Papers with Code 아카이브

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 )

논문

이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.

Zero-Shot Learning

논문

ProTAL: A Drag-and-Link Video Programming Framework for Temporal Action Localization

Model Editing with Graph-Based External Memory

Monocular Marker-free Patient-to-Image Intraoperative Registration for Cochlear Implant Surgery

CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Driving

Zero-Shot Anomaly Detection in Battery Thermal Images Using Visual Question Answering with Prior Knowledge

NovelSeek: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification

UniErase: Unlearning Token as a Universal Erasure Primitive for Language Models

LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing

APEX: Empowering LLMs with Physics-Based Task Planning for Real-time Insight

Beginning with You: Perceptual-Initialization Improves Vision-Language Representation and Alignment

Editing Across Languages: A Survey of Multilingual Knowledge Editing

UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Large Language Models

UPTor: Unified 3D Human Pose Dynamics and Trajectory Prediction for Human-Robot Interaction

Multi-Resolution Haar Network: Enhancing human motion prediction via Haar transform

Revealing the Deceptiveness of Knowledge Editing: A Mechanistic Analysis of Superficial Editing

AGI-Elo: How Far Are We From Mastering A Task?

Uniformity First: Uniformity-aware Test-time Adaptation of Vision-language Models against Image Corruption

CacheFlow: Fast Human Motion Prediction by Cached Normalizing Flow

StarFT: Robust Fine-tuning of Zero-shot Models via Spuriosity Alignment

From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection

Robust Planning for Autonomous Driving via Mixed Adversarial Diffusion Predictions

UniEdit: A Unified Knowledge Editing Benchmark for Large Language Models

Patient-Specific Autoregressive Models for Organ Motion Prediction in Radiotherapy

NAMET: Robust Massive Model Editing via Noise-Aware Memory Optimization

GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder

Cross-Model Transfer of Task Vectors via Few-Shot Orthogonal Alignment

ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization

Feasibility with Language Models for Open-World Compositional Zero-Shot Learning

Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert Reasoner

SurgPose: Generalisable Surgical Instrument Pose Estimation using Zero-Shot Learning and Stereo Vision

CrypticBio: A Large Multimodal Dataset for Visually Confusing Biodiversity

Advanced Crash Causation Analysis for Freeway Safety: A Large Language Model Approach to Identifying Key Contributing Factors

MSCI: Addressing CLIP's Inherent Limitations for Compositional Zero-Shot Learning

Enhancing IoT Cyber Attack Detection in the Presence of Highly Imbalanced Data

Are Spatial-Temporal Graph Convolution Networks for Human Action Recognition Over-Parameterized?

ZEUS: Zero-shot Embeddings for Unsupervised Separation of Tabular Data