Using Sentences as Semantic Representations in Large Scale Zero-Shot Learning

• URL: http://arxiv.org/abs/2010.02959v1
• Date: Tue, 6 Oct 2020 18:22:21 GMT
• Title: Using Sentences as Semantic Representations in Large Scale Zero-Shot Learning
• Authors: Yannick Le Cacheux and Herv\'e Le Borgne and Michel Crucianu
• Abstract summary: Zero-shot learning aims to recognize instances of unseen classes, for which no visual instance is available during training. A good trade-off could be to employ short sentences in natural language as class descriptions. We show that while simple methods cannot achieve very good results with sentences alone, a combination of usual word embeddings and sentences can significantly outperform current state-of-the-art.
• Score: 6.0158981171030685
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Zero-shot learning aims to recognize instances of unseen classes, for which no visual instance is available during training, by learning multimodal relations between samples from seen classes and corresponding class semantic representations. These class representations usually consist of either attributes, which do not scale well to large datasets, or word embeddings, which lead to poorer performance. A good trade-off could be to employ short sentences in natural language as class descriptions. We explore different solutions to use such short descriptions in a ZSL setting and show that while simple methods cannot achieve very good results with sentences alone, a combination of usual word embeddings and sentences can significantly outperform current state-of-the-art.

Related papers

• Manual Verbalizer Enrichment for Few-Shot Text Classification [1.860409237919611]
  acrshortmave is an approach for verbalizer construction by enrichment of class labels. Our model achieves state-of-the-art results while using significantly fewer resources.
  arXiv  Detail & Related papers  (2024-10-08T16:16:47Z)
• Learning Context-aware Classifier for Semantic Segmentation [88.88198210948426]
  In this paper, contextual hints are exploited via learning a context-aware classifier. Our method is model-agnostic and can be easily applied to generic segmentation models. With only negligible additional parameters and +2% inference time, decent performance gain has been achieved on both small and large models.
  arXiv  Detail & Related papers  (2023-03-21T07:00:35Z)
• On Guiding Visual Attention with Language Specification [76.08326100891571]
  We use high-level language specification as advice for constraining the classification evidence to task-relevant features, instead of distractors. We show that supervising spatial attention in this way improves performance on classification tasks with biased and noisy data.
  arXiv  Detail & Related papers  (2022-02-17T22:40:19Z)
• Semantic-Oriented Unlabeled Priming for Large-Scale Language Models [12.074766935042588]
  We introduce Semantic-Oriented Unlabeled Priming (SOUP), a method that classifies examples by retrieving semantically similar unlabeled examples. We also propose bag-of-contexts priming, a new priming strategy that is more suitable for our setting and enables the usage of more examples than fit into the context window.
  arXiv  Detail & Related papers  (2022-02-12T19:50:59Z)
• Learning Debiased and Disentangled Representations for Semantic Segmentation [52.35766945827972]
  We propose a model-agnostic and training scheme for semantic segmentation. By randomly eliminating certain class information in each training iteration, we effectively reduce feature dependencies among classes. Models trained with our approach demonstrate strong results on multiple semantic segmentation benchmarks.
  arXiv  Detail & Related papers  (2021-10-31T16:15:09Z)
• On The Ingredients of an Effective Zero-shot Semantic Parser [95.01623036661468]
  We analyze zero-shot learning by paraphrasing training examples of canonical utterances and programs from a grammar. We propose bridging these gaps using improved grammars, stronger paraphrasers, and efficient learning methods. Our model achieves strong performance on two semantic parsing benchmarks (Scholar, Geo) with zero labeled data.
  arXiv  Detail & Related papers  (2021-10-15T21:41:16Z)
• Reordering Examples Helps during Priming-based Few-Shot Learning [6.579039107070663]
  We show that PERO can learn to generalize efficiently using as few as 10 examples. We demonstrate the effectiveness of the proposed method on the tasks of sentiment classification, natural language inference and fact retrieval.
  arXiv  Detail & Related papers  (2021-06-03T11:02:36Z)
• Rich Semantics Improve Few-shot Learning [49.11659525563236]
  We show that by using 'class-level' language descriptions, that can be acquired with minimal annotation cost, we can improve the few-shot learning performance. We develop a Transformer based forward and backward encoding mechanism to relate visual and semantic tokens.
  arXiv  Detail & Related papers  (2021-04-26T16:48:27Z)
• Leveraging Adversarial Training in Self-Learning for Cross-Lingual Text Classification [52.69730591919885]
  We present a semi-supervised adversarial training process that minimizes the maximal loss for label-preserving input perturbations. We observe significant gains in effectiveness on document and intent classification for a diverse set of languages.
  arXiv  Detail & Related papers  (2020-07-29T19:38:35Z)
• Contextualizing Enhances Gradient Based Meta Learning [7.009032627535598]
  We show how to equip meta learning methods with contextualizers and show that their use can significantly boost performance on a range of few shot learning datasets. Our approach is particularly apt for low-data environments where it is difficult to update parameters without overfitting.
  arXiv  Detail & Related papers  (2020-07-17T04:01:56Z)

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.