We lifted 7 functions out of this paper's own repositories and ran 7 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| youngsean/nids-net | canonical | 7 of 7 |
| Function | Status | Where it lives |
|---|---|---|
| apply_nms_to_results | Ran | youngsean/nids-net/ros/nids_net.py code served (permissive licence) · get_code("7f071ad395866cc1") |
| find_mask_bbox | Ran | youngsean/nids-net/get_object_features_via_FFA.py code served (permissive licence) · get_code("51a6654539b06a4f") |
| get_args_parser | Ran | youngsean/nids-net/RoboTools_test_eval_gdino_FFA.py code served (permissive licence) · get_code("3fa78c080af50ed0") |
| get_args_parser | Ran | youngsean/nids-net/demo_eval_gdino_FFA.py code served (permissive licence) · get_code("979af44dad69deec") |
| get_args_parser | Ran | youngsean/nids-net/lmo_test_eval_gdino_FFA.py code served (permissive licence) · get_code("5fde4e66c71686d7") |
| get_bounding_boxes | Ran | youngsean/nids-net/ros/nids_net.py code served (permissive licence) · get_code("c56731246b8bed37") |
| show_anns | Ran | youngsean/nids-net/ros/nids_net.py code served (permissive licence) · get_code("c2b2608a6e57f95f") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Novel Instance Detection and Segmentation (NIDS) aims at detecting and segmenting novel object instances given a few examples of each instance. We propose a unified, simple, yet effective framework (NIDS-Net) comprising object proposal generation, embedding creation for both instance templates and proposal regions, and embedding matching for instance label assignment. Leveraging recent advancements in large vision methods, we utilize Grounding DINO and Segment Anything Model (SAM) to obtain object proposals with accurate bounding boxes and masks. Central to our approach is the generation of high-quality instance embeddings. We utilized foreground feature averages of patch embeddings from the DINOv2 ViT backbone, followed by refinement through a weight adapter mechanism that we introduce. We show experimentally that our weight adapter can adjust the embeddings locally within their feature space and effectively limit overfitting in the few-shot setting. Furthermore, the weight adapter optimizes weights to enhance the distinctiveness of instance embeddings during similarity computation. This methodology enables a straightforward matching strategy that results in significant performance gains. Our framework surpasses current state-of-the-art methods, demonstrating notable improvements in four detection datasets. In the segmentation tasks on seven core datasets of the BOP challenge, our method outperforms the leading published RGB methods and remains competitive with the best RGB-D method. We have also verified our method using real-world images from a Fetch robot and a RealSense camera. Project Page: https://irvlutd.github.io/NIDSNet/
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2405.17859")
get_code_for_paper("2405.17859")
have("2405.17859")
Connect an agent — have() is free.