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.
MENTOR: Multilingual tExt detectioN TOward leaRning by analogy
VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark
BID: Boundary-Interior Decoding for Unsupervised Temporal Action Localization Pre-Trainin
MoralBERT: A Fine-Tuned Language Model for Capturing Moral Values in Social Discussions
pyvene: A Library for Understanding and Improving PyTorch Models via Interventions
Efficiently Quantifying and Mitigating Ripple Effects in Model Editing
Enhancing Joint Motion Prediction for Individuals with Limb Loss Through Model Reprogramming
Transformer-based Fusion of 2D-pose and Spatio-temporal Embeddings for Distracted Driver Action Recognition
Density-Guided Label Smoothing for Temporal Localization of Driving Actions
Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancement
Deep Learning Approaches for Human Action Recognition in Video Data
Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation
Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learning
Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing
Towards Generalizable and Interpretable Motion Prediction: A Deep Variational Bayes Approach
Personalized LoRA for Human-Centered Text Understanding
Editing Conceptual Knowledge for Large Language Models
CSCNET: Class-Specified Cascaded Network for Compositional Zero-Shot Learning
Consecutive Batch Model Editing with HooK Layers
JointMotion: Joint Self-Supervision for Joint Motion Prediction
ACC-ViT : Atrous Convolution's Comeback in Vision Transformers
MedFLIP: Medical Vision-and-Language Self-supervised Fast Pre-Training with Masked Autoencoder
Fooling Neural Networks for Motion Forecasting via Adversarial Attacks
X-Shot: A Unified System to Handle Frequent, Few-shot and Zero-shot Learning Simultaneously in Classification
Modeling Collaborator: Enabling Subjective Vision Classification With Minimal Human Effort via LLM Tool-Use
A Zero-Shot Reinforcement Learning Strategy for Autonomous Guidewire Navigation
Learning Zero-Shot Material States Segmentation, by Implanting Natural Image Patterns in Synthetic Data
DEMOS: Dynamic Environment Motion Synthesis in 3D Scenes via Local Spherical-BEV Perception
DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction
Leveraging Weakly Annotated Data for Hate Speech Detection in Code-Mixed Hinglish: A Feasibility-Driven Transfer Learning Approach with Large Language Models
AXOLOTL: Fairness through Assisted Self-Debiasing of Large Language Model Outputs
MS-Net: A Multi-Path Sparse Model for Motion Prediction in Multi-Scenes
AKEW: Assessing Knowledge Editing in the Wild
Unveiling Typographic Deceptions: Insights of the Typographic Vulnerability in Large Vision-Language Model
"Flex Tape Can't Fix That": Bias and Misinformation in Edited Language Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.