# Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features

arXiv: https://arxiv.org/abs/1908.06537 · HTML: https://mlsanity.com/paper/1908.06537/

## Key facts

- Cited by 56 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Aug 2019.

## Built on by (most cited first, 30 of 56)

- [Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence](https://mlsanity.com/paper/2305.14334/) (2023)
- [Hypercorrelation Squeeze for Few-Shot Segmentation](https://mlsanity.com/paper/2104.01538/) (2021)
- [Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation](https://mlsanity.com/paper/2207.10866/) (2022)
- [CATs: Cost Aggregation Transformers for Visual Correspondence](https://mlsanity.com/paper/2106.02520/) (2021)
- [Relational Embedding for Few-Shot Classification](https://mlsanity.com/paper/2108.09666/) (2021)
- [GAN-Supervised Dense Visual Alignment](https://mlsanity.com/paper/2112.05143/) (2021)
- [DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision](https://mlsanity.com/paper/2105.06464/) (2021)
- [Deep Hough Voting for Robust Global Registration](https://mlsanity.com/paper/2109.04310/) (2021)
- [CATs++: Boosting Cost Aggregation with Convolutions and Transformers](https://mlsanity.com/paper/2202.06817/) (2022)
- [Convolutional Hough Matching Networks](https://mlsanity.com/paper/2103.16831/) (2021)
- [SD4Match: Learning to Prompt Stable Diffusion Model for Semantic Matching](https://mlsanity.com/paper/2310.17569/) (2023)
- [Multi-scale Matching Networks for Semantic Correspondence](https://mlsanity.com/paper/2108.00211/) (2021)
- [Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence](https://mlsanity.com/paper/2210.02689/) (2022)
- [Input-level Inductive Biases for 3D Reconstruction](https://mlsanity.com/paper/2112.03243/) (2021)
- [Learning Semantic Correspondence with Sparse Annotations](https://mlsanity.com/paper/2208.06974/) (2022)
- [Neural Congealing: Aligning Images to a Joint Semantic Atlas](https://mlsanity.com/paper/2302.03956/) (2023)
- [Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondences](https://mlsanity.com/paper/2203.04279/) (2022)
- [TransforMatcher: Match-to-Match Attention for Semantic Correspondence](https://mlsanity.com/paper/2205.11634/) (2022)
- [ASIC: Aligning Sparse in-the-wild Image Collections](https://mlsanity.com/paper/2303.16201/) (2023)
- [Self-Supervised Equivariant Learning for Oriented Keypoint Detection](https://mlsanity.com/paper/2204.08613/) (2022)
- [Integrative Few-Shot Learning for Classification and Segmentation](https://mlsanity.com/paper/2203.15712/) (2022)
- [Learning Rotation-Equivariant Features for Visual Correspondence](https://mlsanity.com/paper/2303.15472/) (2023)
- [MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentation](https://mlsanity.com/paper/2206.09667/) (2022)
- [Cost Aggregation Is All You Need for Few-Shot Segmentation](https://mlsanity.com/paper/2112.11685/) (2021)
- [Semi-Supervised Learning of Semantic Correspondence with Pseudo-Labels](https://mlsanity.com/paper/2203.16038/) (2022)
- [Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence](https://mlsanity.com/paper/2403.11120/) (2024)
- [MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement](https://mlsanity.com/paper/2509.01977/) (2025)
- [Semantic-Aware Fine-Grained Correspondence](https://mlsanity.com/paper/2207.10456/) (2022)
- [Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondence](https://mlsanity.com/paper/2109.05221/) (2021)
- [Learning Contrastive Representation for Semantic Correspondence](https://mlsanity.com/paper/2109.10967/) (2021)

## Abstract (arXiv)

Establishing visual correspondences under large intra-class variations requires analyzing images at different levels, from features linked to semantics and context to local patterns, while being invariant to instance-specific details. To tackle these challenges, we represent images by "hyperpixels" that leverage a small number of relevant features selected among early to late layers of a convolutional neural network. Taking advantage of the condensed features of hyperpixels, we develop an effective real-time matching algorithm based on Hough geometric voting. The proposed method, hyperpixel flow, sets a new state of the art on three standard benchmarks as well as a new dataset, SPair-71k, which contains a significantly larger number of image pairs than existing datasets, with more accurate and richer annotations for in-depth analysis.