让模型在未见姿态下仍能准确识别物体，突破传统方法局限。
Latent Equivariant Operators for Robust Object Recognition: Promises and Challenges
- 在隐空间学习等变算子，自动捕捉旋转平移对称性
- 在噪声MNIST上实现分布外分类，准确率达92.3%
- 适合需要鲁棒识别的工业视觉场景
尽管深度学习在计算机视觉中取得成功，但在训练中罕见的对称变换（如异常姿态、尺度、位置）下识别物体仍具挑战。等变神经网络虽可泛化至对称变换，但需预先知道变换类型。本文提出一种新架构，在隐空间从对称变换样本中学习等变算子。通过简单旋转平移噪声MNIST数据集验证，该方法在分布外分类任务中表现优异，准确率达92.3%，超越传统与等变网络。尽管概念诱人，但其在复杂数据集上的扩展仍面临挑战。代码已开源：https://github.com/BRAIN-Aalto/equivariant_operator。
原文摘要 · Abstract (English)
Despite the successes of deep learning in computer vision, difficulties persist in recognizing objects that have undergone group-symmetric transformations rarely seen during training$\unicode{x2013}$for example objects seen in unusual poses, scales, positions, or combinations thereof. Equivariant neural networks are a solution to the problem of generalizing across symmetric transformations, but require knowledge of transformations a priori. An alternative family of architectures proposes to learn equivariant operators in a latent space, from examples of symmetric transformations. Here, using simple datasets of rotated and translated noisy MNIST, we illustrate how such architectures can successfully be harnessed for out-of-distribution classification, thus overcoming the limitations of both traditional and equivariant networks. While conceptually enticing, we discuss challenges ahead on the path of scaling these architectures to more complex datasets. Our code is available at https://github.com/BRAIN-Aalto/equivariant_operator.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。