# Interactive Acquisition of Fine-grained Visual Concepts by Exploiting Semantics of Generic Characterizations in Discourse

arXiv: https://arxiv.org/abs/2305.03461 · HTML: https://mlsanity.com/paper/2305.03461/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 33 references that are in the map.
- First posted on arXiv 5 May 2023.

## Builds on (most cited first, 8 of 8)

- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Fine-Grained Image Analysis with Deep Learning: A Survey](https://mlsanity.com/paper/2111.06119/) (2021)
- [Fine-graind Image Classification via Combining Vision and Language](https://mlsanity.com/paper/1704.02792/) (2017)
- [Embedding Human Knowledge into Deep Neural Network via Attention Map](https://mlsanity.com/paper/1905.03540/) (2019)
- [Fine-grained Categorization and Dataset Bootstrapping using Deep Metric Learning with Humans in the Loop](https://mlsanity.com/paper/1512.05227/) (2015)
- [Knowledge-Embedded Representation Learning for Fine-Grained Image Recognition](https://mlsanity.com/paper/1807.00505/) (2018)
- [ProbRobScene: A Probabilistic Specification Language for 3D Robotic Manipulation Environments](https://mlsanity.com/paper/2011.01126/) (2020)

## Built on by (most cited first, 3 of 3)

- [SECURE: Semantics-aware Embodied Conversation under Unawareness for Lifelong Robot Learning](https://mlsanity.com/paper/2409.17755/) (2024)
- [A Taxonomy of Conceptual Alignment in Human-Robot Dialogue](https://mlsanity.com/paper/2606.22360/) (2026)
- [Learning to Assemble Novel Structures with Unfamiliar Parts under Semantic Constraints](https://mlsanity.com/paper/2608.13684/) (2026)

## Abstract (arXiv)

Interactive Task Learning (ITL) concerns learning about unforeseen domain concepts via natural interactions with human users. The learner faces a number of significant constraints: learning should be online, incremental and few-shot, as it is expected to perform tangible belief updates right after novel words denoting unforeseen concepts are introduced. In this work, we explore a challenging symbol grounding task--discriminating among object classes that look very similar--within the constraints imposed by ITL. We demonstrate empirically that more data-efficient grounding results from exploiting the truth-conditions of the teacher's generic statements (e.g., "Xs have attribute Z.") and their implicatures in context (e.g., as an answer to "How are Xs and Ys different?", one infers Y lacks attribute Z).