# Region-Based Representations Revisited

arXiv: https://arxiv.org/abs/2402.02352 · HTML: https://mlsanity.com/paper/2402.02352/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 62 references that are in the map.
- First posted on arXiv 4 Feb 2024.

## Builds on (most cited first, 30 of 35)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [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)
- [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)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [EVA: Exploring the Limits of Masked Visual Representation Learning at Scale](https://mlsanity.com/paper/2211.07636/) (2022)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [Vision Transformer Adapter for Dense Predictions](https://mlsanity.com/paper/2205.08534/) (2022)
- [Segment Everything Everywhere All at Once](https://mlsanity.com/paper/2304.06718/) (2023)
- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [Segment Anything in High Quality](https://mlsanity.com/paper/2306.01567/) (2023)
- [Faster Segment Anything: Towards Lightweight SAM for Mobile Applications](https://mlsanity.com/paper/2306.14289/) (2023)
- [Frozen CLIP Models are Efficient Video Learners](https://mlsanity.com/paper/2208.03550/) (2022)
- [AIM: Adapting Image Models for Efficient Video Action Recognition](https://mlsanity.com/paper/2302.03024/) (2023)

## Built on by (most cited first, 18 of 18)

- [Revisit Anything: Visual Place Recognition via Image Segment Retrieval](https://mlsanity.com/paper/2409.18049/) (2024)
- [RELOCATE: A Simple Training-Free Baseline for Visual Query Localization Using Region-Based Representations](https://mlsanity.com/paper/2412.01826/) (2024)
- [Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning](https://mlsanity.com/paper/2410.14633/) (2024)
- [TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models](https://mlsanity.com/paper/2505.23769/) (2025)
- [O-MaMa: Learning Object Mask Matching between Egocentric and Exocentric Views](https://mlsanity.com/paper/2506.06026/) (2025)
- [Tuning-free Universally-Supervised Semantic Segmentation](https://mlsanity.com/paper/2405.14294/) (2024)
- [Search and Detect: Training-Free Long Tail Object Detection via Web-Image Retrieval](https://mlsanity.com/paper/2409.18733/) (2024)
- [REN: Fast and Efficient Region Encodings from Patch-Based Image Encoders](https://mlsanity.com/paper/2505.18153/) (2025)
- [FORLA: Federated Object-centric Representation Learning with Slot Attention](https://mlsanity.com/paper/2506.02964/) (2025)
- [FRAME: Pre-Training Video Feature Representations via Anticipation and Memory](https://mlsanity.com/paper/2506.05543/) (2025)
- [T-REN: Learning Text-Aligned Region Tokens Improves Dense Vision-Language Alignment and Scalability](https://mlsanity.com/paper/2604.18573/) (2026)
- [Experimental Evaluation of Static Image Sub-Region-Based Search Models Using CLIP](https://mlsanity.com/paper/2506.06938/) (2025)
- [Uncertainty-Gated Region-Level Retrieval for Robust Semantic Segmentation](https://mlsanity.com/paper/2512.18082/) (2025)
- [A Study on Real-time Object Detection using Deep Learning](https://mlsanity.com/paper/2602.15926/) (2026)
- [PlanaReLoc: Camera Relocalization in 3D Planar Primitives via Region-Based Structure Matching](https://mlsanity.com/paper/2603.20818/) (2026)
- [Group-DINOmics: Incorporating People Dynamics into DINO for Self-supervised Group Activity Feature Learning](https://mlsanity.com/paper/2604.04467/) (2026)
- [Metric-Guided Feature Fusion of Visual Foundation Models for Segmentation Tasks](https://mlsanity.com/paper/2605.16864/) (2026)
- [PeCA: Palette Context Assisted Inference for Test-Time Paint-Bucket Colourisation on Animation Videos](https://mlsanity.com/paper/2608.00903/) (2026)

## Abstract (arXiv)

We investigate whether region-based representations are effective for recognition. Regions were once a mainstay in recognition approaches, but pixel and patch-based features are now used almost exclusively. We show that recent class-agnostic segmenters like SAM can be effectively combined with strong unsupervised representations like DINOv2 and used for a wide variety of tasks, including semantic segmentation, object-based image retrieval, and multi-image analysis. Once the masks and features are extracted, these representations, even with linear decoders, enable competitive performance, making them well suited to applications that require custom queries. The compactness of the representation also makes it well-suited to video analysis and other problems requiring inference across many images.