Zero-Shot Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 7
- 평가표
- 33
- 보존된 평가 기록
- 84
Zero-shot learning (ZSL) is a model's ability to detect classes never seen during training. The condition is that the classes are not known during supervised learning.
Earlier work in zero-shot learning use attributes in a two-step approach to infer unknown classes. In the computer vision context, more recent advances learn mappings from image feature space to semantic space. Other approaches learn non-linear multimodal embeddings. In the modern NLP context, language models can be evaluated on downstream tasks without fine tuning.
Benchmark datasets for zero-shot learning include aPY, AwA, and CUB, among others.
( Image credit: Prototypical Networks for Few shot Learning in PyTorch )
Further readings:
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Stylometric Watermarks for Large Language Models
CLIP with Quality Captions: A Strong Pretraining for Vision Tasks
Differentiable Model Scaling using Differentiable Topk
MedConceptsQA: Open Source Medical Concepts QA Benchmark
PRENet: A Plane-Fit Redundancy Encoding Point Cloud Sequence Network for Real-Time 3D Action Recognition
Advanced Natural-based interaction for the ITAlian language: LLaMAntino-3-ANITA
Pseudo-Prompt Generating in Pre-trained Vision-Language Models for Multi-Label Medical Image Classification
A Survey on Backbones for Deep Video Action Recognition
A Mixture of Experts Approach to 3D Human Motion Prediction
The Effect of Model Size on LLM Post-hoc Explainability via LIME
Adversary-Guided Motion Retargeting for Skeleton Anonymization
Unified End-to-End V2X Cooperative Autonomous Driving
Adapting Dual-encoder Vision-language Models for Paraphrased Retrieval
Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt Learning
Enhancing Q-Learning with Large Language Model Heuristics
Dual Relation Mining Network for Zero-Shot Learning
CICA: Content-Injected Contrastive Alignment for Zero-Shot Document Image Classification
Multimodal Sense-Informed Prediction of 3D Human Motions
Source-Free Domain Adaptation Guided by Vision and Vision-Language Pre-Training
Deep Image Restoration For Image Anti-Forensics
Detecting Edited Knowledge in Language Models
Exploiting ChatGPT for Diagnosing Autism-Associated Language Disorders and Identifying Distinct Features
Multi-method Integration with Confidence-based Weighting for Zero-shot Image Classification
What does the Knowledge Neuron Thesis Have to do with Knowledge?
On Mechanistic Knowledge Localization in Text-to-Image Generative Models
StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation
Is Bigger Edit Batch Size Always Better? -- An Empirical Study on Model Editing with Llama-3
CLIPArTT: Adaptation of CLIP to New Domains at Test Time
ADM: Accelerated Diffusion Model via Estimated Priors for Robust Motion Prediction under Uncertainties
PEVA-Net: Prompt-Enhanced View Aggregation Network for Zero/Few-Shot Multi-View 3D Shape Recognition
Weighted Point Cloud Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metric
MAP-Former: Multi-Agent-Pair Gaussian Joint Prediction
CLIP-Mamba: CLIP Pretrained Mamba Models with OOD and Hessian Evaluation
MoST: Multi-modality Scene Tokenization for Motion Prediction
One-Stage Open-Vocabulary Temporal Action Detection Leveraging Temporal Multi-scale and Action Label Features
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.