most citedCompressing Models with Few Samples: Mimicking then Replacing

2 citations · 6 across the 6 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV2023

Quantized Feature Distillation for Network Quantization

Ke Zhu, Yin-Yin He, Jianxin Wu

Neural network quantization aims to accelerate and trim full-precision neural network models by using low bit approximations. Methods adopting the quantization aware training (QAT)…

cs.CV2023★ 1 cited

Instance-based Max-margin for Practical Few-shot Recognition

Minghao Fu, Ke Zhu, Jianxin Wu

In order to mimic the human few-shot learning (FSL) ability better and to make FSL closer to real-world applications, this paper proposes a practical FSL (pFSL) setting. pFSL is ba…

cs.CV2023★ 1 cited

No One Left Behind: Improving the Worst Categories in Long-Tailed Learning

Yingxiao Du, Jianxin Wu

Unlike the case when using a balanced training dataset, the per-class recall (i.e., accuracy) of neural networks trained with an imbalanced dataset are known to vary a lot from cat…

cs.CV2022★ 1 cited

Synergistic Self-supervised and Quantization Learning

Yun-Hao Cao, Peiqin Sun, Yechang Huang +2

With the success of self-supervised learning (SSL), it has become a mainstream paradigm to fine-tune from self-supervised pretrained models to boost the performance on downstream t…

cs.CV2022

Worst Case Matters for Few-Shot Recognition

Minghao Fu, Yun-Hao Cao, Jianxin Wu

Few-shot recognition learns a recognition model with very few (e.g., 1 or 5) images per category, and current few-shot learning methods focus on improving the average accuracy over…

cs.CV2022★ 1 cited

R2-D2: Repetitive Reprediction Deep Decipher for Semi-Supervised Deep Learning

Guo-Hua Wang, Jianxin Wu

Most recent semi-supervised deep learning (deep SSL) methods used a similar paradigm: use network predictions to update pseudo-labels and use pseudo-labels to update network parame…