15 citations · 53 across the 13 of their papers we have counts for
13 papers
The Tree Loss: Improving Generalization with Many Classes
Yujie Wang, Mike Izbicki
Multi-class classification problems often have many semantically similar classes. For example, 90 of ImageNet's 1000 classes are for different breeds of dog. We should expect that…
PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection
Gang Li, Xiang Li, Yujie Wang +3
In this paper, we delve into two key techniques in Semi-Supervised Object Detection (SSOD), namely pseudo labeling and consistency training. We observe that these two techniques cu…
Knowledge Distillation for Object Detection via Rank Mimicking and Prediction-guided Feature Imitation
Gang Li, Xiang Li, Yujie Wang +3
Knowledge Distillation (KD) is a widely-used technology to inherit information from cumbersome teacher models to compact student models, consequently realizing model compression an…
Global Context with Discrete Diffusion in Vector Quantised Modelling for Image Generation
Minghui Hu, Yujie Wang, Tat-Jen Cham +2
The integration of Vector Quantised Variational AutoEncoder (VQ-VAE) with autoregressive models as generation part has yielded high-quality results on image generation. However, th…
One to Transfer All: A Universal Transfer Framework for Vision Foundation Model with Few Data
Yujie Wang, Junqin Huang, Mengya Gao +4
The foundation model is not the last chapter of the model production pipeline. Transferring with few data in a general way to thousands of downstream tasks is becoming a trend of t…
Hierarchical Segment-based Optimization for SLAM
Yuxin Tian, Yujie Wang, Ming Ouyang +1
This paper presents a hierarchical segment-based optimization method for Simultaneous Localization and Mapping (SLAM) system. First we propose a reliable trajectory segmentation me…
INTERN: A New Learning Paradigm Towards General Vision
Jing Shao, Siyu Chen, Yangguang Li +24
Enormous waves of technological innovations over the past several years, marked by the advances in AI technologies, are profoundly reshaping the industry and the society. However,…
Fixing the Teacher-Student Knowledge Discrepancy in Distillation
Jiangfan Han, Mengya Gao, Yujie Wang +3
Training a small student network with the guidance of a larger teacher network is an effective way to promote the performance of the student. Despite the different types, the guide…
Differentiable Network Adaption with Elastic Search Space
Shaopeng Guo, Yujie Wang, Kun Yuan +1
In this paper we propose a novel network adaption method called Differentiable Network Adaption (DNA), which can adapt an existing network to a specific computation budget by adjus…
A Collaborative Visual SLAM Framework for Service Robots
Ming Ouyang, Xuesong Shi, Yujie Wang +5
We present a collaborative visual simultaneous localization and mapping (SLAM) framework for service robots. With an edge server maintaining a map database and performing global op…
DMCP: Differentiable Markov Channel Pruning for Neural Networks
Shaopeng Guo, Yujie Wang, Quanquan Li +1
Recent works imply that the channel pruning can be regarded as searching optimal sub-structure from unpruned networks. However, existing works based on this observation require tra…
Improvement of an Approximated Self-Improving Sorter and Error Analysis of its Estimated Entropy
Yujie Wang
The self-improving sorter proposed by Ailon et al. consists of two phases: a relatively long training phase and rapid operation phase. In this study, we have developed an efficient…
Skin Lesion Segmentation Using Atrous Convolution via DeepLab v3
Yujie Wang, Simon Sun, Jahow Yu +1
As melanoma diagnoses increase across the US, automated efforts to identify malignant lesions become increasingly of interest to the research community. Segmentation of dermoscopic…