# BLO-Inst: Bi-Level Optimization Based Alignment of YOLO and SAM for Robust Instance Segmentation

arXiv: https://arxiv.org/abs/2601.22061 · HTML: https://mlsanity.com/paper/2601.22061/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 44 references that are in the map.
- First posted on arXiv 29 Jan 2026.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [YOLO-World: Real-Time Open-Vocabulary Object Detection](https://mlsanity.com/paper/2401.17270/) (2024)
- [Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation](https://mlsanity.com/paper/2304.12620/) (2023)
- [Customized Segment Anything Model for Medical Image Segmentation](https://mlsanity.com/paper/2304.13785/) (2023)
- [RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation Model](https://mlsanity.com/paper/2306.16269/) (2023)
- [On the Iteration Complexity of Hypergradient Computation](https://mlsanity.com/paper/2006.16218/) (2020)
- [Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond](https://mlsanity.com/paper/2101.11517/) (2021)
- [Temporal RoI Align for Video Object Recognition](https://mlsanity.com/paper/2109.03495/) (2021)
- [Collaborating Foundation Models for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2312.09788/) (2023)
- [Diving into Underwater: Segment Anything Model Guided Underwater Salient Instance Segmentation and A Large-scale Dataset](https://mlsanity.com/paper/2406.06039/) (2024)
- [SOLO: A Simple Framework for Instance Segmentation](https://mlsanity.com/paper/2106.15947/) (2021)
- [A General Descent Aggregation Framework for Gradient-based Bi-level Optimization](https://mlsanity.com/paper/2102.07976/) (2021)
- [Betty: An Automatic Differentiation Library for Multilevel Optimization](https://mlsanity.com/paper/2207.02849/) (2022)
- [AutoProSAM: Automated Prompting SAM for 3D Multi-Organ Segmentation](https://mlsanity.com/paper/2308.14936/) (2023)
- [Generalized Data Weighting via Class-level Gradient Manipulation](https://mlsanity.com/paper/2111.00056/) (2021)
- [A Stochastic Approach to Bi-Level Optimization for Hyperparameter Optimization and Meta Learning](https://mlsanity.com/paper/2410.10417/) (2024)

## Abstract (arXiv)

The Segment Anything Model has revolutionized image segmentation with its zero-shot capabilities, yet its reliance on manual prompts hinders fully automated deployment. While integrating object detectors as prompt generators offers a pathway to automation, existing pipelines suffer from two fundamental limitations: objective mismatch, where detectors optimized for geometric localization do not correspond to the optimal prompting context required by SAM, and alignment overfitting in standard joint training, where the detector simply memorizes specific prompt adjustments for training samples rather than learning a generalizable policy. To bridge this gap, we introduce BLO-Inst, a unified framework that aligns detection and segmentation objectives by bi-level optimization. We formulate the alignment as a nested optimization problem over disjoint data splits. In the lower level, the SAM is fine-tuned to maximize segmentation fidelity given the current detection proposals on a subset (D1). In the upper level, the detector is updated to generate bounding boxes that explicitly minimize the validation loss of the fine-tuned SAM on a separate subset (D2). This effectively transforms the detector into a segmentation-aware prompt generator, optimizing the bounding boxes not just for localization accuracy, but for downstream mask quality. Extensive experiments demonstrate that BLO-Inst achieves superior performance, outperforming standard baselines on tasks in general and biomedical domains.