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.
EgoPCA: A New Framework for Egocentric Hand-Object Interaction Understanding
AGIBench: A Multi-granularity, Multimodal, Human-referenced, Auto-scoring Benchmark for Large Language Models
Bridging the Projection Gap: Overcoming Projection Bias Through Parameterized Distance Learning
EdaDet: Open-Vocabulary Object Detection Using Early Dense Alignment
Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learning
GBE-MLZSL: A Group Bi-Enhancement Framework for Multi-Label Zero-Shot Learning
Neural Gradient Regularizer
Using Large Language Models to Automate Category and Trend Analysis of Scientific Articles: An Application in Ophthalmology
Multiscale Residual Learning of Graph Convolutional Sequence Chunks for Human Motion Prediction
Self-pruning Graph Neural Network for Predicting Inflammatory Disease Activity in Multiple Sclerosis from Brain MR Images
SiT-MLP: A Simple MLP with Point-wise Topology Feature Learning for Skeleton-based Action Recognition
MMVP: Motion-Matrix-based Video Prediction
B2C-AFM: Bi-Directional Co-Temporal and Cross-Spatial Attention Fusion Model for Human Action Recognition
Cross-Modal Retrieval Meets Inference:Improving Zero-Shot Classification with Cross-Modal Retrieval
IndGIC: Supervised Action Recognition under Low Illumination
Balanced Representation Learning for Long-tailed Skeleton-based Action Recognition
Improving Video Violence Recognition with Human Interaction Learning on 3D Skeleton Point Clouds
Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Neurons
Privacy-Enhanced Zero-Shot Learning via Data-Free Knowledge Transfer
DD-GCN: Directed Diffusion Graph Convolutional Network for Skeleton-based Human Action Recognition
Hyperbolic Audio-visual Zero-shot Learning
HR-Pro: Point-supervised Temporal Action Localization via Hierarchical Reliability Propagation
Cross-Video Contextual Knowledge Exploration and Exploitation for Ambiguity Reduction in Weakly Supervised Temporal Action Localization
Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment
POCO: 3D Pose and Shape Estimation with Confidence
ZeroLeak: Using LLMs for Scalable and Cost Effective Side-Channel Patching
Benchmarking Data Efficiency and Computational Efficiency of Temporal Action Localization Models
${\rm E}(3)$-Equivariant Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning
Continual Zero-Shot Learning through Semantically Guided Generative Random Walks
Video BagNet: short temporal receptive fields increase robustness in long-term action recognition
Adversarial Illusions in Multi-Modal Embeddings
Local Spherical Harmonics Improve Skeleton-Based Hand Action Recognition
Image-free Classifier Injection for Zero-Shot Classification
UnLoc: A Unified Framework for Video Localization Tasks
Temporal-Distributed Backdoor Attack Against Video Based Action Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.