Metric Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 7
- 보존된 평가 기록
- 122
The goal of Metric Learning is to learn a representation function that maps objects into an embedded space. The distance in the embedded space should preserve the objects’ similarity — similar objects get close and dissimilar objects get far away. Various loss functions have been developed for Metric Learning. For example, the contrastive loss guides the objects from the same class to be mapped to the same point and those from different classes to be mapped to different points whose distances are larger than a margin. Triplet loss is also popular, which requires the distance between the anchor sample and the positive sample to be smaller than the distance between the anchor sample and the negative sample.
Source: Road Network Metric Learning for Estimated Time of Arrival
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
State Chrono Representation for Enhancing Generalization in Reinforcement Learning
Few-shot Open Relation Extraction with Gaussian Prototype and Adaptive Margin
Learning to Generate and Evaluate Fact-checking Explanations with Transformers
GSSF: Generalized Structural Sparse Function for Deep Cross-modal Metric Learning
PReP: Efficient context-based shape retrieval for missing parts
Geometry-Aware Generative Autoencoders for Warped Riemannian Metric Learning and Generative Modeling on Data Manifolds
Audio-based Kinship Verification Using Age Domain Conversion
GLRT-Based Metric Learning for Remote Sensing Object Retrieval
MARs: Multi-view Attention Regularizations for Patch-based Feature Recognition of Space Terrain
DAAL: Density-Aware Adaptive Line Margin Loss for Multi-Modal Deep Metric Learning
FlashMix: Fast Map-Free LiDAR Localization via Feature Mixing and Contrastive-Constrained Accelerated Training
SeqNet: Sequential Networks for One-Shot Traffic Sign Recognition With Transfer Learning
Zero-Shot Skeleton-based Action Recognition with Dual Visual-Text Alignment
Efficient and Discriminative Image Feature Extraction for Universal Image Retrieval
MeLIAD: Interpretable Few-Shot Anomaly Detection with Metric Learning and Entropy-based Scoring
A Bottom-Up Approach to Class-Agnostic Image Segmentation
A Riemannian Approach to Ground Metric Learning for Optimal Transport
LabellessFace: Fair Metric Learning for Face Recognition without Attribute Labels
Look One and More: Distilling Hybrid Order Relational Knowledge for Cross-Resolution Image Recognition
Transferable Selective Virtual Sensing Active Noise Control Technique Based on Metric Learning
DiffusionPen: Towards Controlling the Style of Handwritten Text Generation
Large Margin Prototypical Network for Few-shot Relation Classification with Fine-grained Features
Towards Fine-Grained Webpage Fingerprinting at Scale
Improved Diversity-Promoting Collaborative Metric Learning for Recommendation
Evidential Transformers for Improved Image Retrieval
FinePseudo: Improving Pseudo-Labelling through Temporal-Alignablity for Semi-Supervised Fine-Grained Action Recognition
Realigned Softmax Warping for Deep Metric Learning
Distance-Forward Learning: Enhancing the Forward-Forward Algorithm Towards High-Performance On-Chip Learning
CLLMFS: A Contrastive Learning enhanced Large Language Model Framework for Few-Shot Named Entity Recognition
Can an unsupervised clustering algorithm reproduce a categorization system?
Visual Neural Decoding via Improved Visual-EEG Semantic Consistency
Open Set Recognition for Random Forest
Categorical Knowledge Fused Recognition: Fusing Hierarchical Knowledge with Image Classification through Aligning and Deep Metric Learning
Keypoint Promptable Re-Identification
Estimating Earthquake Magnitude in Sentinel-1 Imagery via Ranking
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.