https://github.com/HowToMakeABomb101/Hot2MakeAB0mbSite
Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
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.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
I Think, Therefore I am: Benchmarking Awareness of Large Language Models Using AwareBench
Towards Efficient Unconstrained Palmprint Recognition via Deep Distillation Hashing
A Baseline Statistical Method For Robust User-Assisted Multiple Segmentation
SeizureNet: Multi-Spectral Deep Feature Learning for Seizure Type Classification
Learning Transferable Visual Models From Natural Language Supervision
IOHprofiler: A Benchmarking and Profiling Tool for Iterative Optimization Heuristics
IOHprofiler: A Benchmarking and Profiling Tool for Iterative Optimization Heuristics
IOHprofiler: A Benchmarking and Profiling Tool for Iterative Optimization Heuristics
Introducing SLAMBench, a performance and accuracy benchmarking methodology for SLAM
Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation
Benchmarking the Combinatorial Generalizability of Complex Query Answering on Knowledge Graphs
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
Wasserstein Distance Rivals Kullback-Leibler Divergence for Knowledge Distillation
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
COCO: A Platform for Comparing Continuous Optimizers in a Black-Box Setting
Visual Relationship Detection with Language prior and Softmax
BiM-VFI: directional Motion Field-Guided Frame Interpolation for Video with Non-uniform Motions
Parameter-efficient Model Adaptation for Vision Transformers
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.