Article Digests
- Pure Alogrithm
- Convolutional Networks with Adaptive Inference Graphs
- Dynamic Resolution Network
- Dynamic Neural Networks: A Survey
- Reducing overfitting in deep networks by decorrelating representations
- Regularizing cnns with locally constrained decorrelations
- U-Net: Convolutional Networks for Biomedical Image Segmentation
- Semi-Supervised Classification with Graph Convolutional Networks
- CV
- 3D
- Image Detection
- LLCV
- Image Denoise
- Transfer Learning from Synthetic to Real-Noise Denoising with Adaptive Instance Normalization
- Brief review of image denoising techniques
- Toward Convolutional Blind Denoising of Real Photographs
- Deploying Image Deblurring across Mobile Devices: A Perspective of Quality and Latency
- Benchmarking Denoising Algorithms with Real Photographs
- Deep Learning for Image Denoising： A Survey
- Deep Learning on Image Denoising An overview
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
- Dynamic Residual Dense Network for Image Denoising
- Aligned Structured Sparsity Learning for Efficient Image Super-Resolution
- FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising
- Image Blind Denoising With Generative Adversarial Network Based Noise Modeling
- HINet： Half Instance Normalization Network for Image Restoration
- Learning Deep CNN Denoiser Prior for Image Restoration
- Learning Raw Image Denoising with Bayer Pattern Unification and Bayer Preserving Augmentation
- Neural Nearest Neighbors Network
- Practical Deep Raw Image Denoising on Mobile Devices
- Generalized Deep Image to Image Regression
- Real Image Denoising with Feature Attention
- Spatial-Adaptive Network for Single Image Denoising
- A High-Quality Denoising Dataset for Smartphone Cameras
- Robust Image Denoising with Texture-Aware Neural Network
- Unprocessing Images for Learned Raw Denoising
- Noise2Noise: Learning Image Restoration without Clean Data
- Low Light Enhancement
- Restoration
- CLEARER: Multi-Scale Neural Architecture Search for Image Restoration
- CycleISP: Real Image Restoration via Improved Data Synthesis
- Deep Image Prior
- Learning Enriched Features for Real Image Restoration and Enhancement
- Multi-Stage Progressive Image Restoration
- MemNet: A Persistent Memory Network for Image Restoration
- Self-Guided Network for Fast Image Denoising
- Stacking Networks Dynamically for Image Restoration Based on the Plug-and-Play Framework
- Memory-Efficient Hierarchical Neural Architecture Search for Image Denoising
- Attentive Fine-Grained Structured Sparsity for Image Restoration
- Restormer: Efficient Transformer for High-Resolution Image Restoration
- Uformer: A General U-Shaped Transformer for Image Restoration
- Searching for Controllable Image Restoration Networks
- Enhanced Image Restoration Via Supervised Target Feature Transfer
- Super Resolution
- A Layer-Wise Extreme Network Compression for Super Resolution
- Aligned Structured Sparsity Learning for Efficient Image Super-Resolution
- Binarized Neural Network for Single Image Super Resolution
- Fully !antized Image Super-Resolution Networks
- PAMS: Quantized Super-Resolution via Parameterized Max Scale
- Deep Learning for Image Super-resolution: A Survey
- Training Binary Neural Network without Batch Normalization for Image Super-Resolution
- Video super‑resolution based on deep learning: a comprehensive survey
- BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond
- Enhanced Deep Residual Networks for Single Image Super-Resolution
- Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile Devices
- CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution
- Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution
- Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution Networks
- Adaptive Patch Exiting for Scalable Single Image Super-Resolution
- Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search
- Learning Efficient Image Super-Resolution Networks via Structure-Regularized Pruning
- Fine-grained neural architecture search for image super-resolution
- Fast and Memory-Efficient Network Towards Efficient Image Super-Resolution
- DAQ: Channel-Wise Distribution-Aware Quantization for Deep Image Super-Resolution Networks
- Wide Activation for Efficient and Accurate Image Super-Resolution
- Image Denoise
- Uncategorized
- Computer Architecture
- A Survey of Computer Architecture Simulation Techniques and Tools
- DNNAbacus: Toward Accurate Computational Cost Prediction for Deep Neural Networks
- MAPLE-Edge: A Runtime Latency Predictor for Edge Devices
- STONNE: Enabling Cycle-Level Microarchitectural Simulation for DNN Inference Accelerators
- nn-Meter: Towards Accurate Latency Prediction of Deep-Learning Model Inference on Diverse Edge Devices
- EcoFlow Efficient Convolutional Dataflows on Low-Power Neural Network Accelerators
- Model Compression
- GhostNet: More Features from Cheap Operations
- MCUNet: Tiny Deep Learning on IoT Devices
- MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning
- TinyTL: Reduce Activations, Not Trainable Parameters for Efficient On-Device Learning
- 深度神经网络压缩与加速综述
- BNN related articles
- Towards Accurate Binary Convolutional Neural Network
- BATS: Binary ArchitecTure Search
- Bayesian Optimized 1-Bit CNNs
- Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm
- DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
- Learning Frequency Domain Approximation for Binary Neural Networks
- High-Capacity Expert Binary Networks
- Learning Channel-wise Interactions for Binary Convolutional Neural Networks
- ReCU: Reviving the Dead Weights in Binary Neural Networks
- Training Binary Neural Networks with Real-to-Binary Convlutions
- Training Binary Neural Networks through Learning with Noisy Supervision
- Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets
- WRPN: Wide Reduced-Precision Networks
- XNOR-Net
- PokeBNN: A Binary Pursuit of Lightweight Accuracy
- ReActNet Towards Precise Binary Neural Network with Generalized Activation Functions
- Bitwise Neural Networks
- BiT: Robustly Binarized Multi-distilled Transformer
- BinaryDuo: Reducing Gradient Mismatch in Binary Activation Network by Coupling Binary Activations
- BoolNet: Minimizing the Energy Consumption of Binary Neural Networks
- An Empirical study of Binary Neural Networks' Optimisation
- Deployment
- Kownledge Distillation
- NAS
- Neural Architecture Search for Dense Prediction Tasks in Computer Vision
- A Generic Graph-Based Neural Architecture Encoding Scheme for Predictor-Based NAS
- Neural Predictor for Neural Architecture Search
- NAS-BENCH-201: Extending the Scope of Reproducible Neural Architecture Search
- A Generic Graph-based Neural Architecture Encoding Scheme with Multifaceted Information
- Pruning
- Architecture-Aware Network Pruning for Vision Quality Applications
- Structured Pruning of Neural Networks with Budget-Aware Regularization
- ECC: Platform-Independent Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Model
- Revisiting Random Channel Pruning for Neural Network Compression
- DHP: Differentiable Meta Pruning via HyperNetworks
- Universally Slimmable Networks and Improved Training Techniques
- SLIMMABLE NEURAL NETWORKS
- Learning N: M Fine-grained Structured Sparse Neural Networks From Scratch
- AutoSlim: Towards One-Shot Architecture Search for Channel Numbers
- Quantization
- A Survey of Quantization Methods for Efficient Neural Network Inference
- Post training 4-bit quantization of convolutional networks for rapid-deployment
- Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming
- Up or Down? Adaptive Rounding for Post-Training Quantization
- Automated Log-Scale Quantization for Low-Cost Deep Neural Networks
- BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction
- Data-Free Quantization Through Weight Equalization and Bias Correction
- Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks
- Deep Learning with Limited Numerical Precision
- Loss Aware Post-training Quantization
- Learnable Companding Quantization for Accurate Low-bit Neural Networks
- LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks
- Learned Step Size Quantization
- MQBench: Towards Reproducible and Deployable Model Quantization Benchmark
- Improving Neural Network Quantization without Retraining using Outlier Channel Splitting
- Trained quantization thresholds for accurate and efficient fixed-point inference of deep neural networks
- ZeroQ: A Novel Zero Shot Quantization Framework
- NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers
- PACT: Parameterized Clipping Activation for Quantized Neural Networks
- Quantization Applications
- Post-training Quantization on Diffusion Models
- SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
- LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
- Quantizable Transformers Removing Outliers by Helping Attention Heads Do Nothing
- Q-DM: An Efficient Low-bit Quantized Diffusion Model
- Unassorted
- EsyMo: Scalable and Efficient Deep-Learning Inference on Asymmetric Mobile CPUs
- Elf: Accelerate High-resolution Mobile Deep Vision with Content-aware Parallel Offloading
- Flexible High-resolution Object Detection on Edge Devices with Tunable Latency
- CoDL: Efficient CPU-GPU Co-execution for Deep Learning Inference on Mobile Devices
- Melon: Breaking the Memory Wall for Resource-Efficient On-Device Machine Learning
- Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors
- Optical Flow Estimation using a Spatial Pyramid Network
- Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs