Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204510963> ?p ?o ?g. }
- W3204510963 endingPage "3068" @default.
- W3204510963 startingPage "3048" @default.
- W3204510963 abstract "Deep neural models, in recent years, have been successful in almost every field, even solving the most complex problem statements. However, these models are huge in size with millions (and even billions) of parameters, demanding heavy computation power and failing to be deployed on edge devices. Besides, the performance boost is highly dependent on redundant labeled data. To achieve faster speeds and to handle the problems caused by the lack of labeled data, knowledge distillation (KD) has been proposed to transfer information learned from one model to another. KD is often characterized by the so-called 'Student-Teacher' (S-T) learning framework and has been broadly applied in model compression and knowledge transfer. This paper is about KD and S-T learning, which are being actively studied in recent years. First, we aim to provide explanations of what KD is and how/why it works. Then, we provide a comprehensive survey on the recent progress of KD methods together with S-T frameworks typically used for vision tasks. In general, we investigate some fundamental questions that have been driving this research area and thoroughly generalize the research progress and technical details. Additionally, we systematically analyze the research status of KD in vision applications. Finally, we discuss the potentials and open challenges of existing methods and prospect the future directions of KD and S-T learning." @default.
- W3204510963 created "2021-10-11" @default.
- W3204510963 creator A5012837410 @default.
- W3204510963 creator A5027206148 @default.
- W3204510963 date "2022-06-01" @default.
- W3204510963 modified "2023-10-16" @default.
- W3204510963 title "Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks" @default.
- W3204510963 cites W2064675550 @default.
- W3204510963 cites W2077947937 @default.
- W3204510963 cites W2097117768 @default.
- W3204510963 cites W2108598243 @default.
- W3204510963 cites W2294370754 @default.
- W3204510963 cites W2296073425 @default.
- W3204510963 cites W2336829997 @default.
- W3204510963 cites W2413439537 @default.
- W3204510963 cites W2511428026 @default.
- W3204510963 cites W2592335154 @default.
- W3204510963 cites W2612703655 @default.
- W3204510963 cites W2620998106 @default.
- W3204510963 cites W2739879705 @default.
- W3204510963 cites W2743289088 @default.
- W3204510963 cites W2747909401 @default.
- W3204510963 cites W2776460497 @default.
- W3204510963 cites W2798599891 @default.
- W3204510963 cites W2799062425 @default.
- W3204510963 cites W2808668169 @default.
- W3204510963 cites W2885895075 @default.
- W3204510963 cites W2886300652 @default.
- W3204510963 cites W2886322387 @default.
- W3204510963 cites W2886756692 @default.
- W3204510963 cites W2888358068 @default.
- W3204510963 cites W2903707108 @default.
- W3204510963 cites W2904170036 @default.
- W3204510963 cites W2904206140 @default.
- W3204510963 cites W2905535599 @default.
- W3204510963 cites W2908993000 @default.
- W3204510963 cites W2936864631 @default.
- W3204510963 cites W2940288022 @default.
- W3204510963 cites W2945052683 @default.
- W3204510963 cites W2945505221 @default.
- W3204510963 cites W2947696193 @default.
- W3204510963 cites W2948582784 @default.
- W3204510963 cites W2948697666 @default.
- W3204510963 cites W2948734064 @default.
- W3204510963 cites W2952787292 @default.
- W3204510963 cites W2954373340 @default.
- W3204510963 cites W2955192706 @default.
- W3204510963 cites W2959289524 @default.
- W3204510963 cites W2963140444 @default.
- W3204510963 cites W2963370235 @default.
- W3204510963 cites W2963397674 @default.
- W3204510963 cites W2963453233 @default.
- W3204510963 cites W2963465221 @default.
- W3204510963 cites W2963558289 @default.
- W3204510963 cites W2963777504 @default.
- W3204510963 cites W2963785012 @default.
- W3204510963 cites W2963801643 @default.
- W3204510963 cites W2963887950 @default.
- W3204510963 cites W2964005298 @default.
- W3204510963 cites W2964016283 @default.
- W3204510963 cites W2964034721 @default.
- W3204510963 cites W2964111476 @default.
- W3204510963 cites W2964268168 @default.
- W3204510963 cites W2964615694 @default.
- W3204510963 cites W2965995832 @default.
- W3204510963 cites W2966861238 @default.
- W3204510963 cites W2969799213 @default.
- W3204510963 cites W2970454332 @default.
- W3204510963 cites W2971047694 @default.
- W3204510963 cites W2979225039 @default.
- W3204510963 cites W2979548969 @default.
- W3204510963 cites W2981694290 @default.
- W3204510963 cites W2981819252 @default.
- W3204510963 cites W2981884310 @default.
- W3204510963 cites W2982157312 @default.
- W3204510963 cites W2982242214 @default.
- W3204510963 cites W2982461124 @default.
- W3204510963 cites W2982802130 @default.
- W3204510963 cites W2983128379 @default.
- W3204510963 cites W2986015886 @default.
- W3204510963 cites W2986349107 @default.
- W3204510963 cites W2986854316 @default.
- W3204510963 cites W2987014658 @default.
- W3204510963 cites W2987385519 @default.
- W3204510963 cites W2987845715 @default.
- W3204510963 cites W2987861506 @default.
- W3204510963 cites W2988205463 @default.
- W3204510963 cites W2988772405 @default.
- W3204510963 cites W2989980422 @default.
- W3204510963 cites W2990231018 @default.
- W3204510963 cites W2990364385 @default.
- W3204510963 cites W2991633843 @default.
- W3204510963 cites W2991873135 @default.
- W3204510963 cites W2996834012 @default.
- W3204510963 cites W2996970889 @default.
- W3204510963 cites W2997006708 @default.
- W3204510963 cites W2997336365 @default.
- W3204510963 cites W2997563695 @default.