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.
Towards a text-based quantitative and explainable histopathology image analysis
DuInNet: Dual-Modality Feature Interaction for Point Cloud Completion
Malicious Path Manipulations via Exploitation of Representation Vulnerabilities of Vision-Language Navigation Systems
EA-VTR: Event-Aware Video-Text Retrieval
Mitigating Backdoor Attacks using Activation-Guided Model Editing
Towards Adaptive Pseudo-label Learning for Semi-Supervised Temporal Action Localization
Deep Learning-Based Robust Multi-Object Tracking via Fusion of mmWave Radar and Camera Sensors
Composable Interventions for Language Models
Exploring Scalability of Self-Training for Open-Vocabulary Temporal Action Localization
Spatio-Temporal Encoding and Decoding-Based Method for Future Human Activity Skeleton Synthesis
BEVWorld: A Multimodal World Model for Autonomous Driving via Unified BEV Latent Space
Pseudo-triplet Guided Few-shot Composed Image Retrieval
CodeUpdateArena: Benchmarking Knowledge Editing on API Updates
AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation
DyFADet: Dynamic Feature Aggregation for Temporal Action Detection
Referring Atomic Video Action Recognition
Evaluating the Ability of LLMs to Solve Semantics-Aware Process Mining Tasks
Advancing Compressed Video Action Recognition through Progressive Knowledge Distillation
Why Does New Knowledge Create Messy Ripple Effects in LLMs?
FairMedFM: Fairness Benchmarking for Medical Imaging Foundation Models
Mask and Compress: Efficient Skeleton-based Action Recognition in Continual Learning
Semantic Compositions Enhance Vision-Language Contrastive Learning
Engineering an Efficient Object Tracker for Non-Linear Motion
FootBots: A Transformer-based Architecture for Motion Prediction in Soccer
LEMoE: Advanced Mixture of Experts Adaptor for Lifelong Model Editing of Large Language Models
SSP: Self-Supervised Prompting for Cross-Lingual Transfer to Low-Resource Languages using Large Language Models
Snakes and Ladders: Two Steps Up for VideoMamba
Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs?
Expressive Keypoints for Skeleton-based Action Recognition via Skeleton Transformation
The Surprising Effectiveness of Multimodal Large Language Models for Video Moment Retrieval
Understanding Language Model Circuits through Knowledge Editing
How Well Can Knowledge Edit Methods Edit Perplexing Knowledge?
Using joint angles based on the international biomechanical standards for human action recognition and related tasks
Mitigate the Gap: Investigating Approaches for Improving Cross-Modal Alignment in CLIP
BioTrove: A Large Curated Image Dataset Enabling AI for Biodiversity
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.