FaceFusion: Exploiting Full Spectrum of Multiple Datasets
- URL: http://arxiv.org/abs/2305.14601v1
- Date: Wed, 24 May 2023 00:51:04 GMT
- Title: FaceFusion: Exploiting Full Spectrum of Multiple Datasets
- Authors: Chiyoung Song, Dongjae Lee
- Abstract summary: We present a novel training method, named FaceFusion.
It creates a fused view of different datasets that is untainted by identity conflicts, while concurrently training an embedding network using the view.
Using the unified view of combined datasets enables the embedding network to be trained against the entire spectrum of the datasets, leading to a noticeable performance boost.
- Score: 4.438240667468304
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The size of training dataset is known to be among the most dominating aspects
of training high-performance face recognition embedding model. Building a large
dataset from scratch could be cumbersome and time-intensive, while combining
multiple already-built datasets poses the risk of introducing large amount of
label noise. We present a novel training method, named FaceFusion. It creates a
fused view of different datasets that is untainted by identity conflicts, while
concurrently training an embedding network using the view in an end-to-end
fashion. Using the unified view of combined datasets enables the embedding
network to be trained against the entire spectrum of the datasets, leading to a
noticeable performance boost. Extensive experiments confirm superiority of our
method, whose performance in public evaluation datasets surpasses not only that
of using a single training dataset, but also that of previously known methods
under various training circumstances.
Related papers
- Multi-Site Class-Incremental Learning with Weighted Experts in Echocardiography [1.305420351791698]
Building an echocardiography view that maintains performance in real-life cases requires diverse multi-site data.
We propose a class-incremental learning method which learns an expert network for each dataset.
We validate our work on six datasets from multiple sites, demonstrating significant reductions in training time while improving view classification performance.
arXiv Detail & Related papers (2024-07-31T13:05:32Z) - Automated Label Unification for Multi-Dataset Semantic Segmentation with GNNs [48.406728896785296]
We propose a novel approach to automatically construct a unified label space across multiple datasets using graph neural networks.
Unlike existing methods, our approach facilitates seamless training without the need for additional manual reannotation or taxonomy reconciliation.
arXiv Detail & Related papers (2024-07-15T08:42:10Z) - Imitation Learning Datasets: A Toolkit For Creating Datasets, Training
Agents and Benchmarking [0.9944647907864256]
Imitation learning field requires expert data to train agents in a task.
Most often, this learning approach suffers from the absence of available data.
This work aims to address these issues by creating Imitation Learning datasets.
arXiv Detail & Related papers (2024-03-01T14:18:46Z) - Multi-dataset Training of Transformers for Robust Action Recognition [75.5695991766902]
We study the task of robust feature representations, aiming to generalize well on multiple datasets for action recognition.
Here, we propose a novel multi-dataset training paradigm, MultiTrain, with the design of two new loss terms, namely informative loss and projection loss.
We verify the effectiveness of our method on five challenging datasets, Kinetics-400, Kinetics-700, Moments-in-Time, Activitynet and Something-something-v2.
arXiv Detail & Related papers (2022-09-26T01:30:43Z) - Detection Hub: Unifying Object Detection Datasets via Query Adaptation
on Language Embedding [137.3719377780593]
A new design (named Detection Hub) is dataset-aware and category-aligned.
It mitigates the dataset inconsistency and provides coherent guidance for the detector to learn across multiple datasets.
The categories across datasets are semantically aligned into a unified space by replacing one-hot category representations with word embedding.
arXiv Detail & Related papers (2022-06-07T17:59:44Z) - Multi-dataset Pretraining: A Unified Model for Semantic Segmentation [97.61605021985062]
We propose a unified framework, termed as Multi-Dataset Pretraining, to take full advantage of the fragmented annotations of different datasets.
This is achieved by first pretraining the network via the proposed pixel-to-prototype contrastive loss over multiple datasets.
In order to better model the relationship among images and classes from different datasets, we extend the pixel level embeddings via cross dataset mixing.
arXiv Detail & Related papers (2021-06-08T06:13:11Z) - DAIL: Dataset-Aware and Invariant Learning for Face Recognition [67.4903809903022]
To achieve good performance in face recognition, a large scale training dataset is usually required.
It is problematic and troublesome to naively combine different datasets due to two major issues.
Naively treating the same person as different classes in different datasets during training will affect back-propagation.
manually cleaning labels may take formidable human efforts, especially when there are millions of images and thousands of identities.
arXiv Detail & Related papers (2021-01-14T01:59:52Z) - Omni-supervised Facial Expression Recognition via Distilled Data [120.11782405714234]
We propose omni-supervised learning to exploit reliable samples in a large amount of unlabeled data for network training.
We experimentally verify that the new dataset can significantly improve the ability of the learned FER model.
To tackle this, we propose to apply a dataset distillation strategy to compress the created dataset into several informative class-wise images.
arXiv Detail & Related papers (2020-05-18T09:36:51Z)
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.