skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Neural Variational Learning for Grounded Language Acquisition
We propose a learning system in which language is grounded in visual percepts without specific pre-defined categories of terms. We present a unified generative method to acquire a shared semantic/visual embedding that enables the learning of language about a wide range of real-world objects. We evaluate the efficacy of this learning by predicting the semantics of objects and comparing the performance with neural and non-neural inputs. We show that this generative approach exhibits promising results in language grounding without pre-specifying visual categories under low resource settings. Our experiments demonstrate that this approach is generalizable to multilingual, highly varied datasets.  more » « less
Award ID(s):
2024878 1940931 1657469 1813223
PAR ID:
10296639
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
IEEE ROMAN
ISSN:
1944-9437
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; (, npj Science of Learning)
    null (Ed.)
    Abstract How does STEM knowledge learned in school change students’ brains? Using fMRI, we presented photographs of real-world structures to engineering students with classroom-based knowledge and hands-on lab experience, examining how their brain activity differentiated them from their “novice” peers not pursuing engineering degrees. A data-driven MVPA and machine-learning approach revealed that neural response patterns of engineering students were convergent with each other and distinct from novices’ when considering physical forces acting on the structures. Furthermore, informational network analysis demonstrated that the distinct neural response patterns of engineering students reflected relevant concept knowledge: learned categories of mechanical structures. Information about mechanical categories was predominantly represented in bilateral anterior ventral occipitotemporal regions. Importantly, mechanical categories were not explicitly referenced in the experiment, nor does visual similarity between stimuli account for mechanical category distinctions. The results demonstrate how learning abstract STEM concepts in the classroom influences neural representations of objects in the world. 
    more » « less
  2. ; ; ; (, IEEE)
    Humans excel at efficiently navigating through crowds without collision by focusing on specific visual regions relevant to navigation. However, most robotic visual navigation methods rely on deep learning models pre-trained on vision tasks, which prioritize salient objects—not necessarily relevant to navigation and potentially misleading. Alternative approaches train specialized navigation models from scratch, requiring significant computation. On the other hand, self-supervised learning has revolutionized computer vision and natural language processing, but its application to robotic navigation remains underexplored due to the difficulty of defining effective self-supervision signals. Motivated by these observations, in this work, we propose a Self-Supervised Vision-Action Model for Visual Navigation Pre-Training (VANP). Instead of detecting salient objects that are beneficial for tasks such as classification or detection, VANP learns to focus only on specific visual regions that are relevant to the navigation task. To achieve this, VANP uses a history of visual observations, future actions, and a goal image for self-supervision, and embeds them using two small Transformer Encoders. Then, VANP maximizes the information between the embeddings by using a mutual information maximization objective function. We demonstrate that most VANP-extracted features match with human navigation intuition. VANP achieves comparable performance as models learned end-to-end with half the training time and models trained on a large-scale, fully supervised dataset, i.e., ImageNet, with only 0.08% data. 
    more » « less
  3. ; ; ; (, Proceedings of the European Conference on Computer Vision (ECCV))
    We present a scalable approach for Detecting Objects by transferring Common-sense Knowledge (DOCK) from source to target categories. In our setting, the training data for the source categories have bounding box annotations, while those for the target categories only have image-level annotations. Current state-of-the-art approaches focus on image-level visual or semantic similarity to adapt a detector trained on the source categories to the new target categories. In contrast, our key idea is to (i) use similarity not at the image-level, but rather at the region-level, and (ii) leverage richer common-sense (based on attribute, spatial, etc.) to guide the algorithm towards learning the correct detections. We acquire such common-sense cues automatically from readily-available knowledge bases without any extra human effort. On the challenging MS COCO dataset, we find that common-sense knowledge can substantially improve detection performance over existing transfer-learning baselines. 
    more » « less
  4. ; ; ; (, Proceedings of the 32nd AAAI Conference on Arti cial Intelligence (AAAI))
    A major goal of grounded language learning research is to enable robots to connect language predicates to a robot’s physical interactive perception of the world. Coupling object exploratory behaviors such as grasping, lifting, and looking with multiple sensory modalities (e.g., audio, haptics, and vision) enables a robot to ground non-visual words like “heavy” as well as visual words like “red”. A major limitation of existing approaches to multi-modal language grounding is that a robot has to exhaustively explore training objects with a variety of actions when learning a new such language predicate. This paper proposes a method for guiding a robot’s behavioral exploration policy when learning a novel predicate based on known grounded predicates and the novel predicate’s linguistic relationship to them. We demonstrate our approach on two datasets in which a robot explored large sets of objects and was tasked with learning to recognize whether novel words applied to those objects. 
    more » « less
  5. ; ; ; ; ; ; (, EMNLP'20: 2020 Conf. on Empirical Methods in Natural Language Processing, Nov. 2020)
    null (Ed.)
    Current text classification methods typically require a good number of human-labeled documents as training data, which can be costly and difficult to obtain in real applications. Hu-mans can perform classification without seeing any labeled examples but only based on a small set of words describing the categories to be classified. In this paper, we explore the potential of only using the label name of each class to train classification models on un-labeled data, without using any labeled documents. We use pre-trained neural language models both as general linguistic knowledge sources for category understanding and as representation learning models for document classification. Our method (1) associates semantically related words with the label names, (2) finds category-indicative words and trains the model to predict their implied categories, and (3) generalizes the model via self-training. We show that our model achieves around 90% ac-curacy on four benchmark datasets including topic and sentiment classification without using any labeled documents but learning from unlabeled data supervised by at most 3 words (1 in most cases) per class as the label name1. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email