# Seeing Objects in dark with Continual Contrastive Learning

arXiv: https://arxiv.org/abs/2112.02891 · HTML: https://mlsanity.com/paper/2112.02891/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 6 Dec 2021.

## Builds on (most cited first, 22 of 22)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [Unsupervised Image-to-Image Translation Networks](https://mlsanity.com/paper/1703.00848/) (2017)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [Kindling the Darkness: A Practical Low-light Image Enhancer](https://mlsanity.com/paper/1905.04161/) (2019)
- [Scaled-YOLOv4: Scaling Cross Stage Partial Network](https://mlsanity.com/paper/2011.08036/) (2020)
- [Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation](https://mlsanity.com/paper/2103.00860/) (2021)
- [You Only Look One-level Feature](https://mlsanity.com/paper/2103.09460/) (2021)
- [You Only Learn One Representation: Unified Network for Multiple Tasks](https://mlsanity.com/paper/2105.04206/) (2021)
- [Night-to-Day Image Translation for Retrieval-based Localization](https://mlsanity.com/paper/1809.09767/) (2018)
- [Cross-Domain Car Detection Using Unsupervised Image-to-Image Translation: From Day to Night](https://mlsanity.com/paper/1907.08719/) (2019)
- [CoMoGAN: continuous model-guided image-to-image translation](https://mlsanity.com/paper/2103.06879/) (2021)

## Built on by (most cited first, 2 of 2)

- [S2ST: Image-to-Image Translation in the Seed Space of Latent Diffusion](https://mlsanity.com/paper/2312.00116/) (2023)
- [Seed-to-Seed: Unpaired Image Translation in Diffusion Seed Space](https://mlsanity.com/paper/2409.00654/) (2024)

## Abstract (arXiv)

Object Detection, a fundamental computer vision problem, has paramount importance in smart camera systems. However, a truly reliable camera system could be achieved if and only if the underlying object detection component is robust enough across varying imaging conditions (or domains), for instance, different times of the day, adverse weather conditions, etc. In an effort to achieving a reliable camera system, in this paper, we make an attempt to train such a robust detector. Unfortunately, to build a well-performing detector across varying imaging conditions, one would require labeled training images (often in large numbers) from a plethora of corner cases. As manually obtaining such a large labeled dataset may be infeasible, we suggest using synthetic images, to mimic different training image domains. We propose a novel, contrastive learning method to align the latent representations of a pair of real and synthetic images, to make the detector robust to the different domains. However, we found that merely contrasting the embeddings may lead to catastrophic forgetting of the information essential for object detection. Hence, we employ a continual learning based penalty, to alleviate the issue of forgetting, while contrasting the representations. We showcase that our proposed method outperforms a wide range of alternatives to address the extremely challenging, yet under-studied scenario of object detection at night-time.