Visuo-Tactile Zero-Shot Object Recognition with Vision-Language Model
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929500152922112 |
|---|---|
| author | Ueda, Shiori Hashimoto, Atsushi Hamaya, Masashi Tanaka, Kazutoshi Saito, Hideo |
| author_facet | Ueda, Shiori Hashimoto, Atsushi Hamaya, Masashi Tanaka, Kazutoshi Saito, Hideo |
| contents | Tactile perception is vital, especially when distinguishing visually similar objects. We propose an approach to incorporate tactile data into a Vision-Language Model (VLM) for visuo-tactile zero-shot object recognition. Our approach leverages the zero-shot capability of VLMs to infer tactile properties from the names of tactilely similar objects. The proposed method translates tactile data into a textual description solely by annotating object names for each tactile sequence during training, making it adaptable to various contexts with low training costs. The proposed method was evaluated on the FoodReplica and Cube datasets, demonstrating its effectiveness in recognizing objects that are difficult to distinguish by vision alone. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_09276 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Visuo-Tactile Zero-Shot Object Recognition with Vision-Language Model Ueda, Shiori Hashimoto, Atsushi Hamaya, Masashi Tanaka, Kazutoshi Saito, Hideo Robotics Tactile perception is vital, especially when distinguishing visually similar objects. We propose an approach to incorporate tactile data into a Vision-Language Model (VLM) for visuo-tactile zero-shot object recognition. Our approach leverages the zero-shot capability of VLMs to infer tactile properties from the names of tactilely similar objects. The proposed method translates tactile data into a textual description solely by annotating object names for each tactile sequence during training, making it adaptable to various contexts with low training costs. The proposed method was evaluated on the FoodReplica and Cube datasets, demonstrating its effectiveness in recognizing objects that are difficult to distinguish by vision alone. |
| title | Visuo-Tactile Zero-Shot Object Recognition with Vision-Language Model |
| topic | Robotics |
| url | https://arxiv.org/abs/2409.09276 |