Papers › Robot Instance Segmentation with Few Annotations for Grasping
Robot Instance Segmentation with Few Annotations for Grasping
Moshe Kimhi, David Vainshtein, Chaim Baskin, Dotan Di Castro
The ability of robots to manipulate objects relies heavily on their aptitude for visual perception. In domains characterized by cluttered scenes and high object variability, most methods call for vast labeled datasets, laboriously hand-annotated, with the aim of training capable models. Once deployed, the challenge of generalizing to unfamiliar objects implies that the model must evolve alongside its domain. To address this, we propose a novel framework that combines Semi-Supervised Learning (SSL) with Learning Through Interaction (LTI), allowing a model to learn by observing scene alterations and leverage visual consistency despite temporal gaps without requiring curated data of interaction sequences. As a result, our approach exploits partially annotated data through self-supervision and incorporates temporal context using pseudo-sequences generated from unlabeled still images. We validate our method on two common benchmarks, ARMBench mix-object-tote and OCID, where it achieves state-of-the-art performance. Notably, on ARMBench, we attain an AP₅₀ of 86.37, almost a 20% improvement over existing work, and obtain remarkable results in scenarios with extremely low annotation, achieving an AP₅₀ score of 84.89 with just 1 % of annotated data compared to 72 presented in ARMBench on the fully annotated counterpart.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_citation_path(paper_1="2407.01302", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2407.01302")
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Instance Segmentation | ARMBench | RISE (VIT-B) | AP50 | 86.37 | #1 of 7 | Archive leaderboard | report |
| Instance Segmentation | ARMBench | RISE (VIT-B) | AP75 | 77.51 | #1 of 7 | Archive leaderboard | report |
| Instance Segmentation | ARMBench | RISE (R101) | AP50 | 84.74 | #2 of 7 | Archive leaderboard | report |
| Instance Segmentation | ARMBench | RISE (R101) | AP75 | 75.93 | #2 of 7 | Archive leaderboard | report |
| Instance Segmentation | ARMBench | RISE (R50) | AP50 | 83.53 | #3 of 7 | Archive leaderboard | report |
| Instance Segmentation | ARMBench | RISE (R50) | AP75 | 75.15 | #3 of 7 | Archive leaderboard | report |
| Instance Segmentation | ARMBench | Mask2Former | AP50 | 81.2 | #5 of 7 | Archive leaderboard | report |
| Instance Segmentation | ARMBench | Mask2Former | AP75 | 74.0 | #5 of 7 | Archive leaderboard | report |
| Instance Segmentation | ARMBench | Deformable DETR | AP50 | 77.03 | #6 of 7 | Archive leaderboard | report |
| Instance Segmentation | ARMBench | Deformable DETR | AP75 | 63.4 | #6 of 7 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections