No article text was recorded for this version.
hard negative mining overhead
Version 1 of 136 papers37 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Triplet probabilistic embedding for face verification and clustering
- Blog: Simultaneous feature learning and hash coding with deep neural networks
- Blog: Global Selection of Contrastive Batches via Optimization on Sample Permutations
- Blog: Minimizing Sequential Confusion Error in Speech Command Recognition
- Blog: Learning Deep Embeddings with Histogram Loss
- Blog: Hard Negative Examples are Hard, but Useful
- Blog: Mean Field Theory in Deep Metric Learning
- Blog: SphereFace: Deep Hypersphere Embedding for Face Recognition
- Blog: Simple Triplet Loss Based on Intra/Inter-Class Metric Learning for Face Verification
- Blog: No Pairs Left Behind: Improving Metric Learning with Regularized Triplet Objective
- Blog: A Tale of Two Efficient and Informative Negative Sampling Distributions
- Blog: In Defense of the Triplet Loss Again: Learning Robust Person Re-Identification with Fast Approximated Triplet Loss and Label Distillation
- Blog: Learning a Metric Embedding for Face Recognition using the Multibatch Method
- Blog: Metric Learning with Adaptive Density Discrimination Oren Rippel
- Blog: Heterogeneity Aware Deep Embedding for Mobile Periocular Recognition
- Blog: VSE++: Improving Visual-Semantic Embeddings with Hard Negatives
- Blog: Negative-Supervised Cascaded Deep Learning for Traffic Sign Classification
- Blog: Proxy Anchor Loss for Deep Metric Learning
- Blog: Discriminative Learning of Deep Convolutional Feature Point Descriptors
- Blog: 以三元組損失微調時延神經網路語者嵌入函數之語者辨識系統(Time Delay Neural Network-based Speaker Embedding Function Fine-tuned with Triplet Loss for Distance-based Speaker Recognition)
- Blog: Deep Metric Learning via Facility Location
- Blog: Distilling Cross-Task Knowledge via Relationship Matching
- Blog: Smart Mining for Deep Metric Learning
- Blog: Speech Emotion Recognition from Variable-Length Inputs with Triplet Loss Function
- Blog: Proxy-Based Embedding Alignment for RGB-Infrared Person Re-Identification
- Blog: ViLTA: Enhancing Vision-Language Pre-training through Textual Augmentation
- Blog: Working hard to know your neighbor's margins: Local descriptor learning loss
- Blog: Mining Polysemous Triplets with Recurrent Neural Networks for Spoken Language Understanding
- Blog: Deep Metric Learning With Tuplet Margin Loss
- Blog: Learning Intra-Batch Connections for Deep Metric Learning
- Blog: Representation Learning for Treatment Effect Estimation from Observational Data.
- Blog: On Learning Density Aware Embeddings
- Blog: Improved Deep Metric Learning with Multi-class N-pair Loss Objective
- Blog: Scalable Deep Metric Learning on Attributed Graphs
- Blog: Learning to Rank Music Tracks Using Triplet Loss
- Blog: Deep Image Retrieval: Learning Global Representations for Image Search
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_hard_negative_mining_overhead_7905f459,
title = {hard negative mining overhead},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/hard-negative-mining-overhead/rdr_7905f45922aa45359029ec00d21ff0be},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_hard_negative_mining_overhead_7905f459_v1,
title = {hard negative mining overhead},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/hard-negative-mining-overhead/rdr_7905f45922aa45359029ec00d21ff0be/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}