# Learning Online Visual Invariances for Novel Objects via Supervised and Self-Supervised Training

arXiv: https://arxiv.org/abs/2110.01476 · HTML: https://mlsanity.com/paper/2110.01476/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 54 references that are in the map.
- First posted on arXiv 4 Oct 2021.

## Builds on (most cited first, 21 of 21)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Group Equivariant Convolutional Networks](https://mlsanity.com/paper/1602.07576/) (2016)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/1902.06162/) (2019)
- [PathNet: Evolution Channels Gradient Descent in Super Neural Networks](https://mlsanity.com/paper/1701.08734/) (2017)
- [Generalisation in humans and deep neural networks](https://mlsanity.com/paper/1808.08750/) (2018)
- [Deep Learning: A Critical Appraisal](https://mlsanity.com/paper/1801.00631/) (2018)
- [Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting](https://mlsanity.com/paper/1802.02950/) (2018)
- [Learning to Continually Learn](https://mlsanity.com/paper/2002.09571/) (2020)
- [Scale-Invariant Convolutional Neural Networks](https://mlsanity.com/paper/1411.6369/) (2014)
- [Multi-scale Orderless Pooling of Deep Convolutional Activation Features](https://mlsanity.com/paper/1403.1840/) (2014)
- [Self-Supervised Relational Reasoning for Representation Learning](https://mlsanity.com/paper/2006.05849/) (2020)
- [Quantifying Translation-Invariance in Convolutional Neural Networks](https://mlsanity.com/paper/1801.01450/) (2017)
- [Learning rotation invariant convolutional filters for texture classification](https://mlsanity.com/paper/1604.06720/) (2016)
- [CyCNN: A Rotation Invariant CNN using Polar Mapping and Cylindrical Convolution Layers](https://mlsanity.com/paper/2007.10588/) (2020)
- [Learning Translation Invariance in CNNs](https://mlsanity.com/paper/2011.11757/) (2020)
- [A case for robust translation tolerance in humans and CNNs. A commentary on Han et al](https://mlsanity.com/paper/2012.05950/) (2020)

## Built on by (most cited first, 10 of 10)

- [Neither hype nor gloom do DNNs justice](https://mlsanity.com/paper/2312.05355/) (2023)
- [Mixed Evidence for Gestalt Grouping in Deep Neural Networks](https://mlsanity.com/paper/2203.07302/) (2022)
- [Improving Fine-tuning of Self-supervised Models with Contrastive Initialization](https://mlsanity.com/paper/2208.00238/) (2022)
- [MindSet: Vision. A toolbox for testing DNNs on key psychological experiments](https://mlsanity.com/paper/2404.05290/) (2024)
- [Approaching human 3D shape perception with neurally mappable models](https://mlsanity.com/paper/2308.11300/) (2023)
- [Divergences in Color Perception between Deep Neural Networks and Humans](https://mlsanity.com/paper/2309.05809/) (2023)
- [Convolutional Neural Networks Trained to Identify Words Provide a Surprisingly Good Account of Visual Form Priming Effects](https://mlsanity.com/paper/2302.03992/) (2023)
- [Beyond the limitations of any imaginable mechanism: large language models and psycholinguistics](https://mlsanity.com/paper/2303.00077/) (2023)
- [Fixing the problems of deep neural networks will require better training data and learning algorithms](https://mlsanity.com/paper/2311.12819/) (2023)
- [GenView++: Unifying Adaptive Generative Augmentation and Quality-Driven Supervision for Contrastive Representation Learning](https://mlsanity.com/paper/2509.23770/) (2025)

## Abstract (arXiv)

Humans can identify objects following various spatial transformations such as scale and viewpoint. This extends to novel objects, after a single presentation at a single pose, sometimes referred to as online invariance. CNNs have been proposed as a compelling model of human vision, but their ability to identify objects across transformations is typically tested on held-out samples of trained categories after extensive data augmentation. This paper assesses whether standard CNNs can support human-like online invariance by training models to recognize images of synthetic 3D objects that undergo several transformations: rotation, scaling, translation, brightness, contrast, and viewpoint. Through the analysis of models' internal representations, we show that standard supervised CNNs trained on transformed objects can acquire strong invariances on novel classes even when trained with as few as 50 objects taken from 10 classes. This extended to a different dataset of photographs of real objects. We also show that these invariances can be acquired in a self-supervised way, through solving the same/different task. We suggest that this latter approach may be similar to how humans acquire invariances.