1k citations · 3.9k across the 81 of their papers we have counts for
7 papers · 1 filter
Gradient Correction beyond Gradient Descent
Zefan Li, Bingbing Ni, Teng Li +2
The great success neural networks have achieved is inseparable from the application of gradient-descent (GD) algorithms. Based on GD, many variant algorithms have emerged to improv…
Energy Attack: On Transferring Adversarial Examples
Ruoxi Shi, Borui Yang, Yangzhou Jiang +2
In this work we propose Energy Attack, a transfer-based black-box -adversarial attack. The attack is parameter-free and does not require gradient approximation. In partic…
Self-supervised Graph-level Representation Learning with Local and Global Structure
Minghao Xu, Hang Wang, Bingbing Ni +2
This paper studies unsupervised/self-supervised whole-graph representation learning, which is critical in many tasks such as molecule properties prediction in drug and material dis…
MIA-Prognosis: A Deep Learning Framework to Predict Therapy Response
Jiancheng Yang, Jiajun Chen, Kaiming Kuang +3
Predicting clinical outcome is remarkably important but challenging. Research efforts have been paid on seeking significant biomarkers associated with the therapy response or/and p…
Evaluating and Boosting Uncertainty Quantification in Classification
Xiaoyang Huang, Jiancheng Yang, Linguo Li +3
Emergence of artificial intelligence techniques in biomedical applications urges the researchers to pay more attention on the uncertainty quantification (UQ) in machine-assisted me…
Exploiting Channel Similarity for Accelerating Deep Convolutional Neural Networks
Yunxiang Zhang, Chenglong Zhao, Bingbing Ni +2
To address the limitations of existing magnitude-based pruning algorithms in cases where model weights or activations are of large and similar magnitude, we propose a novel perspec…
Image Matching via Loopy RNN
Donghao Luo, Bingbing Ni, Yichao Yan +1
Most existing matching algorithms are one-off algorithms, i.e., they usually measure the distance between the two image feature representation vectors for only one time. In contras…