# Looking Locally: Object-Centric Vision Transformers as Foundation Models for Efficient Segmentation

arXiv: https://arxiv.org/abs/2502.02763 · HTML: https://mlsanity.com/paper/2502.02763/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 36 references that are in the map.
- First posted on arXiv 4 Feb 2025.

## Builds on (most cited first, 30 of 30)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [Deformable ConvNets v2: More Deformable, Better Results](https://mlsanity.com/paper/1811.11168/) (2018)
- [Perceiver IO: A General Architecture for Structured Inputs & Outputs](https://mlsanity.com/paper/2107.14795/) (2021)
- [Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding](https://mlsanity.com/paper/2011.02523/) (2020)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [Faster Segment Anything: Towards Lightweight SAM for Mobile Applications](https://mlsanity.com/paper/2306.14289/) (2023)
- [Vision Transformer with Deformable Attention](https://mlsanity.com/paper/2201.00520/) (2022)
- [TinyViT: Fast Pretraining Distillation for Small Vision Transformers](https://mlsanity.com/paper/2207.10666/) (2022)
- [EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything](https://mlsanity.com/paper/2312.00863/) (2023)
- [SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos](https://mlsanity.com/paper/2206.07764/) (2022)
- [Focal Sparse Convolutional Networks for 3D Object Detection](https://mlsanity.com/paper/2204.12463/) (2022)
- [Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos](https://mlsanity.com/paper/2205.14065/) (2022)
- [Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities](https://mlsanity.com/paper/2306.04829/) (2023)
- [TransNeXt: Robust Foveal Visual Perception for Vision Transformers](https://mlsanity.com/paper/2311.17132/) (2023)
- [Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications](https://mlsanity.com/paper/2401.06197/) (2024)
- [FOVEA: Foveated Image Magnification for Autonomous Navigation](https://mlsanity.com/paper/2108.12102/) (2021)
- [Learning What and Where: Disentangling Location and Identity Tracking Without Supervision](https://mlsanity.com/paper/2205.13349/) (2022)
- [Transformer Normalisation Layers and the Independence of Semantic Subspaces](https://mlsanity.com/paper/2406.17837/) (2024)
- [Learning Object Permanence from Videos via Latent Imaginations](https://mlsanity.com/paper/2310.10372/) (2023)
- [Loci-Segmented: Improving Scene Segmentation Learning](https://mlsanity.com/paper/2310.10410/) (2023)

## Built on by (most cited first, 2 of 2)

- [Self-supervised pretraining for an iterative image size agnostic vision transformer](https://mlsanity.com/paper/2604.20392/) (2026)
- [Semantic Allocation in Ordered Bottlenecks: Predictive Residual Inference for Visual Representation Learning](https://mlsanity.com/paper/2606.25232/) (2026)

## Abstract (arXiv)

Current state-of-the-art segmentation models encode entire images before focusing on specific objects. This wastes computational resources. We introduce FLIP (Fovea-Like Input Patching), a parameter-efficient vision model that realizes object segmentation through biologically-inspired top-down attention. FLIP selectively samples multi-resolution patches centered on objects of interest from the input. As a result, it allocates high-resolution processing to object centers while maintaining coarser peripheral context. This off-grid, scale-invariant design enables FLIP to outperform META's Segment Anything models (SAM, SAM2 and fast variants) by large margins: With more than 440× fewer parameters, FLIP-Tiny (0.51M parameters) reaches a mean IoU of 79.90% while SAM2-L reaches 75.87% IoU (224.45M parameters). FLIP-Large even achieves 83.26% mean IoU (96.6M parameters), still running about 2× faster than SAM2-L. We evaluate on six benchmarks in total. In five established benchmarks (Hypersim, KITTI-360, OpenImages, COCO, LVIS) FLIP consistently outperforms SAM and various variants of it. In our novel ObjaScale dataset, which stress-tests scale invariance with objects ranging from 0.0001% up to 25% of the image area, we show that FLIP segments even very small objects accurately, where existing models fail severely. FLIP opens new possibilities for real-time, object-centric vision and offers much higher energy efficiency. We believe that FLIP can act as a powerful foundation model, as it is very well-suited to track objects over time, for example, when being integrated into slot-based scene segmentation architectures.