 |
 Collaborative Distillation for Top-N RecommendationIndustrial Conference on Data Mining (IDM), 2019 |
 Depth-wise Decomposition for Accelerating Separable Convolutions in
Efficient Convolutional Neural NetworksAdvances in Artificial Intelligence and Machine Learning (AAIML), 2019 |
 Directed-Weighting Group Lasso for Eltwise Blocked CNN PruningBritish Machine Vision Conference (BMVC), 2019 |
 Positive-Unlabeled Compression on the CloudNeural Information Processing Systems (NeurIPS), 2019 |
 Sparse Deep Neural Network Graph ChallengeIEEE Conference on High Performance Extreme Computing (HPEC), 2019 |
 Adaptative Inference Cost With Convolutional Neural Mixture ModelsIEEE International Conference on Computer Vision (ICCV), 2019 |
 Distilled Siamese Networks for Visual TrackingIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019 |
 Scalable Model Compression by Entropy Penalized ReparameterizationInternational Conference on Learning Representations (ICLR), 2019 |
 BlockSwap: Fisher-guided Block Substitution for Network Compression on a
BudgetInternational Conference on Learning Representations (ICLR), 2019 |
 Online Filter Clustering and Pruning for Efficient ConvnetsInternational Conference on Information Photonics (ICIP), 2018 |
 Dynamic Neural Network Channel Execution for Efficient TrainingBritish Machine Vision Conference (BMVC), 2019 |
 RadiX-Net: Structured Sparse Matrices for Deep Neural NetworksIEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum (IPDPS), 2019 |
 |
 TrIMS: Transparent and Isolated Model Sharing for Low Latency Deep
LearningInference in Function as a Service EnvironmentsIEEE International Conference on Cloud Computing (CLOUD), 2018 |
 Multi-layer Pruning Framework for Compressing Single Shot MultiBox
DetectorIEEE Workshop/Winter Conference on Applications of Computer Vision (WACV), 2018 |
 Filter Distillation for Network CompressionIEEE Workshop/Winter Conference on Applications of Computer Vision (WACV), 2018 |
 Restructuring Batch Normalization to Accelerate CNN TrainingUSENIX workshop on Tackling computer systems problems with machine learning techniques (SPMLT), 2018 |
