Papers with Code 아카이브
Novel Concepts
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Measures the ability of models to uncover an underlying concept that unites several ostensibly disparate entities, which hopefully would not co-occur frequently. This provides a limited test of a model's ability to creatively construct the necessary abstraction to make sense of a situation that it cannot have memorized in training.
Source: BIG-bench
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Dialog Policy Learning for Joint Clarification and Active Learning Queries
Characterizing an Analogical Concept Memory for Architectures Implementing the Common Model of Cognition
XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning
Revisit Systematic Generalization via Meaningful Learning
Contextual Blocking Bandits
Exploring Partial Intrinsic and Extrinsic Symmetry in 3D Medical Imaging
FLAT: Few-Shot Learning via Autoencoding Transformation Regularizers
Simple and Lightweight Human Pose Estimation
Direct and indirect transactions and requirements
Knowledge Graph Transfer Network for Few-Shot Recognition
Structure Matters: Towards Generating Transferable Adversarial Images
Learning 3D-aware Egocentric Spatial-Temporal Interaction via Graph Convolutional Networks
Resonant Machine Learning Based on Complex Growth Transform Dynamical Systems
Task-Aware Feature Generation for Zero-Shot Compositional Learning
Variational Prototype Replays for Continual Learning
Task-Driven Modular Networks for Zero-Shot Compositional Learning
A Provable Defense for Deep Residual Networks
25 years of criticality in neuroscience -- established results, open controversies, novel concepts
Situational Grounding within Multimodal Simulations
Understanding MCMC Dynamics as Flows on the Wasserstein Space
Beyond imitation: Zero-shot task transfer on robots by learning concepts as cognitive programs
From Known to the Unknown: Transferring Knowledge to Answer Questions about Novel Visual and Semantic Concepts
Characterizing the Influence of Features on Reading Difficulty Estimation for Non-native Readers
Can Machines Design? An Artificial General Intelligence Approach
Dynamic Few-Shot Visual Learning without Forgetting
Multi-level Semantic Feature Augmentation for One-shot Learning
Decoupled Novel Object Captioner
Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts
Privacy-Enabled Biometric Search
Zero-Shot Learning by Generating Pseudo Feature Representations
Sequential Local Learning for Latent Graphical Models
Tinkering Under the Hood: Interactive Zero-Shot Learning with Net Surgery
A Robust Framework for Classifying Evolving Document Streams in an Expert-Machine-Crowd Setting
Deep Compositional Captioning: Describing Novel Object Categories without Paired Training Data
Schema Independent Relational Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.