Learning by Asking Questions for Knowledge-based Novel Object Recognition

• URL: http://arxiv.org/abs/2210.05879v1
• Date: Wed, 12 Oct 2022 02:51:58 GMT
• Title: Learning by Asking Questions for Knowledge-based Novel Object Recognition
• Authors: Kohei Uehara, Tatsuya Harada
• Abstract summary: In real-world object recognition, there are numerous object classes to be recognized. Conventional image recognition based on supervised learning can only recognize object classes that exist in the training data, and thus has limited applicability in the real world. Inspired by this, we study a framework for acquiring external knowledge through question generation that would help the model instantly recognize novel objects. Our pipeline consists of two components: the Object-based object recognition, and the Question Generator, which generates knowledge-aware questions to acquire novel knowledge.
• Score: 64.55573343404572
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In real-world object recognition, there are numerous object classes to be recognized. Conventional image recognition based on supervised learning can only recognize object classes that exist in the training data, and thus has limited applicability in the real world. On the other hand, humans can recognize novel objects by asking questions and acquiring knowledge about them. Inspired by this, we study a framework for acquiring external knowledge through question generation that would help the model instantly recognize novel objects. Our pipeline consists of two components: the Object Classifier, which performs knowledge-based object recognition, and the Question Generator, which generates knowledge-aware questions to acquire novel knowledge. We also propose a question generation strategy based on the confidence of the knowledge-aware prediction of the Object Classifier. To train the Question Generator, we construct a dataset that contains knowledge-aware questions about objects in the images. Our experiments show that the proposed pipeline effectively acquires knowledge about novel objects compared to several baselines.

Related papers

• Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generators [78.63553017938911]
  Large language models (LLMs) outperform information retrieval techniques for downstream knowledge-intensive tasks. However, community concerns abound regarding the factuality and potential implications of using this uncensored knowledge. We introduce CONNER, designed to evaluate generated knowledge from six important perspectives.
  arXiv  Detail & Related papers  (2023-10-11T08:22:37Z)
• Detecting the open-world objects with the help of the Brain [20.00772846521719]
  Open World Object Detection (OWOD) is a novel computer vision task with a considerable challenge. OWOD algorithms are expected to detect unseen/unknown objects and incrementally learn them. We propose leveraging the VL as the Brain'' of the open-world detector by simply generating unknown labels.
  arXiv  Detail & Related papers  (2023-03-21T06:44:02Z)
• Knowledge-augmented Deep Learning and Its Applications: A Survey [60.221292040710885]
  knowledge-augmented deep learning (KADL) aims to identify domain knowledge and integrate it into deep models for data-efficient, generalizable, and interpretable deep learning. This survey subsumes existing works and offers a bird's-eye view of research in the general area of knowledge-augmented deep learning.
  arXiv  Detail & Related papers  (2022-11-30T03:44:15Z)
• Towards Open-Set Object Detection and Discovery [38.81806249664884]
  We present a new task, namely Open-Set Object Detection and Discovery (OSODD) We propose a two-stage method that first uses an open-set object detector to predict both known and unknown objects. Then, we study the representation of predicted objects in an unsupervised manner and discover new categories from the set of unknown objects.
  arXiv  Detail & Related papers  (2022-04-12T08:07:01Z)
• Knowledge-Guided Object Discovery with Acquired Deep Impressions [41.07379505694274]
  We present a framework called Acquired Deep Impressions (ADI) which continuously learns knowledge of objects as "impressions" ADI first acquires knowledge from scene images containing a single object in a supervised manner. It then learns from novel multi-object scene images which may contain objects that have not been seen before.
  arXiv  Detail & Related papers  (2021-03-19T03:17:57Z)
• Online Learning of Objects through Curiosity-Driven Active Learning [9.89901717499058]
  Children learn continually by asking questions about the concepts they are most curious about. With robots becoming an integral part of our society, they must also learn unknown concepts continually by asking humans questions. This paper presents a novel framework for curiosity-driven online learning of objects.
  arXiv  Detail & Related papers  (2021-03-13T17:42:09Z)
• Towards Open World Object Detection [68.79678648726416]
  ORE: Open World Object Detector is based on contrastive clustering and energy based unknown identification. We find that identifying and characterizing unknown instances helps to reduce confusion in an incremental object detection setting.
  arXiv  Detail & Related papers  (2021-03-03T18:58:18Z)
• Towards a Universal Continuous Knowledge Base [49.95342223987143]
  We propose a method for building a continuous knowledge base that can store knowledge imported from multiple neural networks. Experiments on text classification show promising results. We import the knowledge from multiple models to the knowledge base, from which the fused knowledge is exported back to a single model.
  arXiv  Detail & Related papers  (2020-12-25T12:27:44Z)
• A Review on Intelligent Object Perception Methods Combining Knowledge-based Reasoning and Machine Learning [60.335974351919816]
  Object perception is a fundamental sub-field of Computer Vision. Recent works seek ways to integrate knowledge engineering in order to expand the level of intelligence of the visual interpretation of objects.
  arXiv  Detail & Related papers  (2019-12-26T13:26:49Z)

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.