Using Unlabeled Data for Increasing Low-Shot Classification Accuracy of Relevant and Open-Set Irrelevant Images

• URL: http://arxiv.org/abs/2010.00721v2
• Date: Fri, 3 Jun 2022 18:59:19 GMT
• Title: Using Unlabeled Data for Increasing Low-Shot Classification Accuracy of Relevant and Open-Set Irrelevant Images
• Authors: Spiridon Kasapis, Geng Zhang, Jonathon Smereka and Nickolas Vlahopoulos
• Abstract summary: In search, exploration, and reconnaissance tasks performed with autonomous ground vehicles, an image classification capability is needed. We present an open-set low-shot classifier that uses, during its training, a modest number of labeled images for each relevant class. It is capable of identifying images from the relevant classes, determining when a candidate image is irrelevant, and it can further recognize categories of irrelevant images that were not included in the training.
• Score: 0.4110108749051655
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In search, exploration, and reconnaissance tasks performed with autonomous ground vehicles, an image classification capability is needed for specifically identifying targeted objects (relevant classes) and at the same time recognize when a candidate image does not belong to anyone of the relevant classes (irrelevant images). In this paper, we present an open-set low-shot classifier that uses, during its training, a modest number (less than 40) of labeled images for each relevant class, and unlabeled irrelevant images that are randomly selected at each epoch of the training process. The new classifier is capable of identifying images from the relevant classes, determining when a candidate image is irrelevant, and it can further recognize categories of irrelevant images that were not included in the training (unseen). The proposed low-shot classifier can be attached as a top layer to any pre-trained feature extractor when constructing a Convolutional Neural Network.

Related papers

• Image-free Classifier Injection for Zero-Shot Classification [72.66409483088995]
  Zero-shot learning models achieve remarkable results on image classification for samples from classes that were not seen during training. We aim to equip pre-trained models with zero-shot classification capabilities without the use of image data. We achieve this with our proposed Image-free Injection with Semantics (ICIS)
  arXiv  Detail & Related papers  (2023-08-21T09:56:48Z)
• Few-shot Open-set Recognition Using Background as Unknowns [58.04165813493666]
  Few-shot open-set recognition aims to classify both seen and novel images given only limited training data of seen classes. Our proposed method not only outperforms multiple baselines but also sets new results on three popular benchmarks.
  arXiv  Detail & Related papers  (2022-07-19T04:19:29Z)
• Deep reinforced active learning for multi-class image classification [0.0]
  High accuracy medical image classification can be limited by the costs of acquiring more data as well as the time and expertise needed to label existing images. We apply active learning to medical image classification, a method which aims to maximise model performance on a minimal subset from a larger pool of data.
  arXiv  Detail & Related papers  (2022-06-20T09:30:55Z)
• Generalized Category Discovery [148.32255950504182]
  We consider a highly general image recognition setting wherein, given a labelled and unlabelled set of images, the task is to categorize all images in the unlabelled set. Here, the unlabelled images may come from labelled classes or from novel ones. We first establish strong baselines by taking state-of-the-art algorithms from novel category discovery and adapting them for this task. We then introduce a simple yet effective semi-supervised $k$-means method to cluster the unlabelled data into seen and unseen classes.
  arXiv  Detail & Related papers  (2022-01-07T18:58:35Z)
• Rectifying the Shortcut Learning of Background: Shared Object Concentration for Few-Shot Image Recognition [101.59989523028264]
  Few-Shot image classification aims to utilize pretrained knowledge learned from a large-scale dataset to tackle a series of downstream classification tasks. We propose COSOC, a novel Few-Shot Learning framework, to automatically figure out foreground objects at both pretraining and evaluation stage.
  arXiv  Detail & Related papers  (2021-07-16T07:46:41Z)
• AutoNovel: Automatically Discovering and Learning Novel Visual Categories [138.80332861066287]
  We present a new approach called AutoNovel to tackle the problem of discovering novel classes in an image collection given labelled examples of other classes. We evaluate AutoNovel on standard classification benchmarks and substantially outperform current methods for novel category discovery.
  arXiv  Detail & Related papers  (2021-06-29T11:12:16Z)
• Prototypical Region Proposal Networks for Few-Shot Localization and Classification [1.5100087942838936]
  We develop a framework to unifysegmentation and classification into an end-to-end classification model -- PRoPnet. We empirically demonstrate that our methods improve accuracy on image datasets with natural scenes containing multiple object classes.
  arXiv  Detail & Related papers  (2021-04-08T04:03:30Z)
• Grafit: Learning fine-grained image representations with coarse labels [114.17782143848315]
  This paper tackles the problem of learning a finer representation than the one provided by training labels. By jointly leveraging the coarse labels and the underlying fine-grained latent space, it significantly improves the accuracy of category-level retrieval methods.
  arXiv  Detail & Related papers  (2020-11-25T19:06:26Z)
• Deep Learning Classification With Noisy Labels [1.433758865948252]
  We train face recognition systems for actors identification with a closed set of identities while being exposed to a significant number of perturbators. We review recent works on how to manage noisy annotations when training deep learning classifiers, independently from our interest in face recognition.
  arXiv  Detail & Related papers  (2020-04-23T13:02:45Z)
• Relevance Prediction from Eye-movements Using Semi-interpretable Convolutional Neural Networks [9.007191808968242]
  We propose an image-classification method to predict the perceived-relevance of text documents from eye-movements. An eye-tracking study was conducted where participants read short news articles, and rated them as relevant or irrelevant for answering a trigger question. We encode participants' eye-movement scanpaths as images, and then train a convolutional neural network classifier using these scanpath images.
  arXiv  Detail & Related papers  (2020-01-15T07:02:14Z)

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.