Deep Compact Polyhedral Conic Classifier for Open and Closed Set
Recognition
- URL: http://arxiv.org/abs/2102.12570v1
- Date: Wed, 24 Feb 2021 21:38:31 GMT
- Title: Deep Compact Polyhedral Conic Classifier for Open and Closed Set
Recognition
- Authors: Hakan Cevikalp, Bedirhan Uzun, Okan K\"op\"ukl\"u, Gurkan Ozturk
- Abstract summary: The proposed method has a nice interpretation using polyhedral conic function geometry.
The experimental results show that the proposed method typically outperforms other state-of-the art methods.
- Score: 17.86376652494798
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In this paper, we propose a new deep neural network classifier that
simultaneously maximizes the inter-class separation and minimizes the
intra-class variation by using the polyhedral conic classification function.
The proposed method has one loss term that allows the margin maximization to
maximize the inter-class separation and another loss term that controls the
compactness of the class acceptance regions. Our proposed method has a nice
geometric interpretation using polyhedral conic function geometry. We tested
the proposed method on various visual classification problems including
closed/open set recognition and anomaly detection. The experimental results
show that the proposed method typically outperforms other state-of-the art
methods, and becomes a better choice compared to other tested methods
especially for open set recognition type problems.
Related papers
- Anti-Collapse Loss for Deep Metric Learning Based on Coding Rate Metric [99.19559537966538]
DML aims to learn a discriminative high-dimensional embedding space for downstream tasks like classification, clustering, and retrieval.
To maintain the structure of embedding space and avoid feature collapse, we propose a novel loss function called Anti-Collapse Loss.
Comprehensive experiments on benchmark datasets demonstrate that our proposed method outperforms existing state-of-the-art methods.
arXiv Detail & Related papers (2024-07-03T13:44:20Z) - Convolutional autoencoder-based multimodal one-class classification [80.52334952912808]
One-class classification refers to approaches of learning using data from a single class only.
We propose a deep learning one-class classification method suitable for multimodal data.
arXiv Detail & Related papers (2023-09-25T12:31:18Z) - COMICS: End-to-end Bi-grained Contrastive Learning for Multi-face Forgery Detection [56.7599217711363]
Face forgery recognition methods can only process one face at a time.
Most face forgery recognition methods can only process one face at a time.
We propose COMICS, an end-to-end framework for multi-face forgery detection.
arXiv Detail & Related papers (2023-08-03T03:37:13Z) - Deep Simplex Classifier for Maximizing the Margin in Both Euclidean and
Angular Spaces [18.309720578916146]
This paper introduces a novel classification loss that maximizes the margin in both the Euclidean and angular spaces at the same time.
The proposed method achieves the state-of-the-art accuracies on open set recognition despite its simplicity.
arXiv Detail & Related papers (2022-12-22T14:37:47Z) - Supervised Dimensionality Reduction and Classification with
Convolutional Autoencoders [1.1164202369517053]
A Convolutional Autoencoder is combined to simultaneously produce supervised dimensionality reduction and predictions.
The resulting Latent Space can be utilized to improve traditional, interpretable classification algorithms.
The proposed methodology introduces advanced explainability regarding, not only the data structure through the produced latent space, but also about the classification behaviour.
arXiv Detail & Related papers (2022-08-25T15:18:33Z) - MCDAL: Maximum Classifier Discrepancy for Active Learning [74.73133545019877]
Recent state-of-the-art active learning methods have mostly leveraged Generative Adversarial Networks (GAN) for sample acquisition.
We propose in this paper a novel active learning framework that we call Maximum Discrepancy for Active Learning (MCDAL)
In particular, we utilize two auxiliary classification layers that learn tighter decision boundaries by maximizing the discrepancies among them.
arXiv Detail & Related papers (2021-07-23T06:57:08Z) - Divergence Regulated Encoder Network for Joint Dimensionality Reduction
and Classification [2.989889278970106]
We investigate performing joint dimensionality reduction and classification using a novel histogram neural network.
Motivated by a popular dimensionality reduction approach, t-Distributed Neighbor Embedding (t-SNE), our proposed method incorporates a classification loss computed on samples in a low-dimensional embedding space.
Our results show that the proposed approach maintains and/or improves classification performance and reveals characteristics of features produced by neural networks that may be helpful for other applications.
arXiv Detail & Related papers (2020-12-31T17:39:02Z) - Few-Shot Open-Set Recognition using Meta-Learning [72.15940446408824]
The problem of open-set recognition is considered.
A new oPen sEt mEta LEaRning (PEELER) algorithm is introduced.
arXiv Detail & Related papers (2020-05-27T23:49:26Z) - There and Back Again: Revisiting Backpropagation Saliency Methods [87.40330595283969]
Saliency methods seek to explain the predictions of a model by producing an importance map across each input sample.
A popular class of such methods is based on backpropagating a signal and analyzing the resulting gradient.
We propose a single framework under which several such methods can be unified.
arXiv Detail & Related papers (2020-04-06T17:58:08Z) - Conditional Gaussian Distribution Learning for Open Set Recognition [10.90687687505665]
We propose Conditional Gaussian Distribution Learning (CGDL) for open set recognition.
In addition to detecting unknown samples, this method can also classify known samples by forcing different latent features to approximate different Gaussian models.
Experiments on several standard image reveal that the proposed method significantly outperforms the baseline method and achieves new state-of-the-art results.
arXiv Detail & Related papers (2020-03-19T14:32:08Z)
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.