paper-with-me

홈 › Papers

Spatial Transformer Networks for Curriculum Learning

2021-08-22 · Fatemeh Azimi, Jean-Francois Jacques Nicolas Nies, Sebastian Palacio, Federico Raue, Jörn Hees, Andreas Dengel

Curriculum learning is a bio-inspired training technique that is widely adopted to machine learning for improved optimization and better training of neural networks regarding the convergence rate or obtained accuracy. The main concept in curriculum learning is to start the training with simpler tasks and gradually increase the level of difficulty. Therefore, a natural question is how to determine or generate these simpler tasks. In this work, we take inspiration from Spatial Transformer Networks (STNs) in order to form an easy-to-hard curriculum. As STNs have been proven to be capable of removing the clutter from the input images and obtaining higher accuracy in image classification tasks, we hypothesize that images processed by STNs can be seen as easier tasks and utilized in the interest of curriculum learning. To this end, we study multiple strategies developed for shaping the training curriculum, using the data generated by STNs. We perform various experiments on cluttered MNIST and Fashion-MNIST datasets, where on the former, we obtain an improvement of $3.8$pp in classification accuracy compared to the baseline.

📄 PDF Abstract BibTeX arXiv:2108.09696

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classification

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Adam 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

Spatial-Temporal Transformer with Curriculum Learning for EEG-Based Emotion Recognition

2025-07-19 · Xuetao Lin, Tianhao Peng, Peihong Dai, Yu Liang 외 arxiv

EEG-based emotion recognition plays an important role in developing adaptive brain-computer communication systems, yet faces two fundamental challenges in practical implementations: (1) effective integration of non-stati…

Emotion Recognition

Dual Graph Convolutional Networks with Transformer and Curriculum Learning for Image Captioning

2021-08-05 · Xinzhi Dong, Chengjiang Long, Wenju Xu, Chunxia Xiao

Existing image captioning methods just focus on understanding the relationship between objects or instances in a single image, without exploring the contextual correlation existed among contextual image. In this paper, w…

Image CaptioningObject

Cross-Episodic Curriculum for Transformer Agents

2023-10-12 · NeurIPS 2023 11

We present a new algorithm, Cross-Episodic Curriculum (CEC), to boost the learning efficiency and generalization of Transformer agents. Central to CEC is the placement of cross-episodic experiences into a Transformer's c…

continuous-controlContinuous ControlImitation Learning

TransCurriculum: Multi-Dimensional Curriculum Learning for Fast & Stable Locomotion

2026-03-14 · Prakhar Mishra, Amir Hossain Raj, Xuesu Xiao, Dinesh Manocha arxiv

High-speed legged locomotion struggles with stability and transfer losses at higher command velocities during deployment. One reason is that most curricula vary difficulty along single axis, for example increase the rang…

Curriculum Learning of Physics-Informed Neural Networks based on Spatial Correlation

2026-05-14 · Xujia Chen, Xinyue Hu, Letian Chen, Daming Shi 외 arxiv

Physics-Informed Neural Networks (PINNs) combine deep learning with physical constraints for solving partial differential equations (PDEs), and are widely applied in fluid mechanics, heat transfer, and solid mechanics. H…