← Optimization & Theory
Deep Learning › Optimization & Theory ›

Model Compression

1674 directly classified papers

Papers per year

Papers

CAKES: Channel-wise Automatic KErnel Shrinking for Efficient 3D Networks AAAI 2021
Distribution Adaptive INT8 Quantization for Training CNNs AAAI 2021
Optimizing Information Theory Based Bitwise Bottlenecks for Efficient Mixed-Precision Activation Quantization AAAI 2021
MiniSeg: An Extremely Minimum Network for Efficient COVID-19 Segmentation AAAI 2021
Stochastic Precision Ensemble: Self-Knowledge Distillation for Quantized Deep Neural Networks AAAI 2021
Towards Efficient Tensor Decomposition-Based DNN Model Compression With Optimization Framework CVPR 2021
QPP: Real-Time Quantization Parameter Prediction for Deep Neural Networks CVPR 2021
Continual Learning via Bit-Level Information Preserving CVPR 2021
Content-Aware GAN Compression CVPR 2021
Effective Sparsification of Neural Networks With Global Sparsity Constraint CVPR 2021
DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for Deep Neural Networks CVPR 2021
Learnable Companding Quantization for Accurate Low-Bit Neural Networks CVPR 2021
BCNet: Searching for Network Width With Bilaterally Coupled Network CVPR 2021
Permute, Quantize, and Fine-Tune: Efficient Compression of Neural Networks CVPR 2021
Binary Graph Neural Networks CVPR 2021
RaScaNet: Learning Tiny Models by Raster-Scanning Images CVPR 2021
Practical Single-Image Super-Resolution Using Look-Up Table CVPR 2021
The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network Architectures CVPR 2021
Troubleshooting Blind Image Quality Models in the Wild CVPR 2021
Skip-Convolutions for Efficient Video Processing CVPR 2021
MoViNets: Mobile Video Networks for Efficient Video Recognition CVPR 2021
Layer-Wise Searching for 1-Bit Detectors CVPR 2021
Achieving On-Mobile Real-Time Super-Resolution With Neural Architecture and Pruning Search ICCV 2021
Bit-Mixer: Mixed-Precision Networks With Runtime Bit-Width Selection ICCV 2021
Large Scale Multi-Illuminant (LSMI) Dataset for Developing White Balance Algorithm Under Mixed Illumination ICCV 2021