243 citations · 348 across the 13 of their papers we have counts for
13 papers
Dual Feature Decoupling for Fine-Grained OOD Detection
Xiaokun Li, Yaping Huang, Qingji Guan
Out-of-distribution detection (OOD) is an indispensable technique when applying machine learning models to real-world scenarios. Most existing OOD detection methods have been devel…
Enhancing Gaze Reasoning in Vision Foundation Models for Gaze Following
Shijing Wang, Yaping Huang, Chaoqun Cui +4
Gaze following requires both scene understanding and gaze reasoning to localize the gaze target of an in-scene person. Recently, vision foundation models (VFMs) have demonstrated s…
The Treasure Beneath Multiple Annotations: An Uncertainty-aware Edge Detector
Caixia Zhou, Yaping Huang, Mengyang Pu +3
Deep learning-based edge detectors heavily rely on pixel-wise labels which are often provided by multiple annotators. Existing methods fuse multiple annotations using a simple voti…
Uncertainty-Driven Action Quality Assessment
Caixia Zhou, Yaping Huang
Automatic action quality assessment (AQA) has attracted increasing attention due to its wide applications. However, most existing AQA methods employ deterministic models to predict…
EDTER: Edge Detection with Transformer
Mengyang Pu, Yaping Huang, Yuming Liu +2
Convolutional neural networks have made significant progresses in edge detection by progressively exploring the context and semantic features. However, local details are gradually…
RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depth
Mengyang Pu, Yaping Huang, Qingji Guan +1
As a fundamental building block in computer vision, edges can be categorised into four types according to the discontinuity in surface-Reflectance, Illumination, surface-Normal or…
Learning from Pixel-Level Label Noise: A New Perspective for Semi-Supervised Semantic Segmentation
Rumeng Yi, Yaping Huang, Qingji Guan +2
This paper addresses semi-supervised semantic segmentation by exploiting a small set of images with pixel-level annotations (strong supervisions) and a large set of images with onl…
Transform consistency for learning with noisy labels
Rumeng Yi, Yaping Huang
It is crucial to distinguish mislabeled samples for dealing with noisy labels. Previous methods such as Coteaching and JoCoR introduce two different networks to select clean sample…
Classification-driven Single Image Dehazing
Yanting Pei, Yaping Huang, Xingyuan Zhang
Most existing dehazing algorithms often use hand-crafted features or Convolutional Neural Networks (CNN)-based methods to generate clear images using pixel-level Mean Square Error…
Object Discovery From a Single Unlabeled Image by Mining Frequent Itemset With Multi-scale Features
Runsheng Zhang, Yaping Huang, Mengyang Pu +4
TThe goal of our work is to discover dominant objects in a very general setting where only a single unlabeled image is given. This is far more challenge than typical co-localizatio…
Does Haze Removal Help CNN-based Image Classification?
Yanting Pei, Yaping Huang, Qi Zou +2
Hazy images are common in real scenarios and many dehazing methods have been developed to automatically remove the haze from images. Typically, the goal of image dehazing is to pro…
Effects of Image Degradations to CNN-based Image Classification
Yanting Pei, Yaping Huang, Qi Zou +3
Just like many other topics in computer vision, image classification has achieved significant progress recently by using deep-learning neural networks, especially the Convolutional…
Diagnose like a Radiologist: Attention Guided Convolutional Neural Network for Thorax Disease Classification
Qingji Guan, Yaping Huang, Zhun Zhong +3
This paper considers the task of thorax disease classification on chest X-ray images. Existing methods generally use the global image as input for network learning. Such a strategy…