Supervised ImageNet
Supervised ImageNet research focuses on improving image classification models by leveraging the massive ImageNet dataset. Current efforts concentrate on enhancing data curation strategies, developing more efficient training methods (including exploring alternative architectures like binary neural networks and leveraging self-supervised learning), and addressing challenges like dataset bias and the need for explainable AI. These advancements are crucial for improving the accuracy, efficiency, and trustworthiness of computer vision systems across various applications, from medical imaging to agricultural technology.
Papers
StraIT: Non-autoregressive Generation with Stratified Image Transformer
Shengju Qian, Huiwen Chang, Yuanzhen Li, Zizhao Zhang, Jiaya Jia, Han Zhang
Quality-aware Pre-trained Models for Blind Image Quality Assessment
Kai Zhao, Kun Yuan, Ming Sun, Mading Li, Xing Wen
Speeding Up EfficientNet: Selecting Update Blocks of Convolutional Neural Networks using Genetic Algorithm in Transfer Learning
Md. Mehedi Hasana, Muhammad Ibrahim, Md. Sawkat Ali
FacEDiM: A Face Embedding Distribution Model for Few-Shot Biometric Authentication of Cattle
Meshia Cédric Oveneke, Rucha Vaishampayan, Deogratias Lukamba Nsadisa, Jenny Ambukiyenyi Onya
FTSO: Effective NAS via First Topology Second Operator
Likang Wang, Lei Chen
Efficient Masked Autoencoders with Self-Consistency
Zhaowen Li, Yousong Zhu, Zhiyang Chen, Wei Li, Chaoyang Zhao, Rui Zhao, Ming Tang, Jinqiao Wang
Confidence and Dispersity Speak: Characterising Prediction Matrix for Unsupervised Accuracy Estimation
Weijian Deng, Yumin Suh, Stephen Gould, Liang Zheng
On Suppressing Range of Adaptive Stepsizes of Adam to Improve Generalisation Performance
Guoqiang Zhang
Resilient Binary Neural Network
Sheng Xu, Yanjing Li, Teli Ma, Mingbao Lin, Hao Dong, Baochang Zhang, Peng Gao, Jinhu Lv