Papers › Improving existing segmentators performance with zero-shot segmentators

Improving existing segmentators performance with zero-shot segmentators

26 Jul 2023journal 2023 7archive 2025-07-28

Nanni, L., Fusaro, D., Fantozzi, C., Pretto, A.

This paper explores the potential of using the SAM segmentator to enhance the segmentation capability of known methods. SAM is a promptable segmentation system that offers zero-shot generalization to unfamiliar objects and images, eliminating the need for additional training. The open-source nature of SAM on GitHub allows for easy access and implementation. In our experiments, we aim to improve the segmentation performance by providing SAM with checkpoints extracted from the masks produced by DeepLabv3+, then merging the segmentation masks provided by these two networks. Additionally, we examine the \enquote{oracle} method (as upper bound baseline performance), where segmentation masks are inferred only by SAM with checkpoints extracted from ground truth. In addition, we tested in the CAMO datasets an ensemble of PVTv2 transformers; combining the ensemble and SAM yields state-of-the-art performance in that dataset. The results of our study provide valuable insights into the potential of incorporating the SAM segmentator into existing segmentation techniques. We release with this paper the open-source implementation of our method.

Paper PDF Code

Code

LorisNanni/Improving-existing-segmentators-performance-with-zero-shot-segmentators report

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.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Camouflaged Object Segmentation Segmentation Zero-shot Generalization

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Camouflaged Object Segmentation	CAMO	SAMFusion	MAE	0.0560	#14 of 14	Archive leaderboard	report
Camouflaged Object Segmentation	CAMO	SAMFusion	Weighted F-Measure	0.833	#14 of 14	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.

Methods

Attention Dense Connections Depthwise Convolution Layer Normalization Linear Layer Multi-Head Attention PVTv2 Residual Connection SAM Softmax

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