{"list":"other","total":66,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"1612.03928","title":"Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer","created":"2016-12-12","cited_by_count":1077},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"1910.10699","title":"Contrastive Representation Distillation","created":"2019-10-23","cited_by_count":748},{"id":"1704.05796","title":"Network Dissection: Quantifying Interpretability of Deep Visual Representations","created":"2017-04-19","cited_by_count":708},{"id":"2001.05566","title":"Image Segmentation Using Deep Learning: A Survey","created":"2020-01-15","cited_by_count":660},{"id":"1706.00384","title":"Deep Mutual Learning","created":"2017-06-01","cited_by_count":628},{"id":"1704.03296","title":"Interpretable Explanations of Black Boxes by Meaningful Perturbation","created":"2017-04-11","cited_by_count":612},{"id":"1902.03393","title":"Improved Knowledge Distillation via Teacher Assistant","created":"2019-02-09","cited_by_count":573},{"id":"1905.05055","title":"Object Detection in 20 Years: A Survey","created":"2019-05-13","cited_by_count":531},{"id":"1907.09682","title":"Similarity-Preserving Knowledge Distillation","created":"2019-07-23","cited_by_count":516},{"id":"1905.08094","title":"Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation","created":"2019-05-17","cited_by_count":497},{"id":"1910.01348","title":"On the Efficacy of Knowledge Distillation","created":"2019-10-03","cited_by_count":381},{"id":"1711.00867","title":"The (Un)reliability of saliency methods","created":"2017-11-02","cited_by_count":333},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319},{"id":"2004.05937","title":"Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks","created":"2020-04-13","cited_by_count":316},{"id":"1802.04977","title":"Paraphrasing Complex Network: Network Compression via Factor Transfer","created":"2018-02-14","cited_by_count":260},{"id":"2205.10536","title":"Knowledge Distillation from A Stronger Teacher","created":"2022-05-21","cited_by_count":208},{"id":"1806.04606","title":"Knowledge Distillation by On-the-Fly Native Ensemble","created":"2018-06-12","cited_by_count":186},{"id":"2002.05715","title":"Self-Distillation Amplifies Regularization in Hilbert Space","created":"2020-02-13","cited_by_count":173},{"id":"1908.00821","title":"Learning Lightweight Lane Detection CNNs by Self Attention Distillation","created":"2019-08-02","cited_by_count":162},{"id":"2302.10035","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","created":"2023-02-20","cited_by_count":153},{"id":"2206.06565","title":"LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks","created":"2022-06-14","cited_by_count":148},{"id":"1804.03235","title":"Large scale distributed neural network training through online distillation","created":"2018-04-09","cited_by_count":146},{"id":"2211.01367","title":"Two-Stream Network for Sign Language Recognition and Translation","created":"2022-11-02","cited_by_count":123},{"id":"2210.11584","title":"Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations","created":"2022-10-20","cited_by_count":85},{"id":"2009.08825","title":"Densely Guided Knowledge Distillation using Multiple Teacher Assistants","created":"2020-09-18","cited_by_count":83},{"id":"1904.09149","title":"Knowledge Distillation via Route Constrained Optimization","created":"2019-04-19","cited_by_count":75},{"id":"2005.00727","title":"Heterogeneous Knowledge Distillation using Information Flow Modeling","created":"2020-05-02","cited_by_count":73},{"id":"2310.19909","title":"Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks","created":"2023-10-30","cited_by_count":72},{"id":"2205.10793","title":"Knowledge Distillation via the Target-aware Transformer","created":"2022-05-22","cited_by_count":70},{"id":"2003.03622","title":"Explaining Knowledge Distillation by Quantifying the Knowledge","created":"2020-03-07","cited_by_count":66},{"id":"2102.07650","title":"Learning Student-Friendly Teacher Networks for Knowledge Distillation","created":"2021-02-12","cited_by_count":60},{"id":"2305.15712","title":"Knowledge Diffusion for Distillation","created":"2023-05-25","cited_by_count":53},{"id":"2204.07356","title":"Vision-and-Language Pretrained Models: A Survey","created":"2022-04-15","cited_by_count":50},{"id":"1807.06819","title":"Self-supervised Knowledge Distillation Using Singular Value Decomposition","created":"2018-07-18","cited_by_count":48},{"id":"2404.07236","title":"Lightweight Deep Learning for Resource-Constrained Environments: A Survey","created":"2024-04-08","cited_by_count":38},{"id":"2305.01040","title":"CLIP-S$^4$: Language-Guided Self-Supervised Semantic Segmentation","created":"2023-05-01","cited_by_count":34},{"id":"2105.00290","title":"A Peek Into the Reasoning of Neural Networks: Interpreting with Structural Visual Concepts","created":"2021-05-01","cited_by_count":33},{"id":"2110.15210","title":"Towards Model Agnostic Federated Learning Using Knowledge Distillation","created":"2021-10-28","cited_by_count":31},{"id":"2007.09029","title":"Knowledge Distillation in Deep Learning and its Applications","created":"2020-07-17","cited_by_count":29},{"id":"2306.10687","title":"Categories of Response-Based, Feature-Based, and Relation-Based Knowledge Distillation","created":"2023-06-19","cited_by_count":20},{"id":"2208.08741","title":"Quantifying the Knowledge in a DNN to Explain Knowledge Distillation for Classification","created":"2022-08-18","cited_by_count":19},{"id":"2204.01888","title":"ConceptExplainer: Interactive Explanation for Deep Neural Networks from a Concept Perspective","created":"2022-04-04","cited_by_count":18},{"id":"2108.03738","title":"Human-in-the-loop Extraction of Interpretable Concepts in Deep Learning Models","created":"2021-08-08","cited_by_count":17},{"id":"2211.13133","title":"Structural Knowledge Distillation for Object Detection","created":"2022-11-23","cited_by_count":14},{"id":"2108.12931","title":"NeuroCartography: Scalable Automatic Visual Summarization of Concepts in Deep Neural Networks","created":"2021-08-29","cited_by_count":12},{"id":"2308.06453","title":"Multi-Label Knowledge Distillation","created":"2023-08-12","cited_by_count":12},{"id":"2111.03505","title":"Visualizing the Emergence of Intermediate Visual Patterns in DNNs","created":"2021-11-05","cited_by_count":7},{"id":"2402.12406","title":"Teacher as a Lenient Expert: Teacher-Agnostic Data-Free Knowledge Distillation","created":"2024-02-18","cited_by_count":5},{"id":"2009.09140","title":"Introspective Learning by Distilling Knowledge from Online Self-explanation","created":"2020-09-19","cited_by_count":3},{"id":"2205.03601","title":"ConceptDistil: Model-Agnostic Distillation of Concept Explanations","created":"2022-05-07","cited_by_count":2},{"id":"2303.08360","title":"Knowledge Distillation from Single to Multi Labels: an Empirical Study","created":"2023-03-15","cited_by_count":2},{"id":"2402.14922","title":"Practical Insights into Knowledge Distillation for Pre-Trained Models","created":"2024-02-22","cited_by_count":2},{"id":"2308.13958","title":"Improving Knowledge Distillation for BERT Models: Loss Functions, Mapping Methods, and Weight Tuning","created":"2023-08-26","cited_by_count":1}],"next_cursor":null}