More Like this

1. Random Feature Amplification: Feature Learning and Generalization in Neural Networks

   Frei, Spencer; Chatterji, Niladri S; Bartlett, Peter L (August 2023, Journal of machine learning research)
2. Fed2: Feature-Aligned Federated Learning

   https://doi.org/10.1145/3447548.3467309  

   Yu, Fuxun; Zhang, Weishan; Qin, Zhuwei; Xu, Zirui; Wang, Di; Liu, Chenchen; Tian, Zhi; Chen, Xiang (August 2021, ACM SIGKDD Conference on Knowledge Discovery & Data Mining)
3. Sub2Vec: Feature Learning for Subgraphs

   Adhikari, B; Zhang, Y; Ramakrishnan, N; Prakash, B. Aditya (June 2018, Advances in Knowledge Discovery and Data Mining. PAKDD 2018. Lecture Notes in Computer Science)
4. Position-Aware Recalibration Module: Learning From Feature Semantics and Feature Position

   https://doi.org/10.24963/ijcai.2020/111  

   Ma, Xu; Fu, Song (July 2020, Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence)

   null (Ed.)

   We present a new method to improve the representational power of the features in Convolutional Neural Networks (CNNs). By studying traditional image processing methods and recent CNN architectures, we propose to use positional information in CNNs for effective exploration of feature dependencies. Rather than considering feature semantics alone, we incorporate spatial positions as an augmentation for feature semantics in our design. From this vantage, we present a Position-Aware Recalibration Module (PRM in short) which recalibrates features leveraging both feature semantics and position. Furthermore, inspired by multi-head attention, our module is capable of performing multiple recalibrations where results are concatenated as the output. As PRM is efficient and easy to implement, it can be seamlessly integrated into various base networks and applied to many position-aware visual tasks. Compared to original CNNs, our PRM introduces a negligible number of parameters and FLOPs, while yielding better performance. Experimental results on ImageNet and MS COCO benchmarks show that our approach surpasses related methods by a clear margin with less computational overhead. For example, we improve the ResNet50 by absolute 1.75% (77.65% vs. 75.90%) on ImageNet 2012 validation dataset, and 1.5%~1.9% mAP on MS COCO validation dataset with almost no computational overhead. Codes are made publicly available. 

   more » « less
5. DeepVoxels: Learning Persistent 3D Feature Embeddings

   Sitzmann, Vincent; Thies, Justus; Heide, Felix; Nießner, Matthias; Wetzstein, Gordon; Zollhofer, Michael (June 2019, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR))

   In this work, we address the lack of 3D understanding of generative neural networks by introducing a persistent 3D feature embedding for view synthesis. To this end, we propose DeepVoxels, a learned representation that encodes the view-dependent appearance of a 3D scene without having to explicitly model its geometry. At its core, our approach is based on a Cartesian 3D grid of persistent embedded features that learn to make use of the underlying 3D scene structure. Our approach combines insights from 3D geometric computer vision with recent advances in learning image-to-image mappings based on adversarial loss functions. DeepVoxels is supervised, without requiring a 3D reconstruction of the scene, using a 2D re-rendering loss and enforces perspective and multi-view geometry in a principled manner. We apply our persistent 3D scene representation to the problem of novel view synthesis demonstrating high-quality results for a variety of challenging scenes. 

   more » « less