BL-JUNIPER: A CNN-Assisted Framework for Perceptual Video Coding Leveraging Block-Level JND Jun 29, 2022 Quantization
Code Code Available Supervised Deep Hashing for High-dimensional and Heterogeneous Case-based Reasoning Jun 29, 2022 Deep Hashing Incremental Learning
— Unverified Multi-user Downlink Beamforming using Uplink Downlink Duality with 1-bit Converters for Flat Fading Channels Jun 29, 2022 Quantization
— Unverified Fundamental Limits of Communication Efficiency for Model Aggregation in Distributed Learning: A Rate-Distortion Approach Jun 28, 2022 Model Compression Quantization
— Unverified QTI Submission to DCASE 2021: residual normalization for device-imbalanced acoustic scene classification with efficient design Jun 28, 2022 Acoustic Scene Classification Knowledge Distillation
— Unverified CTMQ: Cyclic Training of Convolutional Neural Networks with Multiple Quantization Steps Jun 26, 2022 Quantization
— Unverified Cactus Mechanisms: Optimal Differential Privacy Mechanisms in the Large-Composition Regime Jun 25, 2022 Quantization
— Unverified Inverted Semantic-Index for Image Retrieval Jun 25, 2022 Clustering image-classification
— Unverified Computational Complexity Evaluation of Neural Network Applications in Signal Processing Jun 24, 2022 Quantization
— Unverified Megapixel Image Generation with Step-Unrolled Denoising Autoencoders Jun 24, 2022 Denoising GPU
Code Code Available QReg: On Regularization Effects of Quantization Jun 24, 2022 Form Quantization
— Unverified Open-source FPGA-ML codesign for the MLPerf Tiny Benchmark Jun 23, 2022 Anomaly Detection image-classification
Code Code Available A Federated Reinforcement Learning Method with Quantization for Cooperative Edge Caching in Fog Radio Access Networks Jun 23, 2022 Deep Reinforcement Learning Quantization
— Unverified Automated Cancer Subtyping via Vector Quantization Mutual Information Maximization Jun 22, 2022 Clustering Quantization
Code Code Available Proximity Graph Maintenance for Fast Online Nearest Neighbor Search Jun 22, 2022 Quantization Recommendation Systems
— Unverified Quantization Robust Federated Learning for Efficient Inference on Heterogeneous Devices Jun 22, 2022 BIG-bench Machine Learning Federated Learning
— Unverified Asymmetric Learned Image Compression with Multi-Scale Residual Block, Importance Map, and Post-Quantization Filtering Jun 21, 2022 Decoder Image Compression
— Unverified QuantFace: Towards Lightweight Face Recognition by Synthetic Data Low-bit Quantization Jun 21, 2022 Face Recognition Lightweight Face Recognition
Code Code Available sqSGD: Locally Private and Communication Efficient Federated Learning Jun 21, 2022 Federated Learning Privacy Preserving
— Unverified Self-Supervised Consistent Quantization for Fully Unsupervised Image Retrieval Jun 20, 2022 Contrastive Learning Image Retrieval
— Unverified Low-Precision Stochastic Gradient Langevin Dynamics Jun 20, 2022 Deep Learning Quantization
Code Code Available LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models Jun 20, 2022 GPU Quantization
Code Code Available Seizure Detection and Prediction by Parallel Memristive Convolutional Neural Networks Jun 20, 2022 EEG Electroencephalogram (EEG)
Code Code Available Towards Efficient Active Learning of PDFA Jun 17, 2022 Active Learning Quantization
Code Code Available FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated Learning Jun 17, 2022 Federated Learning Privacy Preserving
Code Code Available Channel-wise Mixed-precision Assignment for DNN Inference on Constrained Edge Nodes Jun 17, 2022 Neural Architecture Search Quantization
Code Code Available Lossy Compression with Gaussian Diffusion Jun 17, 2022 Quantization
Code Code Available Fast Lossless Neural Compression with Integer-Only Discrete Flows Jun 17, 2022 Quantization
Code Code Available tinySNN: Towards Memory- and Energy-Efficient Spiking Neural Networks Jun 17, 2022 Quantization
— Unverified Accelerating Inference and Language Model Fusion of Recurrent Neural Network Transducers via End-to-End 4-bit Quantization Jun 16, 2022 Language Modeling Language Modelling
— Unverified PeQuENet: Perceptual Quality Enhancement of Compressed Video with Adaptation- and Attention-based Network Jun 16, 2022 Generative Adversarial Network Quantization
Code Code Available Compressed-VFL: Communication-Efficient Learning with Vertically Partitioned Data Jun 16, 2022 Federated Learning Quantization
— Unverified Hardening DNNs against Transfer Attacks during Network Compression using Greedy Adversarial Pruning Jun 15, 2022 Adversarial Robustness Quantization
Code Code Available Edge Inference with Fully Differentiable Quantized Mixed Precision Neural Networks Jun 15, 2022 Edge-computing Quantization
— Unverified QONNX: Representing Arbitrary-Precision Quantized Neural Networks Jun 15, 2022 Quantization
Code Code Available Federated Optimization Algorithms with Random Reshuffling and Gradient Compression Jun 14, 2022 Federated Learning Quantization
Code Code Available Towards Alternative Techniques for Improving Adversarial Robustness: Analysis of Adversarial Training at a Spectrum of Perturbations Jun 13, 2022 Adversarial Robustness Quantization
Code Code Available Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training Jun 13, 2022 Quantization
Code Code Available Why Quantization Improves Generalization: NTK of Binary Weight Neural Networks Jun 13, 2022 Quantization
— Unverified Preprocessing Enhanced Image Compression for Machine Vision Jun 12, 2022 Image Compression object-detection
— Unverified A Directed-Evolution Method for Sparsification and Compression of Neural Networks with Application to Object Identification and Segmentation and considerations of optimal quantization using small number of bits Jun 12, 2022 Quantization
— Unverified Convex Quantization Preserves Logconcavity Jun 11, 2022 Quantization
— Unverified Real-time Hyper-Dimensional Reconfiguration at the Edge using Hardware Accelerators Jun 10, 2022 Few-Shot Learning Quantization
— Unverified SDQ: Stochastic Differentiable Quantization with Mixed Precision Jun 9, 2022 Knowledge Distillation Neural Architecture Search
— Unverified HideNseek: Federated Lottery Ticket via Server-side Pruning and Sign Supermask Jun 9, 2022 Federated Learning Model Compression
— Unverified Memory-Oriented Design-Space Exploration of Edge-AI Hardware for XR Applications Jun 8, 2022 CPU Hand Detection
— Unverified Gradient Obfuscation Gives a False Sense of Security in Federated Learning Jun 8, 2022 Federated Learning image-classification
— Unverified Low-complexity acoustic scene classification in DCASE 2022 Challenge Jun 8, 2022 Acoustic Scene Classification Classification
— Unverified Enhancing Strong PUF Security with Non-monotonic Response Quantization Jun 7, 2022 Quantization
— Unverified Learning Binarized Graph Representations with Multi-faceted Quantization Reinforcement for Top-K Recommendation Jun 5, 2022 Binarization Informativeness
— Unverified 