https://github.com/vcg-uvic/image-matching-benchmark
공식 코드Image Matching across Wide Baselines: From Paper to Practice
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/vchitect/vbench
공식 코드VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models
https://github.com/vcl-iisc/CoNMix
공식 코드CoNMix for Source-free Single and Multi-target Domain Adaptation
https://github.com/vcl-iisc/ZSKD
공식 코드https://github.com/vcl-iisc/data-free-defense-at-test-time
공식 코드https://github.com/vcl-iisc/improved-data-free-test-time-adversarial-defense
공식 코드https://github.com/vectara/FaithJudge
공식 코드Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards
https://github.com/vectorinstitute/humanibench
공식 코드HumaniBench: A Human-Centric Framework for Large Multimodal Models Evaluation
https://github.com/vertaix/llm4mat-bench
공식 코드LLM4Mat-Bench: Benchmarking Large Language Models for Materials Property Prediction
https://github.com/vgthengane/climb3d
공식 코드CLIMB-3D: Continual Learning for Imbalanced 3D Instance Segmentation
https://github.com/vgthengane/continual-clip
공식 코드https://github.com/vibashan/irg-sfda
공식 코드Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection
https://github.com/victorzxy/graphac
공식 코드Task-Agnostic Graph Neural Network Evaluation via Adversarial Collaboration
https://github.com/viczong/extract_covid19_events_from_twitter
공식 코드COVID-19 event extraction from Twitter via extractive question answering with continuous prompts
https://github.com/video-db/ocr-benchmark
공식 코드Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments
https://github.com/viebboy/SRM
공식 코드https://github.com/vijaydwivedi75/lrgb
공식 코드https://github.com/vimal-isi-edu/BioFors
공식 코드https://github.com/vinairesearch/selfsup_pcd
공식 코드Self-Supervised Learning with Multi-View Rendering for 3D Point Cloud Analysis
https://github.com/vinairesearch/tise-toolbox
공식 코드https://github.com/vinayakkapoor/vision_based_grasping_benchmarking
공식 코드A Benchmarking Study of Vision-based Robotic Grasping Algorithms
https://github.com/vincentdengp/3d-lr
공식 코드Can 3D Vision-Language Models Truly Understand Natural Language?
https://github.com/vinthony/depth-distillation
공식 코드https://github.com/vio1etus/flpoison
공식 코드SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning
https://github.com/vis-sustech/visual-analytics-for-emo-algorithm-comparison
공식 코드https://github.com/visinf/idsds
공식 코드https://github.com/visipedia/newt
공식 코드Benchmarking Representation Learning for Natural World Image Collections
https://github.com/visteam-isr-uc/ylfw
공식 코드Young Labeled Faces in the Wild (YLFW): A Dataset for Children Faces Recognition
https://github.com/vita-epfl/jrdb-traj
공식 코드JRDB-Traj: A Dataset and Benchmark for Trajectory Forecasting in Crowds
https://github.com/vita-group/large_scale_gcn_benchmarking
공식 코드A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking
https://github.com/vita-group/slak
공식 코드Are Large Kernels Better Teachers than Transformers for ConvNets?
https://github.com/vita-group/ssharmonization
공식 코드https://github.com/vitae-transformer/aptv2
공식 코드APTv2: Benchmarking Animal Pose Estimation and Tracking with a Large-scale Dataset and Beyond
https://github.com/vitae-transformer/bevsimdet
공식 코드SimDistill: Simulated Multi-modal Distillation for BEV 3D Object Detection
https://github.com/vitae-transformer/simdistill
공식 코드SimDistill: Simulated Multi-modal Distillation for BEV 3D Object Detection
https://github.com/vkinakh/mv-mr
공식 코드MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.