Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces IMPRINT, a framework that enhances zero-shot Object Goal Navigation by enriching textual queries with web-sourced images, addressing the limitations of text-only queries in fine-grained object categories. The method employs a vision-language model to encode retrieved images, creating similarity maps that improve localization in queryable semantic maps without requiring modifications to the navigation policy. Evaluations on the new HSSD-rare benchmark demonstrate that image-conditioned queries lead to significant improvements in object grounding and navigation performance, while also revealing that the effectiveness of these gains is contingent on the quality of downstream detection systems.
Enriching text queries with images can drastically enhance navigation performance in long-tail object categories, revealing a critical dependency on detection quality.
Embodied AI increasingly relies on queryable semantic maps built from pre-trained vision-language models to enable zero-shot Object Goal Navigation (ObjectNav). However, existing approaches typically depend on text-only queries, which become less reliable as semantic specificity increases toward fine-grained object categories. We introduce IMPRINT, a zero-shot plug-and-play framework that enriches textual object queries with web-sourced images to improve grounding in queryable maps. Retrieved images are encoded using a vision-language model, matched against the semantic map to produce similarity maps, and aggregated to yield context-aware localization. Notably, this requires no training or modification of the underlying navigation policy. To explicitly evaluate long-tail behavior, we present HSSD-rare, a new ObjectNav benchmark built on Habitat Synthetic Scenes and featuring semantically specific subcategories. Across both OVON and HSSD-rare, image-conditioned queries consistently improve object grounding and yield end-to-end navigation gains. Further analysis reveals that translating localization gains to navigation performance depends critically on downstream detection quality, highlighting a key systems bottleneck in long-tail embodied navigation.