Paper List | 一文看 AAAI 2021 模型壓縮 paper
【未經允許,請勿轉載】
如果有錯誤之處,非常感謝大家提出,我也是在學習中。
AAAI 2021 – Important Dates
August 15 – August 30, 2020:
Authors register on the AAAI web site
September 1, 2020:
Electronic abstracts due at 11:59 PM UTC-12 (anywhere on earth)
September 9, 2020:
Electronic papers due at 11:59 PM UTC-12 (anywhere on earth)
September 29, 2020:
Abstracts AND full papers due for revisions of rejected NeurIPS/EMNLP submissions by 11:59 PM UTC-12 (anywhere on earth)
AAAI-21 Reviewing Process: Two-Phase Reviewing and NeurIPS/EMNLP Fast Track Submissions
November 3-5, 2020:
Author Feedback Window (anywhere on earth)
December 1, 2020:
Notification of acceptance or rejection
AAAI 2021 Pruning
TransTailor: Pruning the Pre-Trained Model for Improved Transfer Learning
Provable Benefits of Overparameterization
in Model Compression: From Double Descent to Pruning Neural Networks
Linearly Replaceable Filters
for Deep Network
Channel Pruning
Compressing Deep Convolutional Neural Networks by Stacking
Low-Dimensional Binary Convolution Filters
Tied Block Convolution: Leaner and Better CNNs with
Shared Thinner Filters
Revisiting Dominance
Pruning
in Decoupled Search
CAKES:
Channel-Wise
Automatic Kernel Shrinking for Efficient 3D Networks
DPFPS:
Dynamic and Progressive Filter Pruning
for Compressing Convolutional Neural Networks
from Scratch
OPQ: Compressing Deep Neural Networks with
One-Shot Pruning-Quantization
AutoLR: Layer-Wise Pruning and
Auto-Tuning of Learning Rates
in Fine-Tuning of Deep Networks
Accurate and Robust
Feature Importance Estimation
under
Distribution Shifts
Winning Lottery Ticket
s in Deep Generative Models
Slimmable
Generative Adversarial Networks
Towards Faster Deep Collaborative Filtering via Hierarchical Decision Networks
Quantization
Optimizing Information Theory Based Bitwise Bottlenecks for Efficient Mixed-Precision Activation Quantization
Scalable Verification of Quantized Neural Networks
Stochastic Precision Ensemble:
Self-Knowledge Distillation
for Quantized Deep Neural Networks
Weakly Supervised Deep Hyperspherical Quantization for
Image Retrieval
FracBits:
Mixed Precision
Quantization via Fractional Bit-Widths
Distribution Adaptive
INT8
Quantization for Training CNNs
TRQ: Ternary Neural Networks with Residual Quantization
Training
Binary
Neural Network
without Batch Normalization
for Image Super-Resolution
SA-BNN: State-Aware
Binary
Neural Network
Post-training Quantization
with Multiple Points:
Mixed Precision
without Mixed Precision
Any-Precision Deep Neural Networks
Distillation
Show, Attend and Distill: Knowledge Distillation via Attention-Based Feature Matching
PSSM-Distil
: Protein Secondary Structure Prediction (PSSP) on Low-Quality PSSM by Knowledge Distillation with Contrastive Learning
Cross-Layer Distillation with Semantic Calibration
Harmonized Dense Knowledge Distillation Training for Multi-Exit Architectures
Universal Trading for Order Execution with Oracle Policy Distillation
Diverse Knowledge Distillation for End-to-End Person Search
Distilling Localization for Self-Supervised Representation Learning
Data-Free Knowledge Distillation with Soft Targeted Transfer Set Synthesis
Progressive Network Grafting for Few-Shot Knowledge Distillation
Robust Knowledge Transfer via Hybrid Forward on the Teacher-Student Mode
Peer Collaborative Learning for Online Knowledge Distillation