# Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations

arXiv: https://arxiv.org/abs/1611.05113 · HTML: https://mlsanity.com/paper/1611.05113/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Nov 2016.

## Built on by (most cited first, 30 of 50)

- [Hyperbolic Deep Learning in Computer Vision: A Survey](https://mlsanity.com/paper/2305.06611/) (2023)
- [Deep Learning for Instance Retrieval: A Survey](https://mlsanity.com/paper/2101.11282/) (2021)
- [Instance-level Image Retrieval using Reranking Transformers](https://mlsanity.com/paper/2103.12236/) (2021)
- [Part-based Pseudo Label Refinement for Unsupervised Person Re-identification](https://mlsanity.com/paper/2203.14675/) (2022)
- [Learning with Neighbor Consistency for Noisy Labels](https://mlsanity.com/paper/2202.02200/) (2022)
- [DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features](https://mlsanity.com/paper/2108.02927/) (2021)
- [Correlation Verification for Image Retrieval](https://mlsanity.com/paper/2204.01458/) (2022)
- [Label Propagation for Zero-shot Classification with Vision-Language Models](https://mlsanity.com/paper/2404.04072/) (2024)
- [Spectral Geometric Verification: Re-Ranking Point Cloud Retrieval for Metric Localization](https://mlsanity.com/paper/2210.04432/) (2022)
- [LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation](https://mlsanity.com/paper/2503.19777/) (2025)
- [Contrastive Multi-view Hyperbolic Hierarchical Clustering](https://mlsanity.com/paper/2205.02618/) (2022)
- [Boosting vision transformers for image retrieval](https://mlsanity.com/paper/2210.11909/) (2022)
- [Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?](https://mlsanity.com/paper/2309.06891/) (2023)
- [AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-level Retrieval](https://mlsanity.com/paper/2408.03282/) (2024)
- [Contextual Similarity Aggregation with Self-attention for Visual Re-ranking](https://mlsanity.com/paper/2110.13430/) (2021)
- [All the attention you need: Global-local, spatial-channel attention for image retrieval](https://mlsanity.com/paper/2107.08000/) (2021)
- [InsCLR: Improving Instance Retrieval with Self-Supervision](https://mlsanity.com/paper/2112.01390/) (2021)
- [TLDR: Twin Learning for Dimensionality Reduction](https://mlsanity.com/paper/2110.09455/) (2021)
- [Learnable Pillar-based Re-ranking for Image-Text Retrieval](https://mlsanity.com/paper/2304.12570/) (2023)
- [Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model](https://mlsanity.com/paper/2412.18303/) (2024)
- [A Diffusion Weighted Graph Framework for New Intent Discovery](https://mlsanity.com/paper/2310.15836/) (2023)
- [Deep Partial Multi-Label Learning with Graph Disambiguation](https://mlsanity.com/paper/2305.05882/) (2023)
- [Local Propagation for Few-Shot Learning](https://mlsanity.com/paper/2101.01480/) (2021)
- [Evaluating Contrastive Models for Instance-based Image Retrieval](https://mlsanity.com/paper/2104.14939/) (2021)
- [SATTC: Structure-Aware Label-Free Test-Time Calibration for Cross-Subject EEG-to-Image Retrieval](https://mlsanity.com/paper/2603.20738/) (2026)
- [If At First You Don't Succeed: Test Time Re-ranking for Zero-shot, Cross-domain Retrieval](https://mlsanity.com/paper/2303.17703/) (2023)
- [ROGPL: Robust Open-Set Graph Learning via Region-Based Prototype Learning](https://mlsanity.com/paper/2402.18495/) (2024)
- [Get Your Embedding Space in Order: Domain-Adaptive Regression for Forest Monitoring](https://mlsanity.com/paper/2405.00514/) (2024)
- [Towards Accurate Localization by Instance Search](https://mlsanity.com/paper/2107.05005/) (2021)
- [Instance Image Retrieval by Learning Purely From Within the Dataset](https://mlsanity.com/paper/2208.06119/) (2022)

## Abstract (arXiv)

Query expansion is a popular method to improve the quality of image retrieval with both conventional and CNN representations. It has been so far limited to global image similarity. This work focuses on diffusion, a mechanism that captures the image manifold in the feature space. The diffusion is carried out on descriptors of overlapping image regions rather than on a global image descriptor like in previous approaches. An efficient off-line stage allows optional reduction in the number of stored regions. In the on-line stage, the proposed handling of unseen queries in the indexing stage removes additional computation to adjust the precomputed data. We perform diffusion through a sparse linear system solver, yielding practical query times well below one second. Experimentally, we observe a significant boost in performance of image retrieval with compact CNN descriptors on standard benchmarks, especially when the query object covers only a small part of the image. Small objects have been a common failure case of CNN-based retrieval.