{"list":"other","total":64,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"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":"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":"1706.05098","title":"An Overview of Multi-Task Learning in Deep Neural Networks","created":"2017-06-15","cited_by_count":803},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"1803.10704","title":"End-to-End Multi-Task Learning with Attention","created":"2018-03-28","cited_by_count":534},{"id":"1812.03443","title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","created":"2018-12-09","cited_by_count":485},{"id":"1604.03539","title":"Cross-stitch Networks for Multi-task Learning","created":"2016-04-12","cited_by_count":467},{"id":"2110.14048","title":"Conflict-Averse Gradient Descent for Multi-task Learning","created":"2021-10-26","cited_by_count":459},{"id":"1905.07553","title":"Which Tasks Should Be Learned Together in Multi-task Learning?","created":"2019-05-18","cited_by_count":375},{"id":"1904.07392","title":"NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection","created":"2019-04-16","cited_by_count":291},{"id":"1901.02985","title":"Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation","created":"2019-01-10","cited_by_count":260},{"id":"1802.07814","title":"Learning to Explain: An Information-Theoretic Perspective on Model Interpretation","created":"2018-02-21","cited_by_count":248},{"id":"1805.04409","title":"PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing","created":"2018-05-11","cited_by_count":224},{"id":"1912.12854","title":"Pareto Multi-Task Learning","created":"2019-12-30","cited_by_count":224},{"id":"2109.04617","title":"Efficiently Identifying Task Groupings for Multi-Task Learning","created":"2021-09-10","cited_by_count":222},{"id":"2010.06808","title":"Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout","created":"2020-10-14","cited_by_count":201},{"id":"1609.02132","title":"UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memory","created":"2016-09-07","cited_by_count":200},{"id":"2010.05874","title":"Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models","created":"2020-10-12","cited_by_count":169},{"id":"1911.12423","title":"AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning","created":"2019-11-27","cited_by_count":160},{"id":"2001.06902","title":"MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning","created":"2020-01-19","cited_by_count":157},{"id":"1904.08918","title":"Attentive Single-Tasking of Multiple Tasks","created":"2019-04-18","cited_by_count":148},{"id":"1906.03525","title":"Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentation","created":"2019-06-08","cited_by_count":142},{"id":"1801.08297","title":"NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reduction","created":"2018-01-25","cited_by_count":127},{"id":"1703.01513","title":"Genetic CNN","created":"2017-03-04","cited_by_count":124},{"id":"2006.01895","title":"Learning to Branch for Multi-Task Learning","created":"2020-06-02","cited_by_count":115},{"id":"1711.00123","title":"Backpropagation through the Void: Optimizing control variates for black-box gradient estimation","created":"2017-10-31","cited_by_count":106},{"id":"2111.10603","title":"Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learning","created":"2021-11-20","cited_by_count":101},{"id":"1711.06798","title":"MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks","created":"2017-11-18","cited_by_count":94},{"id":"1904.02920","title":"Branched Multi-Task Networks: Deciding What Layers To Share","created":"2019-04-05","cited_by_count":76},{"id":"1605.06391","title":"Deep Multi-task Representation Learning: A Tensor Factorisation Approach","created":"2016-05-20","cited_by_count":69},{"id":"2201.04122","title":"In Defense of the Unitary Scalarization for Deep Multi-Task Learning","created":"2022-01-11","cited_by_count":67},{"id":"2209.11379","title":"Do Current Multi-Task Optimization Methods in Deep Learning Even Help?","created":"2022-09-23","cited_by_count":60},{"id":"2003.12238","title":"MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation","created":"2020-03-27","cited_by_count":57},{"id":"1809.04766","title":"Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations","created":"2018-09-13","cited_by_count":51},{"id":"2008.10292","title":"Automated Search for Resource-Efficient Branched Multi-Task Networks","created":"2020-08-24","cited_by_count":51},{"id":"2003.14058","title":"MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learning","created":"2020-03-31","cited_by_count":50},{"id":"1908.09550","title":"Customizable Architecture Search for Semantic Segmentation","created":"2019-08-26","cited_by_count":41},{"id":"1903.03777","title":"Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search","created":"2019-03-09","cited_by_count":39},{"id":"1906.06059","title":"MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation","created":"2019-06-14","cited_by_count":39},{"id":"1912.06844","title":"Regularizing Deep Multi-Task Networks using Orthogonal Gradients","created":"2019-12-14","cited_by_count":36},{"id":"1708.02813","title":"BlitzNet: A Real-Time Deep Network for Scene Understanding","created":"2017-08-09","cited_by_count":29},{"id":"1606.01735","title":"Integrated perception with recurrent multi-task neural networks","created":"2016-06-06","cited_by_count":24},{"id":"1905.08537","title":"Adaptive Stochastic Natural Gradient Method for One-Shot Neural Architecture Search","created":"2019-05-21","cited_by_count":23},{"id":"1710.08247","title":"Generic 3D Representation via Pose Estimation and Matching","created":"2017-10-23","cited_by_count":17},{"id":"2104.07639","title":"Robust Optimization for Multilingual Translation with Imbalanced Data","created":"2021-04-15","cited_by_count":15},{"id":"2012.09496","title":"Exploiting Learnable Joint Groups for Hand Pose Estimation","created":"2020-12-17","cited_by_count":11},{"id":"1812.05285","title":"IRLAS: Inverse Reinforcement Learning for Architecture Search","created":"2018-12-13","cited_by_count":10},{"id":"1808.00193","title":"Reinforced Evolutionary Neural Architecture Search","created":"2018-08-01","cited_by_count":5},{"id":"2405.05695","title":"Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost","created":"2024-05-09","cited_by_count":1}],"next_cursor":null}