https://github.com/zhouxian/FluidLab
공식 코드FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulation
Papers with Code 아카이브
Knowledge Distillation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 11
- 보존된 평가 기록
- 90
Knowledge distillation is the process of transferring knowledge from a large model to a smaller one. While large models (such as very deep neural networks or ensembles of many models) have higher knowledge capacity than small models, this capacity might not be fully utilized.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/zhouzaida/channel-distillation
공식 코드Channel Distillation: Channel-Wise Attention for Knowledge Distillation
https://github.com/zhouzhengqd/beard
공식 코드BEARD: Benchmarking the Adversarial Robustness for Dataset Distillation
https://github.com/zhuangdizhu/FedGen
공식 코드Data-Free Knowledge Distillation for Heterogeneous Federated Learning
https://github.com/zhudelong/elevator_button_recognition
공식 코드A Large-Scale Dataset for Benchmarking Elevator Button Segmentation and Character Recognition
https://github.com/zhuochunli/learn-from-committee
공식 코드Learning from Committee: Reasoning Distillation from a Mixture of Teachers with Peer-Review
https://github.com/zhxlia/multitat
공식 코드MULTITAT: Benchmarking Multilingual Table-and-Text Question Answering
https://github.com/zhymlumine/nbbench
공식 코드NbBench: Benchmarking Language Models for Comprehensive Nanobody Tasks
https://github.com/zib-iol/feddistill
공식 코드On the Byzantine-Resilience of Distillation-Based Federated Learning
https://github.com/zibojia/rslad
공식 코드Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Better
https://github.com/zibrahim/KD-OP
공식 코드https://github.com/ziegler-ingo/cleavage_prediction
공식 코드What cleaves? Is proteasomal cleavage prediction reaching a ceiling?
https://github.com/zifuwanggg/jdtlosses
공식 코드Jaccard Metric Losses: Optimizing the Jaccard Index with Soft Labels
https://github.com/zihan-liu-00/dl_for_peptide
공식 코드Efficient Prediction of Peptide Self-assembly through Sequential and Graphical Encoding
https://github.com/zihanwangki/x-tc
공식 코드https://github.com/zihuixue/mfh
공식 코드The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation
https://github.com/zihuixue/mke
공식 코드https://github.com/zijianzhang/CARLA_INVS
공식 코드Distributed Dynamic Map Fusion via Federated Learning for Intelligent Networked Vehicles
https://github.com/zikeyuan/gracore
공식 코드GraCoRe: Benchmarking Graph Comprehension and Complex Reasoning in Large Language Models
https://github.com/zinengtang/VidLanKD
공식 코드VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer
https://github.com/zip-group/litv2
공식 코드https://github.com/ziplab/litv2
공식 코드https://github.com/zirak-ai/pashtoocr
공식 코드https://github.com/zisci2/RethinkKD
공식 코드Why does Knowledge Distillation Work? Rethink its Attention and Fidelity Mechanism
https://github.com/zivenzhu/multi-chart-qa
공식 코드MultiChartQA: Benchmarking Vision-Language Models on Multi-Chart Problems
https://github.com/zixuanke/pycontinual
공식 코드CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks
https://github.com/zj-binxia/kdsr
공식 코드Knowledge Distillation based Degradation Estimation for Blind Super-Resolution
https://github.com/zj-binxia/mrda
공식 코드Meta-Learning based Degradation Representation for Blind Super-Resolution
https://github.com/zjjzby/tgnn-fpga-ipdps2022
공식 코드Model-Architecture Co-Design for High Performance Temporal GNN Inference on FPGA
https://github.com/zjq0455/PTQ-Bench
공식 코드https://github.com/zju-swj/rld
공식 코드https://github.com/zju-vipa/DataFree
공식 코드Contrastive Model Inversion for Data-Free Knowledge Distillation
https://github.com/zju-vipa/Fast-Datafree
공식 코드https://github.com/zju-vipa/NetGraft
공식 코드Progressive Network Grafting for Few-Shot Knowledge Distillation
https://github.com/zju-vipa/OSGAN
공식 코드https://github.com/zju-vipa/mosaickd
공식 코드Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.