{"total":102,"rows":[{"id":"2106.14156","title":"Post-Training Quantization for Vision Transformer","created":"2021-06-27","cited_by_count":278,"area":null},{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263,"area":null},{"id":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255,"area":null},{"id":"2102.04010","title":"Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch","created":"2021-02-08","cited_by_count":179,"area":null},{"id":"2104.02151","title":"Distributed Learning in Wireless Networks: Recent Progress and Future Challenges","created":"2021-04-05","cited_by_count":129,"area":null},{"id":"2304.01089","title":"RPTQ: Reorder-based Post-training Quantization for Large Language Models","created":"2023-04-03","cited_by_count":116,"area":null},{"id":"2111.14826","title":"Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation","created":"2021-11-29","cited_by_count":79,"area":null},{"id":"2106.12379","title":"AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks","created":"2021-06-23","cited_by_count":59,"area":null},{"id":"2104.09987","title":"Differentiable Model Compression via Pseudo Quantization Noise","created":"2021-04-20","cited_by_count":45,"area":null},{"id":"2208.08084","title":"AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets","created":"2022-08-17","cited_by_count":38,"area":null},{"id":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","cited_by_count":32,"area":null},{"id":"2104.02244","title":"Content-Aware GAN Compression","created":"2021-04-06","cited_by_count":28,"area":null},{"id":"2206.04459","title":"SDQ: Stochastic Differentiable Quantization with Mixed Precision","created":"2022-06-09","cited_by_count":28,"area":null},{"id":"2109.01905","title":"Spiking Neural Networks with Improved Inherent Recurrence Dynamics for Sequential Learning","created":"2021-09-04","cited_by_count":27,"area":null},{"id":"2109.12338","title":"Distribution-sensitive Information Retention for Accurate Binary Neural Network","created":"2021-09-25","cited_by_count":25,"area":null},{"id":"2109.12872","title":"Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks","created":"2021-09-27","cited_by_count":25,"area":null},{"id":"2106.02295","title":"Differentiable Dynamic Quantization with Mixed Precision and Adaptive Resolution","created":"2021-06-04","cited_by_count":20,"area":null},{"id":"2101.09868","title":"CPT: Efficient Deep Neural Network Training via Cyclic Precision","created":"2021-01-25","cited_by_count":19,"area":null},{"id":"2104.08215","title":"\"BNN - BN = ?\": Training Binary Neural Networks without Batch Normalization","created":"2021-04-16","cited_by_count":17,"area":null},{"id":"2205.01271","title":"Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation","created":"2022-05-03","cited_by_count":16,"area":null},{"id":"2102.08946","title":"S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration","created":"2021-02-17","cited_by_count":15,"area":null},{"id":"2301.10281","title":"Lightweight Neural Architecture Search for Temporal Convolutional Networks at the Edge","created":"2023-01-24","cited_by_count":15,"area":null},{"id":"2102.07567","title":"Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent","created":"2021-02-15","cited_by_count":14,"area":null},{"id":"2104.07085","title":"Fast Walsh-Hadamard Transform and Smooth-Thresholding Based Binary Layers in Deep Neural Networks","created":"2021-04-14","cited_by_count":14,"area":null},{"id":"2110.05185","title":"Dynamic Binary Neural Network by learning channel-wise thresholds","created":"2021-10-08","cited_by_count":13,"area":null},{"id":"2201.02711","title":"Block Walsh-Hadamard Transform Based Binary Layers in Deep Neural Networks","created":"2022-01-07","cited_by_count":13,"area":null},{"id":"2203.01479","title":"Weightless Neural Networks for Efficient Edge Inference","created":"2022-03-03","cited_by_count":13,"area":null},{"id":"2103.14739","title":"Leaky Nets: Recovering Embedded Neural Network Models and Inputs through Simple Power and Timing Side-Channels -- Attacks and Defenses","created":"2021-03-26","cited_by_count":11,"area":null},{"id":"2108.00568","title":"FLASH: Fast Neural Architecture Search with Hardware Optimization","created":"2021-08-01","cited_by_count":11,"area":null},{"id":"2105.13904","title":"An In-Memory Analog Computing Co-Processor for Energy-Efficient CNN Inference on Mobile Devices","created":"2021-05-24","cited_by_count":9,"area":null},{"id":"2106.07268","title":"FastICARL: Fast Incremental Classifier and Representation Learning with Efficient Budget Allocation in Audio Sensing Applications","created":"2021-06-14","cited_by_count":9,"area":null},{"id":"2106.09989","title":"BinarizedAttack: Structural Poisoning Attacks to Graph-based Anomaly Detection","created":"2021-06-18","cited_by_count":9,"area":null},{"id":"2102.01875","title":"AHAR: Adaptive CNN for Energy-efficient Human Activity Recognition in Low-power Edge Devices","created":"2021-02-03","cited_by_count":8,"area":null},{"id":"2107.13490","title":"Adaptive Precision Training (AdaPT): A dynamic fixed point quantized training approach for DNNs","created":"2021-07-28","cited_by_count":8,"area":null},{"id":"2201.11915","title":"The fine line between dead neurons and sparsity in binarized spiking neural networks","created":"2022-01-28","cited_by_count":8,"area":null},{"id":"2103.13598","title":"Recent Advances in Large Margin Learning","created":"2021-03-25","cited_by_count":7,"area":null},{"id":"2107.12445","title":"Towards Low-Latency Energy-Efficient Deep SNNs via Attention-Guided Compression","created":"2021-07-16","cited_by_count":7,"area":null},{"id":"2112.09407","title":"Communication-oriented Model Fine-tuning for Packet-loss Resilient Distributed Inference under Highly Lossy IoT Networks","created":"2021-12-17","cited_by_count":7,"area":null},{"id":"2103.00342","title":"Constrained Differentially Private Federated Learning for Low-bandwidth Devices","created":"2021-02-27","cited_by_count":6,"area":null},{"id":"2206.04385","title":"HideNseek: Federated Lottery Ticket via Server-side Pruning and Sign Supermask","created":"2022-06-09","cited_by_count":6,"area":null},{"id":"2103.13894","title":"Boosting Binary Masks for Multi-Domain Learning through Affine Transformations","created":"2021-03-25","cited_by_count":5,"area":null},{"id":"2105.00528","title":"A 1D-CNN Based Deep Learning Technique for Sleep Apnea Detection in IoT Sensors","created":"2021-05-02","cited_by_count":5,"area":null},{"id":"2201.03386","title":"Sub-mW Keyword Spotting on an MCU: Analog Binary Feature Extraction and Binary Neural Networks","created":"2022-01-10","cited_by_count":5,"area":null},{"id":"2202.06483","title":"BiFSMN: Binary Neural Network for Keyword Spotting","created":"2022-02-14","cited_by_count":5,"area":null},{"id":"2206.07518","title":"Binary Single-dimensional Convolutional Neural Network for Seizure Prediction","created":"2022-06-08","cited_by_count":5,"area":null},{"id":"2111.09348","title":"End-to-End Learned Image Compression with Quantized Weights and Activations","created":"2021-11-17","cited_by_count":4,"area":null},{"id":"2201.02863","title":"PocketNN: Integer-only Training and Inference of Neural Networks via Direct Feedback Alignment and Pocket Activations in Pure C++","created":"2022-01-08","cited_by_count":4,"area":null},{"id":"2201.03013","title":"ThreshNet: An Efficient DenseNet Using Threshold Mechanism to Reduce Connections","created":"2022-01-09","cited_by_count":4,"area":null},{"id":"2203.05696","title":"Toward Efficient Hyperspectral Image Processing inside Camera Pixels","created":"2022-03-11","cited_by_count":4,"area":null},{"id":"2203.14768","title":"Pruning In Time (PIT): A Lightweight Network Architecture Optimizer for Temporal Convolutional Networks","created":"2022-03-28","cited_by_count":4,"area":null},{"id":"2305.02522","title":"BitGNN: Unleashing the Performance Potential of Binary Graph Neural Networks on GPUs","created":"2023-05-04","cited_by_count":4,"area":null},{"id":"2102.11786","title":"QuPeL: Quantized Personalization with Applications to Federated Learning","created":"2021-02-23","cited_by_count":3,"area":null},{"id":"2104.05124","title":"A Bop and Beyond: A Second Order Optimizer for Binarized Neural Networks","created":"2021-04-11","cited_by_count":3,"area":null},{"id":"2104.10044","title":"BCNN: Binary Complex Neural Network","created":"2021-03-28","cited_by_count":3,"area":null},{"id":"2109.09310","title":"Learning Versatile Convolution Filters for Efficient Visual Recognition","created":"2021-09-20","cited_by_count":3,"area":null},{"id":"2110.08562","title":"BNAS v2: Learning Architectures for Binary Networks with Empirical Improvements","created":"2021-10-16","cited_by_count":3,"area":null},{"id":"2302.06405","title":"An Optical XNOR-Bitcount Based Accelerator for Efficient Inference of Binary Neural Networks","created":"2023-02-03","cited_by_count":3,"area":null},{"id":"2101.07295","title":"The Surprising Positive Knowledge Transfer in Continual 3D Object Shape Reconstruction","created":"2021-01-18","cited_by_count":2,"area":null},{"id":"2103.00833","title":"Fast threshold optimization for multi-label audio tagging using Surrogate gradient learning","created":"2021-03-01","cited_by_count":2,"area":null},{"id":"2103.14949","title":"Automated Backend-Aware Post-Training Quantization","created":"2021-03-27","cited_by_count":2,"area":null},{"id":"2105.07331","title":"Is In-Domain Data Really Needed? A Pilot Study on Cross-Domain Calibration for Network Quantization","created":"2021-05-16","cited_by_count":2,"area":null},{"id":"2106.11426","title":"Efficient Inference via Universal LSH Kernel","created":"2021-06-21","cited_by_count":2,"area":null},{"id":"2108.11468","title":"SomnNET: An SpO2 Based Deep Learning Network for Sleep Apnea Detection in Smartwatches","created":"2021-08-25","cited_by_count":2,"area":null},{"id":"2111.14836","title":"Low-bit Quantization of Recurrent Neural Network Language Models Using Alternating Direction Methods of Multipliers","created":"2021-11-29","cited_by_count":2,"area":null},{"id":"2205.03661","title":"Arrhythmia Classifier using Binarized Convolutional Neural Network for Resource-Constrained Devices","created":"2022-05-07","cited_by_count":2,"area":null},{"id":"2207.09049","title":"RepBNN: towards a precise Binary Neural Network with Enhanced Feature Map via Repeating","created":"2022-07-19","cited_by_count":2,"area":null},{"id":"2211.08544","title":"Exploiting the Partly Scratch-off Lottery Ticket for Quantization-Aware Training","created":"2022-11-12","cited_by_count":2,"area":null},{"id":"2303.08970","title":"Gated Compression Layers for Efficient Always-On Models","created":"2023-03-15","cited_by_count":2,"area":null},{"id":"2304.09695","title":"Big-Little Adaptive Neural Networks on Low-Power Near-Subthreshold Processors","created":"2023-04-19","cited_by_count":2,"area":null},{"id":"2101.06608","title":"Network Automatic Pruning: Start NAP and Take a Nap","created":"2021-01-17","cited_by_count":1,"area":null},{"id":"2103.15564","title":"Prototype-based Personalized Pruning","created":"2021-03-25","cited_by_count":1,"area":null},{"id":"2104.09872","title":"Robust Sensor Fusion Algorithms Against Voice Command Attacks in Autonomous Vehicles","created":"2021-04-20","cited_by_count":1,"area":null},{"id":"2107.03375","title":"Differentiable Architecture Pruning for Transfer Learning","created":"2021-07-07","cited_by_count":1,"area":null},{"id":"2109.08231","title":"RAPID-RL: A Reconfigurable Architecture with Preemptive-Exits for Efficient Deep-Reinforcement Learning","created":"2021-09-16","cited_by_count":1,"area":null},{"id":"2110.13859","title":"Defensive Tensorization","created":"2021-10-26","cited_by_count":1,"area":null},{"id":"2111.01135","title":"Arch-Net: Model Distillation for Architecture Agnostic Model Deployment","created":"2021-11-01","cited_by_count":1,"area":null},{"id":"2111.15179","title":"A Highly Effective Low-Rank Compression of Deep Neural Networks with Modified Beam-Search and Modified Stable Rank","created":"2021-11-30","cited_by_count":1,"area":null},{"id":"2203.11081","title":"Image Classification on Accelerated Neural Networks","created":"2022-03-21","cited_by_count":1,"area":null},{"id":"2205.03996","title":"Hardware-Robust In-RRAM-Computing for Object Detection","created":"2022-05-09","cited_by_count":1,"area":null},{"id":"2301.06193","title":"RedBit: An End-to-End Flexible Framework for Evaluating the Accuracy of Quantized CNNs","created":"2023-01-15","cited_by_count":1,"area":null},{"id":"2102.09493","title":"Inferring Graph Signal Translations as Invariant Transformations for Classification Tasks","created":"2021-02-18","cited_by_count":0,"area":null},{"id":"2103.11704","title":"n-hot: Efficient bit-level sparsity for powers-of-two neural network quantization","created":"2021-03-22","cited_by_count":0,"area":null},{"id":"2103.16609","title":"Binarized Neural Networks for Resource-Constrained On-Device Gait Identification","created":"2021-03-30","cited_by_count":0,"area":null},{"id":"2105.03897","title":"Binarized Weight Error Networks With a Transition Regularization Term","created":"2021-05-09","cited_by_count":0,"area":null},{"id":"2105.11848","title":"DTNN: Energy-efficient Inference with Dendrite Tree Inspired Neural Networks for Edge Vision Applications","created":"2021-05-25","cited_by_count":0,"area":null},{"id":"2108.07147","title":"On the Importance of Encrypting Deep Features","created":"2021-08-16","cited_by_count":0,"area":null},{"id":"2110.09962","title":"PR-CIM: a Variation-Aware Binary-Neural-Network Framework for Process-Resilient Computation-in-memory","created":"2021-10-19","cited_by_count":0,"area":null},{"id":"2110.10864","title":"Class-Discriminative CNN Compression","created":"2021-10-21","cited_by_count":0,"area":null},{"id":"2202.06563","title":"Saving RNN Computations with a Neuron-Level Fuzzy Memoization Scheme","created":"2022-02-14","cited_by_count":0,"area":null},{"id":"2202.12422","title":"Standard Deviation-Based Quantization for Deep Neural Networks","created":"2022-02-24","cited_by_count":0,"area":null},{"id":"2205.15404","title":"Gator: Customizable Channel Pruning of Neural Networks with Gating","created":"2022-05-30","cited_by_count":0,"area":null},{"id":"2206.08152","title":"Fault-Tolerant Collaborative Inference through the Edge-PRUNE Framework","created":"2022-06-16","cited_by_count":0,"area":null},{"id":"2208.00302","title":"Efficient Compilation and Mapping of Fixed Function Combinational Logic onto Digital Signal Processors Targeting Neural Network Inference and Utilizing High-level Synthesis","created":"2022-07-30","cited_by_count":0,"area":null},{"id":"2210.06299","title":"SeKron: A Decomposition Method Supporting Many Factorization Structures","created":"2022-10-12","cited_by_count":0,"area":null},{"id":"2210.13468","title":"Fast and Low-Memory Deep Neural Networks Using Binary Matrix Factorization","created":"2022-10-24","cited_by_count":0,"area":null},{"id":"2303.07080","title":"Bag of Tricks with Quantized Convolutional Neural Networks for image classification","created":"2023-03-13","cited_by_count":0,"area":null},{"id":"2305.08075","title":"Analyzing Compression Techniques for Computer Vision","created":"2023-05-14","cited_by_count":0,"area":null},{"id":"2311.10296","title":"BiHRNet: A Binary high-resolution network for Human Pose Estimation","created":"2023-11-17","cited_by_count":0,"area":null},{"id":"2403.14999","title":"Magic for the Age of Quantized DNNs","created":"2024-03-22","cited_by_count":0,"area":null},{"id":"2410.01272","title":"\"No Matter What You Do\": Purifying GNN Models via Backdoor Unlearning","created":"2024-10-02","cited_by_count":0,"area":null}],"next_cursor":"100"}