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.
Mass-Editing Memory with Attention in Transformers: A cross-lingual exploration of knowledge
IMDPrompter: Adapting SAM to Image Manipulation Detection by Cross-View Automated Prompt Learning
VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models
Lifelong Knowledge Editing requires Better Regularization
Leveraging Large Language Models to Predict Antibody Biological Activity Against Influenza A Hemagglutinin
FlexCloud: Direct, Modular Georeferencing and Drift-Correction of Point Cloud Maps
Minimalistic Video Saliency Prediction via Efficient Decoder & Spatio Temporal Action Cues
Building Bridges, Not Walls -- Advancing Interpretability by Unifying Feature, Data, and Model Component Attribution
XRF V2: A Dataset for Action Summarization with Wi-Fi Signals, and IMUs in Phones, Watches, Earbuds, and Glasses
Unraveling the Capabilities of Language Models in News Summarization
Overcoming Semantic Dilution in Transformer-Based Next Frame Prediction
Irony Detection, Reasoning and Understanding in Zero-shot Learning
The Components of Collaborative Joint Perception and Prediction -- A Conceptual Framework
PackDiT: Joint Human Motion and Text Generation via Mutual Prompting
Learning Primitive Relations for Compositional Zero-Shot Learning
GraphSOS: Graph Sampling and Order Selection to Help LLMs Understand Graphs Better
Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image Understanding
Towards Real-World Validation of a Physics-Based Ship Motion Prediction Model
Dual-Modal Prototype Joint Learning for Compositional Zero-Shot Learning
Comprehensive Modeling and Question Answering of Cancer Clinical Practice Guidelines using LLMs
Revisiting CLIP: Efficient Alignment of 3D MRI and Tabular Data using Domain-Specific Foundation Models
SMART-Vision: Survey of Modern Action Recognition Techniques in Vision
Separated Inter/Intra-Modal Fusion Prompts for Compositional Zero-Shot Learning
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling
BlanketGen2-Fit3D: Synthetic Blanket Augmentation Towards Improving Real-World In-Bed Blanket Occluded Human Pose Estimation
Adaptive Cyber-Attack Detection in IIoT Using Attention-Based LSTM-CNN Models
KPL: Training-Free Medical Knowledge Mining of Vision-Language Models
A Survey of World Models for Autonomous Driving
HFGCN:Hypergraph Fusion Graph Convolutional Networks for Skeleton-Based Action Recognition
Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach
Rethinking Pseudo-Label Guided Learning for Weakly Supervised Temporal Action Localization from the Perspective of Noise Correction
Exploring Transferable Homogeneous Groups for Compositional Zero-Shot Learning
Text-guided Synthetic Geometric Augmentation for Zero-shot 3D Understanding
Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness
Computerized Assessment of Motor Imitation for Distinguishing Autism in Video (CAMI-2DNet)
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.