https://github.com/facebookresearch/fair_self_supervision_benchmark
공식 코드Scaling and Benchmarking Self-Supervised Visual Representation Learning
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/facebookresearch/fjd
공식 코드https://github.com/facebookresearch/habitat-sim
공식 코드https://github.com/facebookresearch/intphys2
공식 코드IntPhys 2: Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments
https://github.com/facebookresearch/otter
공식 코드Data Efficient Language-supervised Zero-shot Recognition with Optimal Transport Distillation
https://github.com/facebookresearch/pearl
공식 코드https://github.com/facebookresearch/projectaria_tools
공식 코드Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perception
https://github.com/facebookresearch/pyrobot
공식 코드PyRobot: An Open-source Robotics Framework for Research and Benchmarking
https://github.com/facebookresearch/selavi
공식 코드Labelling unlabelled videos from scratch with multi-modal self-supervision
https://github.com/facebookresearch/tacto
공식 코드TACTO: A Fast, Flexible, and Open-source Simulator for High-Resolution Vision-based Tactile Sensors
https://github.com/facebookresearch/vizseq
공식 코드https://github.com/facebookresearch/wasp
공식 코드WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks
https://github.com/fadedcosine/knn-kd
공식 코드Nearest Neighbor Knowledge Distillation for Neural Machine Translation
https://github.com/fahim-sikder/fairx
공식 코드https://github.com/fair4hep/pfin4uqad
공식 코드https://github.com/fancyssc/step
공식 코드STEP: A Unified Spiking Transformer Evaluation Platform for Fair and Reproducible Benchmarking
https://github.com/fang-haoshu/halpe-fullbody
공식 코드AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time
https://github.com/fantasy-shaw/h-stformer
공식 코드Transport-Hub-Aware Spatial-Temporal Adaptive Graph Transformer for Traffic Flow Prediction
https://github.com/fanyan0411/dsgd
공식 코드Dynamic Sub-graph Distillation for Robust Semi-supervised Continual Learning
https://github.com/farama-foundation/arcade-learning-environment
공식 코드https://github.com/farama-foundation/momaland
공식 코드MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning
https://github.com/fast-vid2vid/fast-vid2vid
공식 코드Fast-Vid2Vid: Spatial-Temporal Compression for Video-to-Video Synthesis
https://github.com/fau-lms/ncn_for_m2m
공식 코드Boosting Neural Image Compression for Machines Using Latent Space Masking
https://github.com/fcdl94/fss
공식 코드https://github.com/fcdl94/mma
공식 코드Modeling Missing Annotations for Incremental Learning in Object Detection
https://github.com/fchollet/ARC
공식 코드https://github.com/fdbtrs/AdaDistill
공식 코드AdaDistill: Adaptive Knowledge Distillation for Deep Face Recognition
https://github.com/fdbtrs/masked-face-recognition-kd
공식 코드Mask-invariant Face Recognition through Template-level Knowledge Distillation
https://github.com/fdbtrs/pocketnet
공식 코드https://github.com/fedbkd/fedbkd
공식 코드FedBKD: Distilled Federated Learning to Embrace Gerneralization and Personalization on Non-IID Data
https://github.com/fedgraph/fedgraph
공식 코드FedGraph: A Research Library and Benchmark for Federated Graph Learning
https://github.com/fedml-ai/fedcv
공식 코드FedCV: A Federated Learning Framework for Diverse Computer Vision Tasks
https://github.com/feedzai/fifar-dataset
공식 코드https://github.com/feilumath/benchmark_TSC
공식 코드Benchmarking optimality of time series classification methods in distinguishing diffusions
https://github.com/feiyanhu/tinyhd
공식 코드https://github.com/felixleopoldo/benchpress
공식 코드Benchpress: A Scalable and Versatile Workflow for Benchmarking Structure Learning Algorithms
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.