{"list":"other","total":54,"rows":[{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"1802.01548","title":"Regularized Evolution for Image Classifier Architecture Search","created":"2018-02-05","cited_by_count":909},{"id":"1908.09791","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","created":"2019-08-26","cited_by_count":787},{"id":"1812.05159","title":"An Empirical Study of Example Forgetting during Deep Neural Network Learning","created":"2018-12-12","cited_by_count":678},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"2107.07075","title":"Deep Learning on a Data Diet: Finding Important Examples Early in Training","created":"2021-07-15","cited_by_count":533},{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528},{"id":"2008.03703","title":"What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation","created":"2020-08-09","cited_by_count":497},{"id":"2009.10795","title":"Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics","created":"2020-09-22","cited_by_count":425},{"id":"2001.00326","title":"NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search","created":"2020-01-02","cited_by_count":416},{"id":"1812.09926","title":"SNAS: Stochastic Neural Architecture Search","created":"2018-12-24","cited_by_count":289},{"id":"2103.00123","title":"GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training","created":"2021-02-27","cited_by_count":274},{"id":"1907.05737","title":"PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search","created":"2019-07-12","cited_by_count":265},{"id":"1910.04465","title":"Searching for A Robust Neural Architecture in Four GPU Hours","created":"2019-10-10","cited_by_count":260},{"id":"1904.12760","title":"Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation","created":"2019-04-29","cited_by_count":230},{"id":"2012.10630","title":"GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learning","created":"2020-12-19","cited_by_count":226},{"id":"1909.09656","title":"Understanding and Robustifying Differentiable Architecture Search","created":"2019-09-20","cited_by_count":178},{"id":"1911.12126","title":"Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search","created":"2019-11-27","cited_by_count":131},{"id":"2210.15809","title":"Coverage-centric Coreset Selection for High Pruning Rates","created":"2022-10-28","cited_by_count":117},{"id":"1907.09595","title":"MixConv: Mixed Depthwise Convolutional Kernels","created":"2019-07-22","cited_by_count":108},{"id":"2002.05283","title":"Stabilizing Differentiable Architecture Search via Perturbation-based Regularization","created":"2020-02-12","cited_by_count":102},{"id":"1809.04184","title":"Searching for Efficient Multi-Scale Architectures for Dense Image Prediction","created":"2018-09-11","cited_by_count":96},{"id":"2108.04392","title":"Rethinking Architecture Selection in Differentiable NAS","created":"2021-08-10","cited_by_count":92},{"id":"1911.13053","title":"Blockwisely Supervised Neural Architecture Search with Knowledge Distillation","created":"2019-11-29","cited_by_count":81},{"id":"2009.01027","title":"DARTS-: Robustly Stepping out of Performance Collapse Without Indicators","created":"2020-09-02","cited_by_count":81},{"id":"2002.09128","title":"DSNAS: Direct Neural Architecture Search without Parameter Retraining","created":"2020-02-21","cited_by_count":69},{"id":"2203.01665","title":"$\\beta$-DARTS: Beta-Decay Regularization for Differentiable Architecture Search","created":"2022-03-03","cited_by_count":64},{"id":"2306.05175","title":"Large-scale Dataset Pruning with Dynamic Uncertainty","created":"2023-06-08","cited_by_count":63},{"id":"2106.10784","title":"iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients","created":"2021-06-21","cited_by_count":51},{"id":"1912.05027","title":"SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization","created":"2019-12-10","cited_by_count":50},{"id":"2010.06176","title":"ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding","created":"2020-10-13","cited_by_count":36},{"id":"1808.05584","title":"BlockQNN: Efficient Block-wise Neural Network Architecture Generation","created":"2018-08-16","cited_by_count":31},{"id":"2010.00969","title":"DOTS: Decoupling Operation and Topology in Differentiable Architecture Search","created":"2020-10-02","cited_by_count":23},{"id":"2107.06869","title":"Core-set Sampling for Efficient Neural Architecture Search","created":"2021-07-08","cited_by_count":23},{"id":"2211.11109","title":"Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairness","created":"2022-11-20","cited_by_count":21},{"id":"2306.03208","title":"NLU on Data Diets: Dynamic Data Subset Selection for NLP Classification Tasks","created":"2023-06-05","cited_by_count":20},{"id":"2006.10724","title":"Cyclic Differentiable Architecture Search","created":"2020-06-18","cited_by_count":18},{"id":"2204.07554","title":"Efficient Architecture Search for Diverse Tasks","created":"2022-04-15","cited_by_count":18},{"id":"2211.05610","title":"BERT on a Data Diet: Finding Important Examples by Gradient-Based Pruning","created":"2022-11-10","cited_by_count":17},{"id":"2005.03566","title":"Noisy Differentiable Architecture Search","created":"2020-05-07","cited_by_count":16},{"id":"2106.04784","title":"Accelerating Neural Architecture Search via Proxy Data","created":"2021-06-09","cited_by_count":14},{"id":"2208.05271","title":"Efficient Joint-Dimensional Search with Solution Space Regularization for Real-Time Semantic Segmentation","created":"2022-08-10","cited_by_count":9},{"id":"1908.01314","title":"MoGA: Searching Beyond MobileNetV3","created":"2019-08-04","cited_by_count":8},{"id":"2207.00728","title":"Multi-scale Attentive Image De-raining Networks via Neural Architecture Search","created":"2022-07-02","cited_by_count":8},{"id":"2301.06393","title":"$\\beta$-DARTS++: Bi-level Regularization for Proxy-robust Differentiable Architecture Search","created":"2023-01-16","cited_by_count":7},{"id":"2211.01454","title":"Speeding up NAS with Adaptive Subset Selection","created":"2022-11-02","cited_by_count":6},{"id":"2201.12725","title":"Generalized Global Ranking-Aware Neural Architecture Ranker for Efficient Image Classifier Search","created":"2022-01-30","cited_by_count":5},{"id":"2312.12648","title":"IS-DARTS: Stabilizing DARTS through Precise Measurement on Candidate Importance","created":"2023-12-19","cited_by_count":5},{"id":"2210.17180","title":"Automated Dominative Subspace Mining for Efficient Neural Architecture Search","created":"2022-10-31","cited_by_count":3},{"id":"2211.08666","title":"Revisiting Training-free NAS Metrics: An Efficient Training-based Method","created":"2022-11-16","cited_by_count":3},{"id":"2302.11868","title":"A2S-NAS: Asymmetric Spectral-Spatial Neural Architecture Search For Hyperspectral Image Classification","created":"2023-02-23","cited_by_count":2}],"next_cursor":null}