# Local Features and Visual Words Emerge in Activations

arXiv: https://arxiv.org/abs/1905.06358 · HTML: https://mlsanity.com/paper/1905.06358/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 May 2019.

## Built on by (most cited first, 30 of 37)

- [Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation](https://mlsanity.com/paper/2107.03358/) (2021)
- [TransVPR: Transformer-based place recognition with multi-level attention aggregation](https://mlsanity.com/paper/2201.02001/) (2022)
- [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)
- [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)
- [The 2021 Image Similarity Dataset and Challenge](https://mlsanity.com/paper/2106.09672/) (2021)
- [Global Features are All You Need for Image Retrieval and Reranking](https://mlsanity.com/paper/2308.06954/) (2023)
- [AlignMixup: Improving Representations By Interpolating Aligned Features](https://mlsanity.com/paper/2103.15375/) (2021)
- [Image Clustering Conditioned on Text Criteria](https://mlsanity.com/paper/2310.18297/) (2023)
- [NinjaDesc: Content-Concealing Visual Descriptors via Adversarial Learning](https://mlsanity.com/paper/2112.12785/) (2021)
- [Boosting vision transformers for image retrieval](https://mlsanity.com/paper/2210.11909/) (2022)
- [IRGen: Generative Modeling for Image Retrieval](https://mlsanity.com/paper/2303.10126/) (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)
- [Graph Convolution Based Efficient Re-Ranking for Visual Retrieval](https://mlsanity.com/paper/2306.08792/) (2023)
- [Let All be Whitened: Multi-teacher Distillation for Efficient Visual Retrieval](https://mlsanity.com/paper/2312.09716/) (2023)
- [DALG: Deep Attentive Local and Global Modeling for Image Retrieval](https://mlsanity.com/paper/2207.00287/) (2022)
- [A Light Touch Approach to Teaching Transformers Multi-view Geometry](https://mlsanity.com/paper/2211.15107/) (2022)
- [LOCORE: Image Re-ranking with Long-Context Sequence Modeling](https://mlsanity.com/paper/2503.21772/) (2025)
- [Multi-Head Deep Metric Learning Using Global and Local Representations](https://mlsanity.com/paper/2112.14327/) (2021)
- [Yes, we CANN: Constrained Approximate Nearest Neighbors for local feature-based visual localization](https://mlsanity.com/paper/2306.09012/) (2023)
- [Coarse-to-Fine: Learning Compact Discriminative Representation for Single-Stage Image Retrieval](https://mlsanity.com/paper/2308.04008/) (2023)
- [On Train-Test Class Overlap and Detection for Image Retrieval](https://mlsanity.com/paper/2404.01524/) (2024)
- [StructVPR++: Distill Structural and Semantic Knowledge with Weighting Samples for Visual Place Recognition](https://mlsanity.com/paper/2503.06601/) (2025)
- [Asymmetric Image Retrieval with Cross Model Compatible Ensembles](https://mlsanity.com/paper/2303.17531/) (2023)
- [STIR: Siamese Transformer for Image Retrieval Postprocessing](https://mlsanity.com/paper/2304.13393/) (2023)
- [Structure Similarity Preservation Learning for Asymmetric Image Retrieval](https://mlsanity.com/paper/2403.00648/) (2024)

## Abstract (arXiv)

We propose a novel method of deep spatial matching (DSM) for image retrieval. Initial ranking is based on image descriptors extracted from convolutional neural network activations by global pooling, as in recent state-of-the-art work. However, the same sparse 3D activation tensor is also approximated by a collection of local features. These local features are then robustly matched to approximate the optimal alignment of the tensors. This happens without any network modification, additional layers or training. No local feature detection happens on the original image. No local feature descriptors and no visual vocabulary are needed throughout the whole process. We experimentally show that the proposed method achieves the state-of-the-art performance on standard benchmarks across different network architectures and different global pooling methods. The highest gain in performance is achieved when diffusion on the nearest-neighbor graph of global descriptors is initiated from spatially verified images.