{"total":76,"rows":[{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203,"area":null},{"id":"2308.06767","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","created":"2023-08-13","cited_by_count":202,"area":null},{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122,"area":null},{"id":"2110.01515","title":"A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning","created":"2021-10-04","cited_by_count":82,"area":null},{"id":"2110.14032","title":"MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge","created":"2021-10-26","cited_by_count":79,"area":null},{"id":"2104.03438","title":"Convolutional Neural Network Pruning with Structural Redundancy Reduction","created":"2021-04-08","cited_by_count":73,"area":null},{"id":"2101.09336","title":"A Comprehensive Survey on Hardware-Aware Neural Architecture Search","created":"2021-01-22","cited_by_count":61,"area":null},{"id":"2209.09476","title":"SparCL: Sparse Continual Learning on the Edge","created":"2022-09-20","cited_by_count":55,"area":null},{"id":"2305.02299","title":"Dynamic Sparse Training with Structured Sparsity","created":"2023-05-03","cited_by_count":38,"area":null},{"id":"2203.15794","title":"CHEX: CHannel EXploration for CNN Model Compression","created":"2022-03-29","cited_by_count":36,"area":null},{"id":"2102.05258","title":"Locally Free Weight Sharing for Network Width Search","created":"2021-02-10","cited_by_count":27,"area":null},{"id":"2105.10533","title":"BCNet: Searching for Network Width with Bilaterally Coupled Network","created":"2021-05-21","cited_by_count":23,"area":null},{"id":"2106.06442","title":"K-shot NAS: Learnable Weight-Sharing for NAS with K-shot Supernets","created":"2021-06-11","cited_by_count":22,"area":null},{"id":"2108.03428","title":"PSViT: Better Vision Transformer via Token Pooling and Attention Sharing","created":"2021-08-07","cited_by_count":21,"area":null},{"id":"2102.11646","title":"HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search","created":"2021-02-23","cited_by_count":20,"area":null},{"id":"2108.12594","title":"Layer-wise Model Pruning based on Mutual Information","created":"2021-08-28","cited_by_count":19,"area":null},{"id":"2305.19454","title":"Dynamic Sparsity Is Channel-Level Sparsity Learner","created":"2023-05-30","cited_by_count":18,"area":null},{"id":"2108.08532","title":"An Information Theory-inspired Strategy for Automatic Network Pruning","created":"2021-08-19","cited_by_count":17,"area":null},{"id":"2202.07190","title":"Pruning Networks with Cross-Layer Ranking & k-Reciprocal Nearest Filters","created":"2022-02-15","cited_by_count":16,"area":null},{"id":"2112.09245","title":"Automated Deep Learning: Neural Architecture Search Is Not the End","created":"2021-12-16","cited_by_count":13,"area":null},{"id":"2207.07929","title":"Towards Lightweight Super-Resolution with Dual Regression Learning","created":"2022-07-16","cited_by_count":13,"area":null},{"id":"2209.11204","title":"Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training","created":"2022-09-22","cited_by_count":11,"area":null},{"id":"2201.05842","title":"UDC: Unified DNAS for Compressible TinyML Models","created":"2022-01-15","cited_by_count":10,"area":null},{"id":"2104.08702","title":"Reconsidering CO2 emissions from Computer Vision","created":"2021-04-18","cited_by_count":9,"area":null},{"id":"2303.11923","title":"Performance-aware Approximation of Global Channel Pruning for Multitask CNNs","created":"2023-03-21","cited_by_count":9,"area":null},{"id":"2403.07221","title":"LookupFFN: Making Transformers Compute-lite for CPU inference","created":"2024-03-12","cited_by_count":8,"area":null},{"id":"2111.11581","title":"Automatic Mapping of the Best-Suited DNN Pruning Schemes for Real-Time Mobile Acceleration","created":"2021-11-22","cited_by_count":7,"area":null},{"id":"2202.10716","title":"HRel: Filter Pruning based on High Relevance between Activation Maps and Class Labels","created":"2022-02-22","cited_by_count":7,"area":null},{"id":"2101.04935","title":"Single-path Bit Sharing for Automatic Loss-aware Model Compression","created":"2021-01-13","cited_by_count":6,"area":null},{"id":"2110.10921","title":"CATRO: Channel Pruning via Class-Aware Trace Ratio Optimization","created":"2021-10-21","cited_by_count":6,"area":null},{"id":"2202.05451","title":"ACORT: A Compact Object Relation Transformer for Parameter Efficient Image Captioning","created":"2022-02-11","cited_by_count":6,"area":null},{"id":"2105.12686","title":"Dynamic Probabilistic Pruning: A general framework for hardware-constrained pruning at different granularities","created":"2021-05-26","cited_by_count":5,"area":null},{"id":"2107.07110","title":"Compact and Optimal Deep Learning with Recurrent Parameter Generators","created":"2021-07-15","cited_by_count":5,"area":null},{"id":"2203.02651","title":"Ensemble Knowledge Guided Sub-network Search and Fine-tuning for Filter Pruning","created":"2022-03-05","cited_by_count":5,"area":null},{"id":"2211.15155","title":"GraphPNAS: Learning Distribution of Good Neural Architectures via Deep Graph Generative Models","created":"2022-11-28","cited_by_count":5,"area":null},{"id":"2203.13714","title":"Searching for Network Width with Bilaterally Coupled Network","created":"2022-03-25","cited_by_count":4,"area":null},{"id":"2402.17862","title":"REPrune: Channel Pruning via Kernel Representative Selection","created":"2024-02-27","cited_by_count":4,"area":null},{"id":"2503.22733","title":"RBFleX-NAS: Training-Free Neural Architecture Search Using Radial Basis Function Kernel and Hyperparameter Detection","created":"2025-03-26","cited_by_count":4,"area":null},{"id":"2106.10705","title":"Automated Deepfake Detection","created":"2021-06-20","cited_by_count":2,"area":null},{"id":"2108.06822","title":"CONet: Channel Optimization for Convolutional Neural Networks","created":"2021-08-15","cited_by_count":2,"area":null},{"id":"2110.01154","title":"An Analysis of Super-Net Heuristics in Weight-Sharing NAS","created":"2021-10-04","cited_by_count":2,"area":null},{"id":"2207.06968","title":"DASS: Differentiable Architecture Search for Sparse neural networks","created":"2022-07-14","cited_by_count":2,"area":null},{"id":"2307.00198","title":"Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler","created":"2023-07-01","cited_by_count":2,"area":null},{"id":"2311.02003","title":"Efficient Model-Based Deep Learning via Network Pruning and Fine-Tuning","created":"2023-11-03","cited_by_count":2,"area":null},{"id":"2103.15692","title":"Self-Constructing Neural Networks Through Random Mutation","created":"2021-03-29","cited_by_count":1,"area":null},{"id":"2104.08446","title":"Towards Efficient Convolutional Network Models with Filter Distribution Templates","created":"2021-04-17","cited_by_count":1,"area":null},{"id":"2104.13255","title":"Width Transfer: On the (In)variance of Width Optimization","created":"2021-04-24","cited_by_count":1,"area":null},{"id":"2106.07211","title":"Differentiable Neural Architecture Search with Morphism-based Transformable Backbone Architectures","created":"2021-06-14","cited_by_count":1,"area":null},{"id":"2110.10876","title":"Evolving Transferable Neural Pruning Functions","created":"2021-10-21","cited_by_count":1,"area":null},{"id":"2110.12477","title":"Exploring Gradient Flow Based Saliency for DNN Model Compression","created":"2021-10-24","cited_by_count":1,"area":null},{"id":"2208.10498","title":"Design Automation for Fast, Lightweight, and Effective Deep Learning Models: A Survey","created":"2022-08-22","cited_by_count":1,"area":null},{"id":"2212.10878","title":"Automatic Network Adaptation for Ultra-Low Uniform-Precision Quantization","created":"2022-12-21","cited_by_count":1,"area":null},{"id":"2310.06218","title":"SUBP: Soft Uniform Block Pruning for 1xN Sparse CNNs Multithreading Acceleration","created":"2023-10-10","cited_by_count":1,"area":null},{"id":"2502.03658","title":"Advancing Weight and Channel Sparsification with Enhanced Saliency","created":"2025-02-05","cited_by_count":1,"area":null},{"id":"2506.14667","title":"DDS-NAS: Dynamic Data Selection within Neural Architecture Search via On-line Hard Example Mining applied to Image Classification","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2605.06278","title":"PACE: Prune-And-Compress Ensemble Models","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2103.16350","title":"Differentiable Network Adaption with Elastic Search Space","created":"2021-03-30","cited_by_count":0,"area":null},{"id":"2104.13993","title":"Filter Distribution Templates in Convolutional Networks for Image Classification Tasks","created":"2021-04-28","cited_by_count":0,"area":null},{"id":"2107.00070","title":"Dep-$L_0$: Improving $L_0$-based Network Sparsification via Dependency Modeling","created":"2021-06-30","cited_by_count":0,"area":null},{"id":"2110.04492","title":"Weight Evolution: Improving Deep Neural Networks Training through Evolving Inferior Weight Values","created":"2021-10-09","cited_by_count":0,"area":null},{"id":"2110.08013","title":"Joint Channel and Weight Pruning for Model Acceleration on Moblie Devices","created":"2021-10-15","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":"2205.01508","title":"Compact Neural Networks via Stacking Designed Basic Units","created":"2022-05-03","cited_by_count":0,"area":null},{"id":"2209.03534","title":"CWP: Instance complexity weighted channel-wise soft masks for network pruning","created":"2022-09-08","cited_by_count":0,"area":null},{"id":"2303.16212","title":"A Multi-objective Complex Network Pruning Framework Based on Divide-and-conquer and Global Performance Impairment Ranking","created":"2023-03-28","cited_by_count":0,"area":null},{"id":"2307.00758","title":"Structured Network Pruning by Measuring Filter-wise Interactions","created":"2023-07-03","cited_by_count":0,"area":null},{"id":"2308.08222","title":"HyperSNN: A new efficient and robust deep learning model for resource constrained control applications","created":"2023-08-16","cited_by_count":0,"area":null},{"id":"2308.08504","title":"ResBuilder: Automated Learning of Depth with Residual Structures","created":"2023-08-16","cited_by_count":0,"area":null},{"id":"2308.14605","title":"A Generalization of Continuous Relaxation in Structured Pruning","created":"2023-08-28","cited_by_count":0,"area":null},{"id":"2408.16233","title":"PSE-Net: Channel Pruning for Convolutional Neural Networks with Parallel-subnets Estimator","created":"2024-08-29","cited_by_count":0,"area":null},{"id":"2409.03777","title":"A Greedy Hierarchical Approach to Whole-Network Filter-Pruning in CNNs","created":"2024-08-22","cited_by_count":0,"area":null},{"id":"2410.07046","title":"S2HPruner: Soft-to-Hard Distillation Bridges the Discretization Gap in Pruning","created":"2024-10-09","cited_by_count":0,"area":null},{"id":"2507.23437","title":"Coflex: Enhancing HW-NAS with Sparse Gaussian Processes for Efficient and Scalable DNN Accelerator Design","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2508.02291","title":"FAIR-Pruner: A Flexible Framework for Automatic Layer-Wise Pruning via Tolerance of Difference","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2509.11661","title":"DTGen: Generative Diffusion-Based Few-Shot Data Augmentation for Fine-Grained Dirty Tableware Recognition","created":"2025-09-15","cited_by_count":0,"area":null},{"id":"2609.23087","title":"Neural Spectral Capacity: Measuring and Designing Architectures from Network Specification Alone","created":"2026-09-19","cited_by_count":0,"area":null}],"next_cursor":null}