# Self-Supervised Learning Based on Transformed Image Reconstruction for Equivariance-Coherent Feature Representation

arXiv: https://arxiv.org/abs/2503.18753 · HTML: https://mlsanity.com/paper/2503.18753/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 51 references that are in the map.
- First posted on arXiv 24 Mar 2025.

## Builds on (most cited first, 30 of 35)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [Deep Learning in Neural Networks: An Overview](https://mlsanity.com/paper/1404.7828/) (2014)
- [ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth](https://mlsanity.com/paper/2302.12288/) (2023)
- [Steerable CNNs](https://mlsanity.com/paper/1612.08498/) (2016)
- [What Should Not Be Contrastive in Contrastive Learning](https://mlsanity.com/paper/2008.05659/) (2020)
- [Deep Image Homography Estimation](https://mlsanity.com/paper/1606.03798/) (2016)
- [Contrastive Masked Autoencoders are Stronger Vision Learners](https://mlsanity.com/paper/2207.13532/) (2022)
- [Equivariant Contrastive Learning](https://mlsanity.com/paper/2111.00899/) (2021)
- [Learning Symmetric Embeddings for Equivariant World Models](https://mlsanity.com/paper/2204.11371/) (2022)
- [Self-supervised learning of Split Invariant Equivariant representations](https://mlsanity.com/paper/2302.10283/) (2023)
- [AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders](https://mlsanity.com/paper/2211.09120/) (2022)
- [Adaptive Temporal Encoding Network for Video Instance-level Human Parsing](https://mlsanity.com/paper/1808.00661/) (2018)
- [Structuring Representation Geometry with Rotationally Equivariant Contrastive Learning](https://mlsanity.com/paper/2306.13924/) (2023)
- [Steerable Partial Differential Operators for Equivariant Neural Networks](https://mlsanity.com/paper/2106.10163/) (2021)

## Built on by (most cited first, 1 of 1)

- [Learning Group Actions In Disentangled Latent Image Representations](https://mlsanity.com/paper/2512.04015/) (2025)

## Abstract (arXiv)

Self-supervised learning (SSL) methods have achieved remarkable success in learning image representations allowing invariances in them - but therefore discarding transformation information that some computer vision tasks actually require. While recent approaches attempt to address this limitation by learning equivariant features using linear operators in feature space, they impose restrictive assumptions that constrain flexibility and generalization. We introduce a weaker definition for the transformation relation between image and feature space denoted as equivariance-coherence. We propose a novel SSL auxiliary task that learns equivariance-coherent representations through intermediate transformation reconstruction, which can be integrated with existing joint embedding SSL methods. Our key idea is to reconstruct images at intermediate points along transformation paths, e.g. when training on 30-degree rotations, we reconstruct the 10-degree and 20-degree rotation states. Reconstructing intermediate states requires the transformation information used in augmentations, rather than suppressing it, and therefore fosters features containing the augmented transformation information. Our method decomposes feature vectors into invariant and equivariant parts, training them with standard SSL losses and reconstruction losses, respectively. We demonstrate substantial improvements on synthetic equivariance benchmarks while maintaining competitive performance on downstream tasks requiring invariant representations. The approach seamlessly integrates with existing SSL methods (iBOT, DINOv2) and consistently enhances performance across diverse tasks, including segmentation, detection, depth estimation, and video dense prediction. Our framework provides a practical way for augmenting SSL methods with equivariant capabilities while preserving invariant performance.