# Stable Single-Pixel Contrastive Learning for Semantic and Geometric Tasks

arXiv: https://arxiv.org/abs/2512.04970 · HTML: https://mlsanity.com/paper/2512.04970/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 40 references that are in the map.
- First posted on arXiv 4 Dec 2025.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Vision Transformer Adapter for Dense Predictions](https://mlsanity.com/paper/2205.08534/) (2022)
- [Dense Contrastive Learning for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2011.09157/) (2020)
- [Simple diffusion: End-to-end diffusion for high resolution images](https://mlsanity.com/paper/2301.11093/) (2023)
- [Deep ViT Features as Dense Visual Descriptors](https://mlsanity.com/paper/2112.05814/) (2021)
- [Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/2011.10043/) (2020)
- [Universal Correspondence Network](https://mlsanity.com/paper/1606.03558/) (2016)
- [Semantic Segmentation using Vision Transformers: A survey](https://mlsanity.com/paper/2305.03273/) (2023)
- [A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction](https://mlsanity.com/paper/2207.01223/) (2022)
- [Local Feature Matching Using Deep Learning: A Survey](https://mlsanity.com/paper/2401.17592/) (2024)
- [Location-Aware Self-Supervised Transformers for Semantic Segmentation](https://mlsanity.com/paper/2212.02400/) (2022)
- [Visual question answering: from early developments to recent advances -- a survey](https://mlsanity.com/paper/2501.03939/) (2025)
- [Near, far: Patch-ordering enhances vision foundation models' scene understanding](https://mlsanity.com/paper/2408.11054/) (2024)
- [Exploring Overcomplete Representations for Single Image Deraining using CNNs](https://mlsanity.com/paper/2010.10661/) (2020)
- [From Saliency to DINO: Saliency-guided Vision Transformer for Few-shot Keypoint Detection](https://mlsanity.com/paper/2304.03140/) (2023)
- [Overcomplete Deep Subspace Clustering Networks](https://mlsanity.com/paper/2011.08306/) (2020)
- [A Critical Analysis of Image-based Camera Pose Estimation Techniques](https://mlsanity.com/paper/2201.05816/) (2022)
- [Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization](https://mlsanity.com/paper/2211.15059/) (2022)
- [Aligning Motion-Blurred Images Using Contrastive Learning on Overcomplete Pixels](https://mlsanity.com/paper/2410.07410/) (2024)

## Abstract (arXiv)

We pilot a family of stable contrastive losses for learning pixel-level representations that jointly capture semantic and geometric information. Our approach maps each pixel of an image to an overcomplete descriptor that is both view-invariant and semantically meaningful. It enables precise point-correspondence across images without requiring momentum-based teacher-student training. Two experiments in synthetic 2D and 3D environments demonstrate the properties of our loss and the resulting overcomplete representations.