A metric learning reality check
Deep metric learning papers from the past four years have consistently claimed great
advances in accuracy, often more than doubling the performance of decade-old methods. In …
advances in accuracy, often more than doubling the performance of decade-old methods. In …
Crossclr: Cross-modal contrastive learning for multi-modal video representations
Contrastive learning allows us to flexibly define powerful losses by contrasting positive pairs
from sets of negative samples. Recently, the principle has also been used to learn cross …
from sets of negative samples. Recently, the principle has also been used to learn cross …
Hyperbolic vision transformers: Combining improvements in metric learning
A Ermolov, L Mirvakhabova… - Proceedings of the …, 2022 - openaccess.thecvf.com
Metric learning aims to learn a highly discriminative model encouraging the embeddings of
similar classes to be close in the chosen metrics and pushed apart for dissimilar ones. The …
similar classes to be close in the chosen metrics and pushed apart for dissimilar ones. The …
Training vision transformers for image retrieval
Transformers have shown outstanding results for natural language understanding and, more
recently, for image classification. We here extend this work and propose a transformer …
recently, for image classification. We here extend this work and propose a transformer …
[HTML][HTML] Facial kinship verification: A comprehensive review and outlook
Abstract The goal of Facial Kinship Verification (FKV) is to automatically determine whether
two individuals have a kin relationship or not from their given facial images or videos. It is an …
two individuals have a kin relationship or not from their given facial images or videos. It is an …
Cross-batch memory for embedding learning
Mining informative negative instances are of central importance to deep metric learning
(DML). However, the hard-mining ability of existing DML methods is intrinsically limited by …
(DML). However, the hard-mining ability of existing DML methods is intrinsically limited by …
Smooth-ap: Smoothing the path towards large-scale image retrieval
Optimising a ranking-based metric, such as Average Precision (AP), is notoriously
challenging due to the fact that it is non-differentiable, and hence cannot be optimised …
challenging due to the fact that it is non-differentiable, and hence cannot be optimised …
Multiple instance learning framework with masked hard instance mining for whole slide image classification
The whole slide image (WSI) classification is often formulated as a multiple instance
learning (MIL) problem. Since the positive tissue is only a small fraction of the gigapixel WSI …
learning (MIL) problem. Since the positive tissue is only a small fraction of the gigapixel WSI …
Ranked list loss for deep metric learning
The objective of deep metric learning (DML) is to learn embeddings that can capture
semantic similarity information among data points. Existing pairwise or tripletwise loss …
semantic similarity information among data points. Existing pairwise or tripletwise loss …
Contrastive learning with adversarial examples
CH Ho, N Nvasconcelos - Advances in Neural Information …, 2020 - proceedings.neurips.cc
Contrastive learning (CL) is a popular technique for self-supervised learning (SSL) of visual
representations. It uses pairs of augmentations of unlabeled training examples to define a …
representations. It uses pairs of augmentations of unlabeled training examples to define a …