# Curriculum Self-Paced Learning for Cross-Domain Object Detection

arXiv: https://arxiv.org/abs/1911.06849 · HTML: https://mlsanity.com/paper/1911.06849/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Nov 2019.

## Built on by (most cited first, 30 of 39)

- [Curriculum Learning: A Survey](https://mlsanity.com/paper/2101.10382/) (2021)
- [Cross-Domain Adaptive Teacher for Object Detection](https://mlsanity.com/paper/2111.13216/) (2021)
- [Unsupervised Domain Adaptation of Object Detectors: A Survey](https://mlsanity.com/paper/2105.13502/) (2021)
- [How Simulation Helps Autonomous Driving:A Survey of Sim2real, Digital Twins, and Parallel Intelligence](https://mlsanity.com/paper/2305.01263/) (2023)
- [Curriculum Direct Preference Optimization for Diffusion and Consistency Models](https://mlsanity.com/paper/2405.13637/) (2024)
- [Deep Spatially and Temporally Aware Similarity Computation for Road Network Constrained Trajectories](https://mlsanity.com/paper/2112.09339/) (2021)
- [Boost Your Human Image Generation Model via Direct Preference Optimization](https://mlsanity.com/paper/2405.20216/) (2024)
- [Enhancing Source-Free Domain Adaptive Object Detection with Low-confidence Pseudo Label Distillation](https://mlsanity.com/paper/2407.13524/) (2024)
- [Curricular Object Manipulation in LiDAR-based Object Detection](https://mlsanity.com/paper/2304.04248/) (2023)
- [Self-paced ensemble learning for speech and audio classification](https://mlsanity.com/paper/2103.11988/) (2021)
- [Learning Rate Curriculum](https://mlsanity.com/paper/2205.09180/) (2022)
- [Learning to Learn: How to Continuously Teach Humans and Machines](https://mlsanity.com/paper/2211.15470/) (2022)
- [RecRecNet: Rectangling Rectified Wide-Angle Images by Thin-Plate Spline Model and DoF-based Curriculum Learning](https://mlsanity.com/paper/2301.01661/) (2023)
- [Effective Pseudo-Labeling based on Heatmap for Unsupervised Domain Adaptation in Cell Detection](https://mlsanity.com/paper/2303.05269/) (2023)
- [Reverse Stable Diffusion: What prompt was used to generate this image?](https://mlsanity.com/paper/2308.01472/) (2023)
- [Curriculum Learning with Quality-Driven Data Selection](https://mlsanity.com/paper/2407.00102/) (2024)
- [Approaching Outside: Scaling Unsupervised 3D Object Detection from 2D Scene](https://mlsanity.com/paper/2407.08569/) (2024)
- [Say No to Freeloader: Protecting Intellectual Property of Your Deep Model](https://mlsanity.com/paper/2408.13161/) (2024)
- [A Psychology-based Unified Dynamic Framework for Curriculum Learning](https://mlsanity.com/paper/2408.05326/) (2024)
- [Detect, Augment, Compose, and Adapt: Four Steps for Unsupervised Domain Adaptation in Object Detection](https://mlsanity.com/paper/2308.15353/) (2023)
- [Domain Adaptive Detection of MAVs: A Benchmark and Noise Suppression Network](https://mlsanity.com/paper/2403.16669/) (2024)
- [CBM: Curriculum by Masking](https://mlsanity.com/paper/2407.05193/) (2024)
- [Cross-Region Building Counting in Satellite Imagery using Counting Consistency](https://mlsanity.com/paper/2110.13558/) (2021)
- [AWADA: Attention-Weighted Adversarial Domain Adaptation for Object Detection](https://mlsanity.com/paper/2208.14662/) (2022)
- [iQPP: A Benchmark for Image Query Performance Prediction](https://mlsanity.com/paper/2302.10126/) (2023)
- [Are Dense Labels Always Necessary for 3D Object Detection from Point Cloud?](https://mlsanity.com/paper/2403.02818/) (2024)
- [MambaNUT: Nighttime UAV Tracking via Mamba-based Adaptive Curriculum Learning](https://mlsanity.com/paper/2412.00626/) (2024)
- [ERNetCL: A novel emotion recognition network in textual conversation based on curriculum learning strategy](https://mlsanity.com/paper/2308.06450/) (2023)
- [Dynamic Task and Weight Prioritization Curriculum Learning for Multimodal Imagery](https://mlsanity.com/paper/2310.19109/) (2023)
- [Does YOLO Really Need to See Every Training Image in Every Epoch?](https://mlsanity.com/paper/2603.17684/) (2026)

## Abstract (arXiv)

Training (source) domain bias affects state-of-the-art object detectors, such as Faster R-CNN, when applied to new (target) domains. To alleviate this problem, researchers proposed various domain adaptation methods to improve object detection results in the cross-domain setting, e.g. by translating images with ground-truth labels from the source domain to the target domain using Cycle-GAN. On top of combining Cycle-GAN transformations and self-paced learning in a smart and efficient way, in this paper, we propose a novel self-paced algorithm that learns from easy to hard. Our method is simple and effective, without any overhead during inference. It uses only pseudo-labels for samples taken from the target domain, i.e. the domain adaptation is unsupervised. We conduct experiments on four cross-domain benchmarks, showing better results than the state of the art. We also perform an ablation study demonstrating the utility of each component in our framework. Additionally, we study the applicability of our framework to other object detectors. Furthermore, we compare our difficulty measure with other measures from the related literature, proving that it yields superior results and that it correlates well with the performance metric.