Improving Face Recognition by Clustering Unlabeled Faces in the Wild
- URL: http://arxiv.org/abs/2007.06995v2
- Date: Wed, 15 Jul 2020 17:30:17 GMT
- Title: Improving Face Recognition by Clustering Unlabeled Faces in the Wild
- Authors: Aruni RoyChowdhury, Xiang Yu, Kihyuk Sohn, Erik Learned-Miller,
Manmohan Chandraker
- Abstract summary: We propose a novel identity separation method based on extreme value theory.
It greatly reduces the problems caused by overlapping-identity label noise.
Experiments on both controlled and real settings demonstrate our method's consistent improvements.
- Score: 77.48677160252198
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: While deep face recognition has benefited significantly from large-scale
labeled data, current research is focused on leveraging unlabeled data to
further boost performance, reducing the cost of human annotation. Prior work
has mostly been in controlled settings, where the labeled and unlabeled data
sets have no overlapping identities by construction. This is not realistic in
large-scale face recognition, where one must contend with such overlaps, the
frequency of which increases with the volume of data. Ignoring identity overlap
leads to significant labeling noise, as data from the same identity is split
into multiple clusters. To address this, we propose a novel identity separation
method based on extreme value theory. It is formulated as an
out-of-distribution detection algorithm, and greatly reduces the problems
caused by overlapping-identity label noise. Considering cluster assignments as
pseudo-labels, we must also overcome the labeling noise from clustering errors.
We propose a modulation of the cosine loss, where the modulation weights
correspond to an estimate of clustering uncertainty. Extensive experiments on
both controlled and real settings demonstrate our method's consistent
improvements over supervised baselines, e.g., 11.6% improvement on IJB-A
verification.
Related papers
- Label Noise: Correcting the Forward-Correction [0.0]
Training neural network classifiers on datasets with label noise poses a risk of overfitting them to the noisy labels.
We propose an approach to tackling overfitting caused by label noise.
Motivated by this observation, we propose imposing a lower bound on the training loss to mitigate overfitting.
arXiv Detail & Related papers (2023-07-24T19:41:19Z) - Learning with Noisy labels via Self-supervised Adversarial Noisy Masking [33.87292143223425]
We propose a novel training approach termed adversarial noisy masking.
It adaptively modulates the input data and label simultaneously, preventing the model to overfit noisy samples.
It is tested on both synthetic and real-world noisy datasets.
arXiv Detail & Related papers (2023-02-14T03:13:26Z) - Neighbour Consistency Guided Pseudo-Label Refinement for Unsupervised
Person Re-Identification [80.98291772215154]
Unsupervised person re-identification (ReID) aims at learning discriminative identity features for person retrieval without any annotations.
Recent advances accomplish this task by leveraging clustering-based pseudo labels.
We propose a Neighbour Consistency guided Pseudo Label Refinement framework.
arXiv Detail & Related papers (2022-11-30T09:39:57Z) - Plug-and-Play Pseudo Label Correction Network for Unsupervised Person
Re-identification [36.3733132520186]
We propose a graph-based pseudo label correction network (GLC) to refine the pseudo labels in the manner of supervised clustering.
GLC learns to rectify the initial noisy labels by means of the relationship constraints between samples on the k Nearest Neighbor graph.
Our method is widely compatible with various clustering-based methods and promotes the state-of-the-art performance consistently.
arXiv Detail & Related papers (2022-06-14T05:59:37Z) - S3: Supervised Self-supervised Learning under Label Noise [53.02249460567745]
In this paper we address the problem of classification in the presence of label noise.
In the heart of our method is a sample selection mechanism that relies on the consistency between the annotated label of a sample and the distribution of the labels in its neighborhood in the feature space.
Our method significantly surpasses previous methods on both CIFARCIFAR100 with artificial noise and real-world noisy datasets such as WebVision and ANIMAL-10N.
arXiv Detail & Related papers (2021-11-22T15:49:20Z) - Refining Pseudo Labels with Clustering Consensus over Generations for
Unsupervised Object Re-identification [84.72303377833732]
Unsupervised object re-identification targets at learning discriminative representations for object retrieval without any annotations.
We propose to estimate pseudo label similarities between consecutive training generations with clustering consensus and refine pseudo labels with temporally propagated and ensembled pseudo labels.
The proposed pseudo label refinery strategy is simple yet effective and can be seamlessly integrated into existing clustering-based unsupervised re-identification methods.
arXiv Detail & Related papers (2021-06-11T02:42:42Z) - Exploiting Sample Uncertainty for Domain Adaptive Person
Re-Identification [137.9939571408506]
We estimate and exploit the credibility of the assigned pseudo-label of each sample to alleviate the influence of noisy labels.
Our uncertainty-guided optimization brings significant improvement and achieves the state-of-the-art performance on benchmark datasets.
arXiv Detail & Related papers (2020-12-16T04:09:04Z) - Unsupervised Person Re-identification via Softened Similarity Learning [122.70472387837542]
Person re-identification (re-ID) is an important topic in computer vision.
This paper studies the unsupervised setting of re-ID, which does not require any labeled information.
Experiments on two image-based and video-based datasets demonstrate state-of-the-art performance.
arXiv Detail & Related papers (2020-04-07T17:16:41Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.