Invariance and Stability of Deep Convolutional Representations
By Alberto Bietti, Julien Mairal. 2017
41 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Yong Jae Lee
- Luc Van Gool
- Fanyi Xiao
- Ming-Hsuan Yang
- Dacheng Tao
- Zhiding Yu
- Andrew Zisserman
- Trevor Darrell
In Representation & Self-Supervised Learning
- Yong Jae Lee
- Zhiding Yu
- Fanyi Xiao
- Richard Zhang
- Yingli Tian
- Longlong Jing
- Abhinav Kumar Gupta
- Dacheng Tao
Citations in the corpus
- Making Convolutional Networks Shift-Invariant Again (2019, background): “While theoretically interesting (Bietti & Mairal, 2017), CKNs perform at lower accuracy than contempo-raries, resulting in limited usage.”
- Biological Sequence Modeling with Convolutional Kernel Networks (2017, neutral): “Going up in the hierarchy, each point would carries information from a larger sequence neighborhood with more invariance due to the effect of pooling layers [Bietti and Mairal, 2017].”
- Delving Deeper into Anti-Aliasing in ConvNets (2020, background): “le when applied to different spatial locations and channel groups. 2 Related Work Network robustness In deep learning, the robustness problem related to adversarial attacks [18,30], input translation [2,22,36], and natural perturbations [28] has been widely studied. The crux of these studies is how ”