490 citations · 999 across the 19 of their papers we have counts for
4 papers · 1 filter
Balancing Logit Variation for Long-tailed Semantic Segmentation
Yuchao Wang, Jingjing Fei, Haochen Wang +5
Semantic segmentation usually suffers from a long-tail data distribution. Due to the imbalanced number of samples across categories, the features of those tail classes may get sque…
Phonetic and Prosody-aware Self-supervised Learning Approach for Non-native Fluency Scoring
Kaiqi Fu, Shaojun Gao, Shuju Shi +3
Speech fluency/disfluency can be evaluated by analyzing a range of phonetic and prosodic features. Deep neural networks are commonly trained to map fluency-related features into th…
Correlational Image Modeling for Self-Supervised Visual Pre-Training
Wei Li, Jiahao Xie, Chen Change Loy
We introduce Correlational Image Modeling (CIM), a novel and surprisingly effective approach to self-supervised visual pre-training. Our CIM performs a simple pretext task: we rand…
Objective Evaluation-based High-efficiency Learning Framework for Hyperspectral Image Classification
Xuming Zhang, Jian Yan, Jia Tian +3
Deep learning methods have been successfully applied to hyperspectral image (HSI) classification with remarkable performance. Because of limited labelled HSI data, earlier studies…