1 citations · 2 across the 10 of their papers we have counts for
10 papers
Rethinking the Sample Relations for Few-Shot Classification
Guowei Yin, Sheng Huang, Luwen Huangfu +2
Feature quality is paramount for classification performance, particularly in few-shot scenarios. Contrastive learning, a widely adopted technique for enhancing feature quality, lev…
Category-Prompt Refined Feature Learning for Long-Tailed Multi-Label Image Classification
Jiexuan Yan, Sheng Huang, Nankun Mu +2
Real-world data consistently exhibits a long-tailed distribution, often spanning multiple categories. This complexity underscores the challenge of content comprehension, particular…
SAM-MIL: A Spatial Contextual Aware Multiple Instance Learning Approach for Whole Slide Image Classification
Heng Fang, Sheng Huang, Wenhao Tang +2
Multiple Instance Learning (MIL) represents the predominant framework in Whole Slide Image (WSI) classification, covering aspects such as sub-typing, diagnosis, and beyond. Current…
Data Distribution Distilled Generative Model for Generalized Zero-Shot Recognition
Yijie Wang, Mingjian Hong, Luwen Huangfu +1
In the realm of Zero-Shot Learning (ZSL), we address biases in Generalized Zero-Shot Learning (GZSL) models, which favor seen data. To counter this, we introduce an end-to-end gene…
Kernel Inversed Pyramidal Resizing Network for Efficient Pavement Distress Recognition
Rong Qin, Luwen Huangfu, Devon Hood +2
Pavement Distress Recognition (PDR) is an important step in pavement inspection and can be powered by image-based automation to expedite the process and reduce labor costs. Pavemen…
PicT: A Slim Weakly Supervised Vision Transformer for Pavement Distress Classification
Wenhao Tang, Sheng Huang, Xiaoxian Zhang +1
Automatic pavement distress classification facilitates improving the efficiency of pavement maintenance and reducing the cost of labor and resources. A recently influential branch…
Boosting Multi-Label Image Classification with Complementary Parallel Self-Distillation
Jiazhi Xu, Sheng Huang, Fengtao Zhou +3
Multi-Label Image Classification (MLIC) approaches usually exploit label correlations to achieve good performance. However, emphasizing correlation like co-occurrence may overlook…
Weakly Supervised Patch Label Inference Networks for Efficient Pavement Distress Detection and Recognition in the Wild
Sheng Huang, Wenhao Tang, Guixin Huang +2
Automatic image-based pavement distress detection and recognition are vital for pavement maintenance and management. However, existing deep learning-based methods largely omit the…
An Iteratively Optimized Patch Label Inference Network for Automatic Pavement Distress Detection
Wenhao Tang, Sheng Huang, Qiming Zhao +2
We present a novel deep learning framework named the Iteratively Optimized Patch Label Inference Network (IOPLIN) for automatically detecting various pavement distresses that are n…
Sparse Graph-based Transduction for Image Classification
Sheng Huang, Dan Yang, Jia Zhou +2
Motivated by the remarkable successes of Graph-based Transduction (GT) and Sparse Representation (SR), we present a novel Classifier named Sparse Graph-based Classifier (SGC) for i…