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.
Privacy-Preserving Customer Support: A Framework for Secure and Scalable Interactions
Mobile-TeleVision: Predictive Motion Priors for Humanoid Whole-Body Control
Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning
Robust Multiple Description Neural Video Codec with Masked Transformer for Dynamic and Noisy Networks
DenseVLM: A Retrieval and Decoupled Alignment Framework for Open-Vocabulary Dense Prediction
JAPAGEN: Efficient Few/Zero-shot Learning via Japanese Training Dataset Generation with LLM
KNN-MMD: Cross Domain Wireless Sensing via Local Distribution Alignment
$S^3$: Synonymous Semantic Space for Improving Zero-Shot Generalization of Vision-Language Models
PriorMotion: Generative Class-Agnostic Motion Prediction with Raster-Vector Motion Field Priors
Automated Medical Report Generation for ECG Data: Bridging Medical Text and Signal Processing with Deep Learning
Unified Framework for Open-World Compositional Zero-shot Learning
D-LORD for Motion Stylization
Expanding Event Modality Applications through a Robust CLIP-Based Encoder
Gaussian Processes for Probabilistic Estimates of Earthquake Ground Shaking: A 1-D Proof-of-Concept
Diffusion in Zero-Shot Learning for Environmental Audio
Multimodal Remote Sensing Scene Classification Using VLMs and Dual-Cross Attention Networks
Unveiling Concept Attribution in Diffusion Models
Optimizing Large Language Models for Turkish: New Methodologies in Corpus Selection and Training
Enhancing Robustness of CLIP to Common Corruptions through Bimodal Test-Time Adaptation
PROFIT: A Specialized Optimizer for Deep Fine Tuning
The use of large language models to enhance cancer clinical trial educational materials
Perturb and Recover: Fine-tuning for Effective Backdoor Removal from CLIP
Vision Technologies with Applications in Traffic Surveillance Systems: A Holistic Survey
TAROT: Targeted Data Selection via Optimal Transport
Proto Successor Measure: Representing the Space of All Possible Solutions of Reinforcement Learning
ForgerySleuth: Empowering Multimodal Large Language Models for Image Manipulation Detection
SkelMamba: A State Space Model for Efficient Skeleton Action Recognition of Neurological Disorders
Multimodal Whole Slide Foundation Model for Pathology
Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition
CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image Collections
An End-to-End Two-Stream Network Based on RGB Flow and Representation Flow for Human Action Recognition
Active Data Curation Effectively Distills Large-Scale Multimodal Models
One Mind, Many Tongues: A Deep Dive into Language-Agnostic Knowledge Neurons in Large Language Models
FLEX-CLIP: Feature-Level GEneration Network Enhanced CLIP for X-shot Cross-modal Retrieval
DECODE: Domain-aware Continual Domain Expansion for Motion Prediction
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.