MMF: A loss extension for feature learning in open set recognition

• URL: http://arxiv.org/abs/2006.15117v2
• Date: Mon, 3 May 2021 21:37:12 GMT
• Title: MMF: A loss extension for feature learning in open set recognition
• Authors: Jingyun Jia, Philip K. Chan
• Abstract summary: We propose an add-on extension for loss functions in neural networks to address the open set recognition problem. Our loss extension leverages the neural network to find polar representations for the known classes so that the representations of the known and the unknown classes become more effectively separable.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Open set recognition (OSR) is the problem of classifying the known classes, meanwhile identifying the unknown classes when the collected samples cannot exhaust all the classes. There are many applications for the OSR problem. For instance, the frequently emerged new malware classes require a system that can classify the known classes and identify the unknown malware classes. In this paper, we propose an add-on extension for loss functions in neural networks to address the OSR problem. Our loss extension leverages the neural network to find polar representations for the known classes so that the representations of the known and the unknown classes become more effectively separable. Our contributions include: First, we introduce an extension that can be incorporated into different loss functions to find more discriminative representations. Second, we show that the proposed extension can significantly improve the performances of two different types of loss functions on datasets from two different domains. Third, we show that with the proposed extension, one loss function outperforms the others in terms of training time and model accuracy.

Related papers

• Class-Independent Increment: An Efficient Approach for Multi-label Class-Incremental Learning [49.65841002338575]
  This paper focuses on the challenging yet practical multi-label class-incremental learning (MLCIL) problem. We propose a novel class-independent incremental network (CINet) to extract multiple class-level embeddings for multi-label samples. It learns and preserves the knowledge of different classes by constructing class-specific tokens.
  arXiv  Detail & Related papers  (2025-03-01T14:40:52Z)
• Learning Large Margin Sparse Embeddings for Open Set Medical Diagnosis [8.131130865777346]
  Open set recognition (OSR) states that categories unseen in training could appear in testing. OSR requires an algorithm to not only correctly classify known classes, but also recognize unknown classes and forward them to experts for further diagnosis. We propose Open Margin Cosine Loss (OMCL) unifying two mechanisms. The former, called Margin Loss with Adaptive Scale (MLAS), introduces angular margin for reinforcing intra-class compactness and inter-class separability. The latter, called Open-Space Suppression (OSS), opens the classifier by recognizing sparse embedding space as unknowns using proposed feature space descriptors.
  arXiv  Detail & Related papers  (2023-07-10T13:09:42Z)
• Class-Incremental Learning: A Survey [84.30083092434938]
  Class-Incremental Learning (CIL) enables the learner to incorporate the knowledge of new classes incrementally. CIL tends to catastrophically forget the characteristics of former ones, and its performance drastically degrades. We provide a rigorous and unified evaluation of 17 methods in benchmark image classification tasks to find out the characteristics of different algorithms.
  arXiv  Detail & Related papers  (2023-02-07T17:59:05Z)
• PatchMix Augmentation to Identify Causal Features in Few-shot Learning [55.64873998196191]
  Few-shot learning aims to transfer knowledge learned from base with sufficient categories labelled data to novel categories with scarce known information. We propose a novel data augmentation strategy dubbed as PatchMix that can break this spurious dependency. We show that such an augmentation mechanism, different from existing ones, is able to identify the causal features.
  arXiv  Detail & Related papers  (2022-11-29T08:41:29Z)
• Class-Specific Semantic Reconstruction for Open Set Recognition [101.24781422480406]
  Open set recognition enables deep neural networks (DNNs) to identify samples of unknown classes. We propose a novel method, called Class-Specific Semantic Reconstruction (CSSR), that integrates the power of auto-encoder (AE) and prototype learning. Results of experiments conducted on multiple datasets show that the proposed method achieves outstanding performance in both close and open set recognition.
  arXiv  Detail & Related papers  (2022-07-05T16:25:34Z)
• Representation learning with function call graph transformations for malware open set recognition [0.0]
  Open set recognition problem has been a challenge in many machine learning (ML) applications, such as security. In this paper, we introduce a self-supervised pre-training approach for the OSR problem in malware classification.
  arXiv  Detail & Related papers  (2022-05-13T22:40:14Z)
• Incremental Class Learning using Variational Autoencoders with Similarity Learning [0.0]
  Catastrophic forgetting in neural networks during incremental learning remains a challenging problem. Our research investigates catastrophic forgetting for four well-known metric-based loss functions during incremental class learning. The angular loss was least affected, followed by contrastive, triplet loss, and centre loss with good mining techniques.
  arXiv  Detail & Related papers  (2021-10-04T10:19:53Z)
• Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection [89.43987367139724]
  Face forgery detection is raising ever-increasing interest in computer vision. Recent works have reached sound achievements, but there are still unignorable problems. A novel frequency-aware discriminative feature learning framework is proposed in this paper.
  arXiv  Detail & Related papers  (2021-03-16T14:17:17Z)
• CC-Loss: Channel Correlation Loss For Image Classification [35.43152123975516]
  The channel correlation loss (CC-Loss) is able to constrain the specific relations between classes and channels. Two different backbone models trained with the proposed CC-Loss outperform the state-of-the-art loss functions on three image classification datasets.
  arXiv  Detail & Related papers  (2020-10-12T05:59:06Z)
• Universal-to-Specific Framework for Complex Action Recognition [114.78468658086572]
  We propose an effective universal-to-specific (U2S) framework for complex action recognition. The U2S framework is composed of threeworks: a universal network, a category-specific network, and a mask network. Experiments on a variety of benchmark datasets demonstrate the effectiveness of the U2S framework.
  arXiv  Detail & Related papers  (2020-07-13T01:49:07Z)
• Deep Learning and Open Set Malware Classification: A Survey [0.0]
  Recent machine learning works have shed light on Open Set Recognition (OSR) problem in machine learning. OSR system should not only correctly classify the known classes, but also recognize the unknown class. This survey provides an overview of different deep learning techniques, a discussion of OSR and graph representation solutions and an introduction of malware classification systems.
  arXiv  Detail & Related papers  (2020-04-08T21:36:21Z)
• Learning Class Regularized Features for Action Recognition [68.90994813947405]
  We introduce a novel method named Class Regularization that performs class-based regularization of layer activations. We show that using Class Regularization blocks in state-of-the-art CNN architectures for action recognition leads to systematic improvement gains of 1.8%, 1.2% and 1.4% on the Kinetics, UCF-101 and HMDB-51 datasets, respectively.
  arXiv  Detail & Related papers  (2020-02-07T07:27:49Z)

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.