# AnchorNet: A Weakly Supervised Network to Learn Geometry-sensitive Features For Semantic Matching

arXiv: https://arxiv.org/abs/1704.04749 · HTML: https://mlsanity.com/paper/1704.04749/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Apr 2017.

## Built on by (most cited first, 13 of 13)

- [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)
- [The Functional Correspondence Problem](https://mlsanity.com/paper/2109.01097/) (2021)
- [Learning Part Segmentation through Unsupervised Domain Adaptation from Synthetic Vehicles](https://mlsanity.com/paper/2103.14098/) (2021)
- [Do It Yourself: Learning Semantic Correspondence from Pseudo-Labels](https://mlsanity.com/paper/2506.05312/) (2025)
- [Learning Contrastive Representation for Semantic Correspondence](https://mlsanity.com/paper/2109.10967/) (2021)
- [GECO: Geometrically Consistent Embedding with Lightspeed Inference](https://mlsanity.com/paper/2508.00746/) (2025)
- [Locality-aware Channel-wise Dropout for Occluded Face Recognition](https://mlsanity.com/paper/2107.09270/) (2021)
- [Weakly Supervised Keypoint Discovery](https://mlsanity.com/paper/2109.13423/) (2021)
- [Learning to Focus: Cascaded Feature Matching Network for Few-shot Image Recognition](https://mlsanity.com/paper/2101.05018/) (2021)
- [Towards Geometry-Grounded Dense Semantic Matching with VGGT Priors](https://mlsanity.com/paper/2509.21263/) (2025)
- [PartCo: Part-Level Correspondence Priors Enhance Category Discovery](https://mlsanity.com/paper/2509.22769/) (2025)
- [LMPNet for Weakly-supervised Keypoint Discovery](https://mlsanity.com/paper/2507.02308/) (2025)

## Abstract (arXiv)

Despite significant progress of deep learning in recent years, state-of-the-art semantic matching methods still rely on legacy features such as SIFT or HoG. We argue that the strong invariance properties that are key to the success of recent deep architectures on the classification task make them unfit for dense correspondence tasks, unless a large amount of supervision is used. In this work, we propose a deep network, termed AnchorNet, that produces image representations that are well-suited for semantic matching. It relies on a set of filters whose response is geometrically consistent across different object instances, even in the presence of strong intra-class, scale, or viewpoint variations. Trained only with weak image-level labels, the final representation successfully captures information about the object structure and improves results of state-of-the-art semantic matching methods such as the deformable spatial pyramid or the proposal flow methods. We show positive results on the cross-instance matching task where different instances of the same object category are matched as well as on a new cross-category semantic matching task aligning pairs of instances each from a different object class.