# Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection

arXiv: https://arxiv.org/abs/2205.03346 · HTML: https://mlsanity.com/paper/2205.03346/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 54 references that are in the map.
- First posted on arXiv 6 May 2022.

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

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [Kindling the Darkness: A Practical Low-light Image Enhancer](https://mlsanity.com/paper/1905.04161/) (2019)
- [Unprocessing Images for Learned Raw Denoising](https://mlsanity.com/paper/1811.11127/) (2018)
- [LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancement](https://mlsanity.com/paper/1511.03995/) (2015)
- [Benchmarking Denoising Algorithms with Real Photographs](https://mlsanity.com/paper/1707.01313/) (2017)
- [Getting to Know Low-light Images with The Exclusively Dark Dataset](https://mlsanity.com/paper/1805.11227/) (2018)
- [UG2+ Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environments](https://mlsanity.com/paper/1904.04474/) (2019)
- [AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations rather than Data](https://mlsanity.com/paper/1901.04596/) (2019)
- [Attention Guided Low-light Image Enhancement with a Large Scale Low-light Simulation Dataset](https://mlsanity.com/paper/1908.00682/) (2019)
- [Handheld Mobile Photography in Very Low Light](https://mlsanity.com/paper/1910.11336/) (2019)
- [MSR-net:Low-light Image Enhancement Using Deep Convolutional Network](https://mlsanity.com/paper/1711.02488/) (2017)
- [RENOIR - A Dataset for Real Low-Light Image Noise Reduction](https://mlsanity.com/paper/1409.8230/) (2014)
- [Regularizing Deep Multi-Task Networks using Orthogonal Gradients](https://mlsanity.com/paper/1912.06844/) (2019)
- [Automatic ISP image quality tuning using non-linear optimization](https://mlsanity.com/paper/1902.09023/) (2019)
- [Exploring Image Enhancement for Salient Object Detection in Low Light Images](https://mlsanity.com/paper/2007.16124/) (2020)
- [Pushing the Limits of Unconstrained Face Detection: a Challenge Dataset and Baseline Results](https://mlsanity.com/paper/1804.10275/) (2018)
- [AVT: Unsupervised Learning of Transformation Equivariant Representations by Autoencoding Variational Transformations](https://mlsanity.com/paper/1903.10863/) (2019)
- [EnAET: A Self-Trained framework for Semi-Supervised and Supervised Learning with Ensemble Transformations](https://mlsanity.com/paper/1911.09265/) (2019)
- [Learning the image processing pipeline](https://mlsanity.com/paper/1605.09336/) (2016)

## Built on by (most cited first, 30 of 59)

- [Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification](https://mlsanity.com/paper/2207.09519/) (2022)
- [You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction](https://mlsanity.com/paper/2205.14871/) (2022)
- [Instance Segmentation in the Dark](https://mlsanity.com/paper/2304.14298/) (2023)
- [Aleth-NeRF: Illumination Adaptive NeRF with Concealing Field Assumption](https://mlsanity.com/paper/2312.09093/) (2023)
- [Light the Night: A Multi-Condition Diffusion Framework for Unpaired Low-Light Enhancement in Autonomous Driving](https://mlsanity.com/paper/2404.04804/) (2024)
- [JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restoration](https://mlsanity.com/paper/2504.04158/) (2025)
- [Bilevel Fast Scene Adaptation for Low-Light Image Enhancement](https://mlsanity.com/paper/2306.01343/) (2023)
- [FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision](https://mlsanity.com/paper/2308.03594/) (2023)
- [RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images](https://mlsanity.com/paper/2408.14802/) (2024)
- [Rawgment: Noise-Accounted RAW Augmentation Enables Recognition in a Wide Variety of Environments](https://mlsanity.com/paper/2210.16046/) (2022)
- [Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation](https://mlsanity.com/paper/2312.01220/) (2023)
- [ODCR: Orthogonal Decoupling Contrastive Regularization for Unpaired Image Dehazing](https://mlsanity.com/paper/2404.17825/) (2024)
- [Noise Self-Regression: A New Learning Paradigm to Enhance Low-Light Images Without Task-Related Data](https://mlsanity.com/paper/2211.04700/) (2022)
- [PE-YOLO: Pyramid Enhancement Network for Dark Object Detection](https://mlsanity.com/paper/2307.10953/) (2023)
- [Learning Degradation-Independent Representations for Camera ISP Pipelines](https://mlsanity.com/paper/2307.00761/) (2023)
- [Similarity Min-Max: Zero-Shot Day-Night Domain Adaptation](https://mlsanity.com/paper/2307.08779/) (2023)
- [Aleth-NeRF: Low-light Condition View Synthesis with Concealing Fields](https://mlsanity.com/paper/2303.05807/) (2023)
- [You Only Look Around: Learning Illumination Invariant Feature for Low-light Object Detection](https://mlsanity.com/paper/2410.18398/) (2024)
- [Fearless Luminance Adaptation: A Macro-Micro-Hierarchical Transformer for Exposure Correction](https://mlsanity.com/paper/2309.00872/) (2023)
- [Exploring Resolution and Degradation Clues as Self-supervised Signal for Low Quality Object Detection](https://mlsanity.com/paper/2208.03062/) (2022)
- [Self-Aligned Concave Curve: Illumination Enhancement for Unsupervised Adaptation](https://mlsanity.com/paper/2210.03792/) (2022)
- [Practical exposure correction via compensation](https://mlsanity.com/paper/2212.14245/) (2022)
- [Dark-ISP: Enhancing RAW Image Processing for Low-Light Object Detection](https://mlsanity.com/paper/2509.09183/) (2025)
- [Blind Multimodal Quality Assessment of Low-light Images](https://mlsanity.com/paper/2303.10369/) (2023)
- [Division Gets Better: Learning Brightness-Aware and Detail-Sensitive Representations for Low-Light Image Enhancement](https://mlsanity.com/paper/2307.09104/) (2023)
- [Understanding Dark Scenes by Contrasting Multi-Modal Observations](https://mlsanity.com/paper/2308.12320/) (2023)
- [Holistic Dynamic Frequency Transformer for Image Fusion and Exposure Correction](https://mlsanity.com/paper/2309.01183/) (2023)
- [Unified-EGformer: Exposure Guided Lightweight Transformer for Mixed-Exposure Image Enhancement](https://mlsanity.com/paper/2407.13170/) (2024)
- [Towards a General-Purpose Zero-Shot Synthetic Low-Light Image and Video Pipeline](https://mlsanity.com/paper/2504.12169/) (2025)
- [From Enhancement to Understanding: Build a Generalized Bridge for Low-light Vision via Semantically Consistent Unsupervised Fine-tuning](https://mlsanity.com/paper/2507.08380/) (2025)

## Abstract (arXiv)

Dark environment becomes a challenge for computer vision algorithms owing to insufficient photons and undesirable noise. To enhance object detection in a dark environment, we propose a novel multitask auto encoding transformation (MAET) model which is able to explore the intrinsic pattern behind illumination translation. In a self-supervision manner, the MAET learns the intrinsic visual structure by encoding and decoding the realistic illumination-degrading transformation considering the physical noise model and image signal processing (ISP). Based on this representation, we achieve the object detection task by decoding the bounding box coordinates and classes. To avoid the over-entanglement of two tasks, our MAET disentangles the object and degrading features by imposing an orthogonal tangent regularity. This forms a parametric manifold along which multitask predictions can be geometrically formulated by maximizing the orthogonality between the tangents along the outputs of respective tasks. Our framework can be implemented based on the mainstream object detection architecture and directly trained end-to-end using normal target detection datasets, such as VOC and COCO. We have achieved the state-of-the-art performance using synthetic and real-world datasets. Code is available at https://github.com/cuiziteng/MAET.