Curriculum for Crowd Counting -- Is it Worthy?
Not on the map. Why?
Abstract (arXiv)
Recent advances in deep learning techniques have achieved remarkable performance in several computer vision problems. A notably intuitive technique called Curriculum Learning (CL) has been introduced recently for training deep learning models. Surprisingly, curriculum learning achieves significantly improved results in some tasks but marginal or no improvement in others. Hence, there is still a debate about its adoption as a standard method to train supervised learning models. In this work, we investigate the impact of curriculum learning in crowd counting using the density estimation method. We performed detailed investigations by conducting 112 experiments using six different CL settings using eight different crowd models. Our experiments show that curriculum learning improves the model learning performance and shortens the convergence time.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 30 of its 48 references that are in the map. First posted on arXiv 15 Jan 2024.
Builds on
30 of 48 references.
References · 30
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
- 2014Going Deeper with Convolutionscited by 4,231
- 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 350
- 2018CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenescited by 267
- 2019Competence-based Curriculum Learning for Neural Machine Translationcited by 201
- 2018Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowdscited by 186
- 2019Bayesian Loss for Crowd Count Estimation with Point Supervisioncited by 162
- 2020When Do Curricula Work?cited by 105
- 2015Webly Supervised Learning of Convolutional Networkscited by 95
- 2017Curriculum Learning and Minibatch Bucketing in Neural Machine Translationcited by 63
18 more
- 2019Crowd Counting and Density Estimation by Trellis Encoder-Decoder Networkcited by 56
- 2016CrowdNet: A Deep Convolutional Network for Dense Crowd Countingcited by 52
- 2017How hard can it be? Estimating the difficulty of visual search in an imagecited by 52
- 2017CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Countingcited by 41
- 2018Attention-Guided Curriculum Learning for Weakly Supervised Classification and Localization of Thoracic Diseases on Chest Radiographscited by 32
- 2019Locality-constrained Spatial Transformer Network for Video Crowd Countingcited by 30
- 2017Multi-scale Convolutional Neural Networks for Crowd Countingcited by 26
- 2016Self Paced Deep Learning for Weakly Supervised Object Detectioncited by 25
- 2020Pixel-wise Crowd Understanding via Synthetic Datacited by 23
- 2019Dynamically Composing Domain-Data Selection with Clean-Data Selection by "Co-Curricular Learning" for Neural Machine Translationcited by 20
- 2016Weakly Supervised Object Localization Using Size Estimatescited by 16
- 2022Revisiting Crowd Counting: State-of-the-art, Trends, and Future Perspectivescited by 16
- 2017Multiple Instance Curriculum Learning for Weakly Supervised Object Detectioncited by 13
- 2020A Real-Time Deep Network for Crowd Countingcited by 7
- 2023LCDnet: A Lightweight Crowd Density Estimation Model for Real-time Video Surveillancecited by 6
- 2020Learning Error-Driven Curriculum for Crowd Countingcited by 5
- 2022A Unified Multi-Task Learning Framework of Real-Time Drone Supervision for Crowd Countingcited by 5
- 2022CLIP: Train Faster with Less Datacited by 4
Built on by
Citing papers per year: 2024: 1.
1 paper.
- 2024Accelerating Deep Learning with Fixed Time Budgetcited by 0
- 2024Accelerating Deep Learning with Fixed Time Budget3 Oct 2024