paper-with-me

홈 › Papers

Curriculum Self-Paced Learning for Cross-Domain Object Detection

2019-11-15 · Petru Soviany, Radu Tudor Ionescu, Paolo Rota, Nicu Sebe

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.

📄 PDF Abstract BibTeX arXiv:1911.06849

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationObjectobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

RPN A Region Proposal Network, or RPN, is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
RoIPool 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Faster R-CNN Faster R-CNN is an object detection model that improves on Fast R-CNN by utilising a region proposal network…

Similar Papers 제목 키워드 기반

Self Paced Gaussian Contextual Reinforcement Learning

2026-03-24 · Mohsen Sahraei Ardakani, Rui Song arxiv

Curriculum learning improves reinforcement learning (RL) efficiency by sequencing tasks from simple to complex. However, many self-paced curriculum methods rely on computationally expensive inner-loop optimizations, limi…

Reinforcement Learning

SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility

2026-04-09 · Xuyang Zhi, Peilun zhou, Chengqiang Lu, Hang Lv 외 arxiv

The evolution of Large Language Models (LLMs) is shifting the focus from single, verifiable tasks toward complex, open-ended real-world scenarios, imposing significant challenges on the post-training phase. In these sett…

Understanding Self-Paced Learning under Concave Conjugacy Theory

2018-05-21 · Shiqi Liu, Zilu Ma, Deyu Meng

By simulating the easy-to-hard learning manners of humans/animals, the learning regimes called curriculum learning~(CL) and self-paced learning~(SPL) have been recently investigated and invoked broad interests. However, …

Training with Growing Sets: A Simple Alternative to Curriculum Learning and Self Paced Learning

2018-01-01 · ICLR 2018 1 · Melike Nur Mermer, Mehmet Fatih Amasyali

Curriculum learning and Self paced learning are popular topics in the machine learning that suggest to put the training samples in order by considering their difficulty levels. Studies in these topics show that starting …

Reward-Machine-Guided, Self-Paced Reinforcement Learning

2023-05-25 · Cevahir Koprulu, Ufuk Topcu

Self-paced reinforcement learning (RL) aims to improve the data efficiency of learning by automatically creating sequences, namely curricula, of probability distributions over contexts. However, existing techniques for s…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)