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.
Quantum Polar Metric Learning: Efficient Classically Learned Quantum Embeddings
DUCK: Distance-based Unlearning via Centroid Kinematics
Beyond Accuracy: Statistical Measures and Benchmark for Evaluation of Representation from Self-Supervised Learning
Deep Metric Learning for Computer Vision: A Brief Overview
Robust Concept Erasure via Kernelized Rate-Distortion Maximization
SEINE: SEgment-based Indexing for NEural information retrieval
VehicleGAN: Pair-flexible Pose Guided Image Synthesis for Vehicle Re-identification
Shadow: A Novel Loss Function for Efficient Training in Siamese Networks
Enhancing mTBI Diagnosis with Residual Triplet Convolutional Neural Network Using 3D CT
Exploring Graph Classification Techniques Under Low Data Constraints: A Comprehensive Study
Image Patch-Matching with Graph-Based Learning in Street Scenes
Deep Hashing via Householder Quantization
ProcSim: Proxy-based Confidence for Robust Similarity Learning
Causal Fair Metric: Bridging Causality, Individual Fairness, and Adversarial Robustness
Neural Snowflakes: Universal Latent Graph Inference via Trainable Latent Geometries
Adaptive End-to-End Metric Learning for Zero-Shot Cross-Domain Slot Filling
Object Detection in Aerial Images in Scarce Data Regimes
Long-Tailed Classification Based on Coarse-Grained Leading Forest and Multi-Center Loss
Hyp-UML: Hyperbolic Image Retrieval with Uncertainty-aware Metric Learning
FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators
SCoRe: Submodular Combinatorial Representation Learning
Dark Side Augmentation: Generating Diverse Night Examples for Metric Learning
Ugly Ducklings or Swans: A Tiered Quadruplet Network with Patient-Specific Mining for Improved Skin Lesion Classification
RaLF: Flow-based Global and Metric Radar Localization in LiDAR Maps
Image-Text Pre-Training for Logo Recognition
Learning Unified Distance Metric Across Diverse Data Distributions with Parameter-Efficient Transfer Learning
Deep Attentive Time Warping
Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?
Getting More for Less: Using Weak Labels and AV-Mixup for Robust Audio-Visual Speaker Verification
Compressive Mahalanobis Metric Learning Adapts to Intrinsic Dimension
Introspective Deep Metric Learning
A Long-Tail Friendly Representation Framework for Artist and Music Similarity
SSIG: A Visually-Guided Graph Edit Distance for Floor Plan Similarity
BWSNet: Automatic Perceptual Assessment of Audio Signals
Bridging the Projection Gap: Overcoming Projection Bias Through Parameterized Distance Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.