Model Compression

Finding trainable sparse networks through Neural Tangent Transfer ICML 2020 FIREPruning: Learning-based Filter Pruning for Convolutional Neural Network Compression ACML 2020 Forward and Backward Information Retention for Accurate Binary Neural Networks CVPR 2020 Fractional Skipping: Towards Finer-Grained Dynamic CNN Inference AAAI 2020 FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training NeurIPS 2020 Frequency Domain Compact 3D Convolutional Neural Networks CVPR 2020 GAN Compression: Efficient Architectures for Interactive Conditional GANs CVPR 2020 GhostNet: More Features From Cheap Operations CVPR 2020 Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection ICML 2020 Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression CVPR 2020 Harmonious Coexistence of Structured Weight Pruning and Ternarization for Deep Neural Networks AAAI 2020 HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks NeurIPS 2020 Heterogeneous Knowledge Distillation Using Information Flow Modeling CVPR 2020 Hierarchical Knowledge Squeezed Adversarial Network Compression AAAI 2020 High Performance Natural Language Processing EMNLP 2020 HLHLp: Quantized Neural Networks Training for Reaching Flat Minima in Loss Surface AAAI 2020 HRank: Filter Pruning Using High-Rank Feature Map CVPR 2020 Improved Knowledge Distillation via Teacher Assistant AAAI 2020 Incremental Multi-Domain Learning with Network Latent Tensor Factorization AAAI 2020 Indirect Stochastic Gradient Quantization and Its Application in Distributed Deep Learning AAAI 2020 Information-Theoretic Understanding of Population Risk Improvement with Model Compression AAAI 2020 InstaNAS: Instance-Aware Neural Architecture Search AAAI 2020 Inter-Region Affinity Distillation for Road Marking Segmentation CVPR 2020 Iterative Compression of End-to-End ASR Model Using AutoML Interspeech 2020 Kernel Based Progressive Distillation for Adder Neural Networks NeurIPS 2020