe…
View article: PP-PicoDet: A Better Real-Time Object Detector on Mobile Devices
PP-PicoDet: A Better Real-Time Object Detector on Mobile Devices Open
The better accuracy and efficiency trade-off has been a challenging problem in object detection. In this work, we are dedicated to studying key optimizations and neural network architecture choices for object detection to improve accuracy …
View article: EdgeFlow: Achieving Practical Interactive Segmentation with Edge-Guided Flow
EdgeFlow: Achieving Practical Interactive Segmentation with Edge-Guided Flow Open
High-quality training data play a key role in image segmentation tasks. Usually, pixel-level annotations are expensive, laborious and time-consuming for the large volume of training data. To reduce labelling cost and improve segmentation q…
View article: PaddleSeg: A High-Efficient Development Toolkit for Image Segmentation
PaddleSeg: A High-Efficient Development Toolkit for Image Segmentation Open
Image Segmentation plays an essential role in computer vision and image processing with various applications from medical diagnosis to autonomous car driving. A lot of segmentation algorithms have been proposed for addressing specific prob…