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.
Part Aware Contrastive Learning for Self-Supervised Action Recognition
ZeroSearch: Local Image Search from Text with Zero Shot Learning
GeneFace++: Generalized and Stable Real-Time Audio-Driven 3D Talking Face Generation
Company classification using zero-shot learning
Improving Rating Prediction in Multi-Criteria Recommender Systems via a Collective Factor Model
ALMERIA: Boosting pairwise molecular contrasts with scalable methods
The Parrot Dilemma: Human-Labeled vs. LLM-augmented Data in Classification Tasks
ContrastMotion: Self-supervised Scene Motion Learning for Large-Scale LiDAR Point Clouds
Weakly-Supervised Temporal Action Localization with Bidirectional Semantic Consistency Constraint
Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential
A Neuro-Symbolic Approach for Enhanced Human Motion Prediction
RPLKG: Robust Prompt Learning with Knowledge Graph
Information Extraction from Documents: Question Answering vs Token Classification in real-world setups
CLaMP: Contrastive Language-Music Pre-training for Cross-Modal Symbolic Music Information Retrieval
A baseline on continual learning methods for video action recognition
Segment Anything Model for Medical Image Analysis: an Experimental Study
Text2Seg: Remote Sensing Image Semantic Segmentation via Text-Guided Visual Foundation Models
LLM as A Robotic Brain: Unifying Egocentric Memory and Control
On the Effectiveness of Image Manipulation Detection in the Age of Social Media
Self-Supervised 3D Action Representation Learning with Skeleton Cloud Colorization
Tailoring Domain Adaptation for Machine Translation Quality Estimation
Pose Constraints for Consistent Self-supervised Monocular Depth and Ego-motion
Improving Weakly Supervised Temporal Action Localization by Bridging Train-Test Gap in Pseudo Labels
TagCLIP: Improving Discrimination Ability of Open-Vocabulary Semantic Segmentation
PMI Sampler: Patch Similarity Guided Frame Selection for Aerial Action Recognition
WYTIWYR: A User Intent-Aware Framework with Multi-modal Inputs for Visualization Retrieval
NEV-NCD: Negative Learning, Entropy, and Variance regularization based novel action categories discovery
Skeleton-based action analysis for ADHD diagnosis
Enhancing Model Learning and Interpretation Using Multiple Molecular Graph Representations for Compound Property and Activity Prediction
ChatGPT-4 Outperforms Experts and Crowd Workers in Annotating Political Twitter Messages with Zero-Shot Learning
What does CLIP know about a red circle? Visual prompt engineering for VLMs
On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligence
SemEval-2023 Task 12: Sentiment Analysis for African Languages (AfriSenti-SemEval)
DeepSegmenter: Temporal Action Localization for Detecting Anomalies in Untrimmed Naturalistic Driving Videos
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.