{"list":"other","total":54,"rows":[{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"1706.08840","title":"Gradient Episodic Memory for Continual Learning","created":"2017-06-26","cited_by_count":1898},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"1810.04650","title":"Multi-Task Learning as Multi-Objective Optimization","created":"2018-10-10","cited_by_count":821},{"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":"1806.01768","title":"Evidential Deep Learning to Quantify Classification Uncertainty","created":"2018-06-05","cited_by_count":732},{"id":"1708.06519","title":"Learning Efficient Convolutional Networks through Network Slimming","created":"2017-08-22","cited_by_count":676},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"1811.11168","title":"Deformable ConvNets v2: More Deformable, Better Results","created":"2018-11-27","cited_by_count":670},{"id":"1709.01686","title":"BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks","created":"2017-09-06","cited_by_count":596},{"id":"1603.08983","title":"Adaptive Computation Time for Recurrent Neural Networks","created":"2016-03-29","cited_by_count":506},{"id":"1711.08565","title":"Person Transfer GAN to Bridge Domain Gap for Person Re-Identification","created":"2017-11-23","cited_by_count":480},{"id":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475},{"id":"1903.07071","title":"Bag of Tricks and A Strong Baseline for Deep Person Re-identification","created":"2019-03-17","cited_by_count":430},{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408},{"id":"2002.10857","title":"Circle Loss: A Unified Perspective of Pair Similarity Optimization","created":"2020-02-25","cited_by_count":403},{"id":"1910.07104","title":"Orthogonal Gradient Descent for Continual Learning","created":"2019-10-15","cited_by_count":369},{"id":"1406.6247","title":"Recurrent Models of Visual Attention","created":"2014-06-24","cited_by_count":349},{"id":"1711.09485","title":"SkipNet: Learning Dynamic Routing in Convolutional Networks","created":"2017-11-26","cited_by_count":332},{"id":"1812.08928","title":"Slimmable Neural Networks","created":"2018-12-21","cited_by_count":305},{"id":"1511.06297","title":"Conditional Computation in Neural Networks for faster models","created":"2015-11-19","cited_by_count":167},{"id":"2006.02631","title":"FastReID: A Pytorch Toolbox for General Instance Re-identification","created":"2020-06-04","cited_by_count":166},{"id":"1702.07811","title":"Adaptive Neural Networks for Efficient Inference","created":"2017-02-25","cited_by_count":163},{"id":"1711.11503","title":"Convolutional Networks with Adaptive Inference Graphs","created":"2017-11-30","cited_by_count":148},{"id":"1904.05373","title":"Pixel-Adaptive Convolutional Neural Networks","created":"2019-04-10","cited_by_count":126},{"id":"1711.09224","title":"CondenseNet: An Efficient DenseNet using Learned Group Convolutions","created":"2017-11-25","cited_by_count":122},{"id":"1803.02579","title":"Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional Networks","created":"2018-03-07","cited_by_count":122},{"id":"1812.02224","title":"Adapting Auxiliary Losses Using Gradient Similarity","created":"2018-12-05","cited_by_count":100},{"id":"2010.05300","title":"Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification","created":"2020-10-11","cited_by_count":100},{"id":"2107.10161","title":"Evidential Deep Learning for Open Set Action Recognition","created":"2021-07-21","cited_by_count":96},{"id":"2102.02051","title":"Trusted Multi-View Classification","created":"2021-02-03","cited_by_count":94},{"id":"1912.03203","title":"Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference","created":"2019-12-06","cited_by_count":91},{"id":"2202.02931","title":"TRGP: Trust Region Gradient Projection for Continual Learning","created":"2022-02-07","cited_by_count":82},{"id":"2003.11942","title":"Towards Backward-Compatible Representation Learning","created":"2020-03-26","cited_by_count":75},{"id":"2002.07772","title":"The Tree Ensemble Layer: Differentiability meets Conditional Computation","created":"2020-02-18","cited_by_count":57},{"id":"2011.09161","title":"Positive-Congruent Training: Towards Regression-Free Model Updates","created":"2020-11-18","cited_by_count":57},{"id":"1704.01344","title":"Not All Pixels Are Equal: Difficulty-aware Semantic Segmentation via Deep Layer Cascade","created":"2017-04-05","cited_by_count":53},{"id":"2002.07965","title":"Being Bayesian about Categorical Probability","created":"2020-02-19","cited_by_count":35},{"id":"1708.04607","title":"Segmentation-Aware Convolutional Networks Using Local Attention Masks","created":"2017-08-15","cited_by_count":31},{"id":"1910.02940","title":"Deformable Kernels: Adapting Effective Receptive Fields for Object Deformation","created":"2019-10-07","cited_by_count":29},{"id":"2006.16331","title":"Asymmetric metric learning for knowledge transfer","created":"2020-06-29","cited_by_count":29},{"id":"2104.12642","title":"CompOFA: Compound Once-For-All Networks for Faster Multi-Platform Deployment","created":"2021-04-26","cited_by_count":26},{"id":"1406.7362","title":"Exponentially Increasing the Capacity-to-Computation Ratio for Conditional Computation in Deep Learning","created":"2014-06-28","cited_by_count":24},{"id":"1603.01250","title":"Decision Forests, Convolutional Networks and the Models in-Between","created":"2016-03-03","cited_by_count":15},{"id":"1805.01556","title":"Pixel-wise Attentional Gating for Parsimonious Pixel Labeling","created":"2018-05-03","cited_by_count":12},{"id":"2102.13549","title":"Gradient-guided Loss Masking for Neural Machine Translation","created":"2021-02-26","cited_by_count":8},{"id":"2108.03372","title":"Neighborhood Consensus Contrastive Learning for Backward-Compatible Representation","created":"2021-08-07","cited_by_count":8},{"id":"1603.04186","title":"Visual Concept Recognition and Localization via Iterative Introspection","created":"2016-03-14","cited_by_count":6}],"next_cursor":null}