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.
Skeleton-in-Context: Unified Skeleton Sequence Modeling with In-Context Learning
Lite-Mind: Towards Efficient and Robust Brain Representation Network
The Potential of Vision-Language Models for Content Moderation of Children's Videos
MGTR: Multi-Granular Transformer for Motion Prediction with LiDAR
Large Knowledge Model: Perspectives and Challenges
Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training
SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference
Hulk: A Universal Knowledge Translator for Human-Centric Tasks
CILF-CIAE: CLIP-driven Image-Language Fusion for Correcting Inverse Age Estimation
MMFusion: Combining Image Forensic Filters for Visual Manipulation Detection and Localization
Evaluating Dependencies in Fact Editing for Language Models: Specificity and Implication Awareness
Semantics-aware Motion Retargeting with Vision-Language Models
Generating Action-conditioned Prompts for Open-vocabulary Video Action Recognition
Deeper into Self-Supervised Monocular Indoor Depth Estimation
ArabIcros: AI-Powered Arabic Crossword Puzzle Generation for Educational Applications
Large Language Models Are Zero-Shot Text Classifiers
Meta-Learned Attribute Self-Interaction Network for Continual and Generalized Zero-Shot Learning
Prompt Tuning for Zero-shot Compositional Learning
FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation models
A-Scan2BIM: Assistive Scan to Building Information Modeling
Class Distribution Shifts in Zero-Shot Learning: Learning Robust Representations
Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understanding
DEVIAS: Learning Disentangled Video Representations of Action and Scene
Applying Large Language Models and Chain-of-Thought for Automatic Scoring
Explaining CLIP's performance disparities on data from blind/low vision users
Generative Hierarchical Temporal Transformer for Hand Pose and Action Modeling
Dynamic Dense Graph Convolutional Network for Skeleton-based Human Motion Prediction
Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection
MVBench: A Comprehensive Multi-modal Video Understanding Benchmark
MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training
Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition
End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames
F4D: Factorized 4D Convolutional Neural Network for Efficient Video-level Representation Learning
Align before Adapt: Leveraging Entity-to-Region Alignments for Generalizable Video Action Recognition
Italian Crossword Generator: Enhancing Education through Interactive Word Puzzles
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.