{"list":"other","total":94,"rows":[{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1904.01866","title":"A Comprehensive Overhaul of Feature Distillation","created":"2019-04-03","cited_by_count":348},{"id":"2104.09044","title":"Distilling Knowledge via Knowledge Review","created":"2021-04-19","cited_by_count":288},{"id":"1905.12886","title":"iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images","created":"2019-05-30","cited_by_count":197},{"id":"2007.05558","title":"The Computational Limits of Deep Learning","created":"2020-07-10","cited_by_count":193},{"id":"2106.05945","title":"Does Knowledge Distillation Really Work?","created":"2021-06-10","cited_by_count":190},{"id":"1905.00076","title":"Ensemble Distribution Distillation","created":"2019-04-30","cited_by_count":158},{"id":"1804.03235","title":"Large scale distributed neural network training through online distillation","created":"2018-04-09","cited_by_count":146},{"id":"2012.03236","title":"Cross-Layer Distillation with Semantic Calibration","created":"2020-12-06","cited_by_count":143},{"id":"2006.07114","title":"Knowledge Distillation Meets Self-Supervision","created":"2020-06-12","cited_by_count":142},{"id":"2301.07014","title":"Dataset Distillation: A Comprehensive Review","created":"2023-01-17","cited_by_count":127},{"id":"1910.02551","title":"Soft-Label Dataset Distillation and Text Dataset Distillation","created":"2019-10-06","cited_by_count":107},{"id":"1711.05852","title":"Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy","created":"2017-11-15","cited_by_count":101},{"id":"2301.04272","title":"Data Distillation: A Survey","created":"2023-01-11","cited_by_count":87},{"id":"2005.00727","title":"Heterogeneous Knowledge Distillation using Information Flow Modeling","created":"2020-05-02","cited_by_count":73},{"id":"2303.13005","title":"From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels","created":"2023-03-23","cited_by_count":69},{"id":"2102.04420","title":"The Multi-Temporal Urban Development SpaceNet Dataset","created":"2021-02-08","cited_by_count":62},{"id":"2001.01306","title":"Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysis","created":"2020-01-05","cited_by_count":61},{"id":"2112.07558","title":"Multi-Modal Temporal Attention Models for Crop Mapping from Satellite Time Series","created":"2021-12-14","cited_by_count":49},{"id":"2006.02963","title":"RarePlanes: Synthetic Data Takes Flight","created":"2020-06-04","cited_by_count":48},{"id":"2004.06500","title":"SpaceNet 6: Multi-Sensor All Weather Mapping Dataset","created":"2020-04-14","cited_by_count":47},{"id":"2304.04262","title":"A Comprehensive Survey on Knowledge Distillation of Diffusion Models","created":"2023-04-09","cited_by_count":45},{"id":"1911.03462","title":"Knowledge Distillation for Incremental Learning in Semantic Segmentation","created":"2019-11-08","cited_by_count":40},{"id":"2004.00176","title":"Knowledge as Priors: Cross-Modal Knowledge Generalization for Datasets without Superior Knowledge","created":"2020-04-01","cited_by_count":35},{"id":"2008.07816","title":"Knowledge Transfer via Dense Cross-Layer Mutual-Distillation","created":"2020-08-18","cited_by_count":32},{"id":"2108.05698","title":"Preventing Catastrophic Forgetting and Distribution Mismatch in Knowledge Distillation via Synthetic Data","created":"2021-08-11","cited_by_count":32},{"id":"2208.10160","title":"PANDA: Prompt Transfer Meets Knowledge Distillation for Efficient Model Adaptation","created":"2022-08-22","cited_by_count":31},{"id":"2303.11098","title":"Understanding the Role of the Projector in Knowledge Distillation","created":"2023-03-20","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":"2002.12620","title":"TextBrewer: An Open-Source Knowledge Distillation Toolkit for Natural Language Processing","created":"2020-02-28","cited_by_count":26},{"id":"2304.01731","title":"Selective Knowledge Sharing for Privacy-Preserving Federated Distillation without A Good Teacher","created":"2023-04-04","cited_by_count":25},{"id":"2010.03034","title":"Why Skip If You Can Combine: A Simple Knowledge Distillation Technique for Intermediate Layers","created":"2020-10-06","cited_by_count":24},{"id":"2103.14473","title":"Distilling a Powerful Student Model via Online Knowledge Distillation","created":"2021-03-26","cited_by_count":22},{"id":"2204.07028","title":"Exploring the Distributed Knowledge Congruence in Proxy-data-free Federated Distillation","created":"2022-04-14","cited_by_count":22},{"id":"2310.00258","title":"NAYER: Noisy Layer Data Generation for Efficient and Effective Data-free Knowledge Distillation","created":"2023-09-30","cited_by_count":22},{"id":"2209.13335","title":"PROD: Progressive Distillation for Dense Retrieval","created":"2022-09-27","cited_by_count":21},{"id":"2304.10550","title":"Deep transfer learning for intrusion detection in industrial control networks: A comprehensive review","created":"2023-04-19","cited_by_count":21},{"id":"2306.10687","title":"Categories of Response-Based, Feature-Based, and Relation-Based Knowledge Distillation","created":"2023-06-19","cited_by_count":20},{"id":"2406.07876","title":"Small Scale Data-Free Knowledge Distillation","created":"2024-06-12","cited_by_count":20},{"id":"2011.12913","title":"torchdistill: A Modular, Configuration-Driven Framework for Knowledge Distillation","created":"2020-11-25","cited_by_count":19},{"id":"2105.06987","title":"Scaling Ensemble Distribution Distillation to Many Classes with Proxy Targets","created":"2021-05-14","cited_by_count":19},{"id":"2401.15863","title":"Importance-Aware Adaptive Dataset Distillation","created":"2024-01-29","cited_by_count":18},{"id":"2104.00352","title":"Decentralized and Model-Free Federated Learning: Consensus-Based Distillation in Function Space","created":"2021-04-01","cited_by_count":17},{"id":"2406.01954","title":"Plug-and-Play Diffusion Distillation","created":"2024-06-04","cited_by_count":16},{"id":"2402.09816","title":"Mind the Modality Gap: Towards a Remote Sensing Vision-Language Model via Cross-modal Alignment","created":"2024-02-15","cited_by_count":15},{"id":"2403.09053","title":"Towards a theory of model distillation","created":"2024-03-14","cited_by_count":15},{"id":"2105.07637","title":"Class-Incremental Few-Shot Object Detection","created":"2021-05-17","cited_by_count":13},{"id":"2302.02108","title":"Knowledge Distillation in Vision Transformers: A Critical Review","created":"2023-02-04","cited_by_count":13},{"id":"2203.11490","title":"SSD-KD: A Self-supervised Diverse Knowledge Distillation Method for Lightweight Skin Lesion Classification Using Dermoscopic Images","created":"2022-03-22","cited_by_count":12},{"id":"2204.00771","title":"Fast Real-time Personalized Speech Enhancement: End-to-End Enhancement Network (E3Net) and Knowledge Distillation","created":"2022-04-02","cited_by_count":12},{"id":"2310.04550","title":"Module-wise Adaptive Distillation for Multimodality Foundation Models","created":"2023-10-06","cited_by_count":12},{"id":"2203.08295","title":"Self-Distribution Distillation: Efficient Uncertainty Estimation","created":"2022-03-15","cited_by_count":11},{"id":"2312.15322","title":"Hardware-Aware DNN Compression via Diverse Pruning and Mixed-Precision Quantization","created":"2023-12-23","cited_by_count":10},{"id":"2404.00936","title":"A Comprehensive Review of Knowledge Distillation in Computer Vision","created":"2024-04-01","cited_by_count":10},{"id":"2004.08116","title":"Triplet Loss for Knowledge Distillation","created":"2020-04-17","cited_by_count":9},{"id":"2110.02580","title":"Deep Transfer Learning for Land Use and Land Cover Classification: A Comparative Study","created":"2021-10-06","cited_by_count":9},{"id":"2110.15538","title":"On Cross-Layer Alignment for Model Fusion of Heterogeneous Neural Networks","created":"2021-10-29","cited_by_count":9},{"id":"2205.06701","title":"Knowledge Distillation Meets Open-Set Semi-Supervised Learning","created":"2022-05-13","cited_by_count":9},{"id":"2209.03355","title":"Generative Adversarial Super-Resolution at the Edge with Knowledge Distillation","created":"2022-09-07","cited_by_count":9},{"id":"2306.14662","title":"Cross Architecture Distillation for Face Recognition","created":"2023-06-26","cited_by_count":9},{"id":"2309.07707","title":"CoLLD: Contrastive Layer-to-layer Distillation for Compressing Multilingual Pre-trained Speech Encoders","created":"2023-09-14","cited_by_count":9},{"id":"2407.17877","title":"Advancing 3D Point Cloud Understanding through Deep Transfer Learning: A Comprehensive Survey","created":"2024-07-25","cited_by_count":9},{"id":"2408.10210","title":"A Survey on Symbolic Knowledge Distillation of Large Language Models","created":"2024-07-12","cited_by_count":9},{"id":"2203.14205","title":"Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparison","created":"2022-03-27","cited_by_count":8},{"id":"2305.06244","title":"Explainable Knowledge Distillation for On-device Chest X-Ray Classification","created":"2023-05-10","cited_by_count":8},{"id":"2309.06612","title":"Harmonic-NAS: Hardware-Aware Multimodal Neural Architecture Search on Resource-constrained Devices","created":"2023-09-12","cited_by_count":8},{"id":"2311.08955","title":"A Spectral Diffusion Prior for Hyperspectral Image Super-Resolution","created":"2023-11-15","cited_by_count":8},{"id":"2003.05326","title":"Training-Set Distillation for Real-Time UAV Object Tracking","created":"2020-03-11","cited_by_count":7},{"id":"2203.08667","title":"Graph Flow: Cross-layer Graph Flow Distillation for Dual Efficient Medical Image Segmentation","created":"2022-03-16","cited_by_count":7},{"id":"2305.05233","title":"DynamicKD: An Effective Knowledge Distillation via Dynamic Entropy Correction-Based Distillation for Gap Optimizing","created":"2023-05-09","cited_by_count":7},{"id":"2109.12662","title":"Improving Question Answering Performance Using Knowledge Distillation and Active Learning","created":"2021-09-26","cited_by_count":6},{"id":"2112.03814","title":"A Contrastive Distillation Approach for Incremental Semantic Segmentation in Aerial Images","created":"2021-12-07","cited_by_count":6},{"id":"2204.01542","title":"CDKT-FL: Cross-Device Knowledge Transfer using Proxy Dataset in Federated Learning","created":"2022-04-04","cited_by_count":6},{"id":"2402.11242","title":"Learning with Imbalanced Noisy Data by Preventing Bias in Sample Selection","created":"2024-02-17","cited_by_count":6},{"id":"2408.07080","title":"DisCoM-KD: Cross-Modal Knowledge Distillation via Disentanglement Representation and Adversarial Learning","created":"2024-08-05","cited_by_count":6},{"id":"2108.12173","title":"CoCo DistillNet: a Cross-layer Correlation Distillation Network for Pathological Gastric Cancer Segmentation","created":"2021-08-27","cited_by_count":5},{"id":"2201.11661","title":"TrustAL: Trustworthy Active Learning using Knowledge Distillation","created":"2022-01-26","cited_by_count":5},{"id":"2309.08961","title":"UNIDEAL: Curriculum Knowledge Distillation Federated Learning","created":"2023-09-16","cited_by_count":4},{"id":"2310.08619","title":"Unlocking the capabilities of explainable fewshot learning in remote sensing","created":"2023-10-12","cited_by_count":4},{"id":"2404.01746","title":"Towards Scalable & Efficient Interaction-Aware Planning in Autonomous Vehicles using Knowledge Distillation","created":"2024-04-02","cited_by_count":4},{"id":"2404.14704","title":"Unsupervised Domain Adaptation Architecture Search with Self-Training for Land Cover Mapping","created":"2024-04-23","cited_by_count":4},{"id":"2406.13344","title":"WaterMono: Teacher-Guided Anomaly Masking and Enhancement Boosting for Robust Underwater Self-Supervised Monocular Depth Estimation","created":"2024-06-19","cited_by_count":4},{"id":"2407.14242","title":"Continual Panoptic Perception: Towards Multi-modal Incremental Interpretation of Remote Sensing Images","created":"2024-07-19","cited_by_count":4},{"id":"2407.18175","title":"Quasar-ViT: Hardware-Oriented Quantization-Aware Architecture Search for Vision Transformers","created":"2024-07-25","cited_by_count":4},{"id":"2408.04278","title":"LaDiMo: Layer-wise Distillation Inspired MoEfier","created":"2024-08-08","cited_by_count":4},{"id":"2404.06795","title":"Extracting Clean and Balanced Subset for Noisy Long-tailed Classification","created":"2024-04-10","cited_by_count":3},{"id":"2301.08092","title":"RNAS-CL: Robust Neural Architecture Search by Cross-Layer Knowledge Distillation","created":"2023-01-19","cited_by_count":2},{"id":"2401.09271","title":"PixelDINO: Semi-Supervised Semantic Segmentation for Detecting Permafrost Disturbances","created":"2024-01-17","cited_by_count":2},{"id":"1812.02937","title":"Optimizing speed/accuracy trade-off for person re-identification via knowledge distillation","created":"2018-12-07","cited_by_count":1},{"id":"2209.04130","title":"In-situ animal behavior classification using knowledge distillation and fixed-point quantization","created":"2022-09-09","cited_by_count":1},{"id":"2210.13743","title":"Online Cross-Layer Knowledge Distillation on Graph Neural Networks with Deep Supervision","created":"2022-10-25","cited_by_count":1},{"id":"2405.20058","title":"Enhancing Plant Disease Detection: A Novel CNN-Based Approach with Tensor Subspace Learning and HOWSVD-MD","created":"2024-05-30","cited_by_count":1},{"id":"2407.04871","title":"Improving Knowledge Distillation in Transfer Learning with Layer-wise Learning Rates","created":"2024-07-05","cited_by_count":1}],"next_cursor":null}