# Towards Few-Annotation Learning in Computer Vision: Application to Image Classification and Object Detection tasks

arXiv: https://arxiv.org/abs/2311.04888 · HTML: https://mlsanity.com/paper/2311.04888/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 280 references that are in the map.
- First posted on arXiv 8 Nov 2023.

## Builds on (most cited first, 25 of 25)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Neural Turing Machines](https://mlsanity.com/paper/1410.5401/) (2014)
- [Meta-SGD: Learning to Learn Quickly for Few-Shot Learning](https://mlsanity.com/paper/1707.09835/) (2017)
- [A Simple Semi-Supervised Learning Framework for Object Detection](https://mlsanity.com/paper/2005.04757/) (2020)
- [Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model](https://mlsanity.com/paper/2211.02001/) (2022)
- [A Survey on Deep Semi-supervised Learning](https://mlsanity.com/paper/2103.00550/) (2021)
- [Few-Shot Learning via Learning the Representation, Provably](https://mlsanity.com/paper/2002.09434/) (2020)
- [SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning](https://mlsanity.com/paper/1911.04623/) (2019)
- [Provable Meta-Learning of Linear Representations](https://mlsanity.com/paper/2002.11684/) (2020)
- [Dataset Augmentation in Feature Space](https://mlsanity.com/paper/1702.05538/) (2017)
- [Data Augmentation by Pairing Samples for Images Classification](https://mlsanity.com/paper/1801.02929/) (2018)
- [Are all negatives created equal in contrastive instance discrimination?](https://mlsanity.com/paper/2010.06682/) (2020)
- [A Survey of Self-Supervised and Few-Shot Object Detection](https://mlsanity.com/paper/2110.14711/) (2021)
- [Anchor DETR: Query Design for Transformer-Based Object Detection](https://mlsanity.com/paper/2109.07107/) (2021)
- [Revisiting Fine-tuning for Few-shot Learning](https://mlsanity.com/paper/1910.00216/) (2019)
- [Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutes](https://mlsanity.com/paper/1711.04325/) (2017)
- [How to Train Your MAML to Excel in Few-Shot Classification](https://mlsanity.com/paper/2106.16245/) (2021)

## Abstract (arXiv)

In this thesis, we develop theoretical, algorithmic and experimental contributions for Machine Learning with limited labels, and more specifically for the tasks of Image Classification and Object Detection in Computer Vision. In a first contribution, we are interested in bridging the gap between theory and practice for popular Meta-Learning algorithms used in Few-Shot Classification. We make connections to Multi-Task Representation Learning, which benefits from solid theoretical foundations, to verify the best conditions for a more efficient meta-learning. Then, to leverage unlabeled data when training object detectors based on the Transformer architecture, we propose both an unsupervised pretraining and a semi-supervised learning method in two other separate contributions. For pretraining, we improve Contrastive Learning for object detectors by introducing the localization information. Finally, our semi-supervised method is the first tailored to transformer-based detectors.