Learning rotation-aware features: From invariant priors to equivariant descriptors

2012

101 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

Citations in the corpus

Group Equivariant Convolutional Networks (2016, methodology): “This includes work on transforming autoencoders (Hinton et al., 2011), equivariant Boltzmann machines (Kivinen & Williams, 2011; Sohn & Lee, 2012), equivariant descriptors (Schmidt & Roth, 2012), and equivariant ﬁltering (Skibbe, 2013).”
RotDCF: Decomposition of Convolutional Filters for Rotation-Equivariant Deep Networks (2018, background): “Rotation-invariant descriptors were studied in [31] with product models, and in [16, 19, 32] by estimating the speciﬁc image transformation.”
Variational Inference of Disentangled Latent Concepts from Unlabeled Observations (2017, background): “…setting which assumes the knowledge about the nature of input transformations (e.g., rotations, translations, scaling for images, etc.) (Schmidt and Roth, 2012; Bruna and Mallat, 2013; Anselmi et al., 2014, 2016; Cohen and Welling, 2016; Dieleman et al., 2016; Haasdonk et al., 2005; Mroueh et al.,…”
Harmonic Networks: Deep Translation and Rotation Equivariance (2016, neutral): “2 - Conv-RBM [22] 3 .”
Exploiting Cyclic Symmetry in Convolutional Neural Networks (2016, background): “Schmidt & Roth (2012) modify Markov random ﬁelds (MRF) to learn rotation-invariant image priors.”
Learning Steerable Filters for Rotation Equivariant CNNs (2017, neutral): “0004 Schmidt and Roth [28] 4 .”
Oriented Response Networks (2017, background): “In [21, 36], the Convolutional Restricted Boltzmann Machine (C-RBM) induces transformation-aware filters, i.”
Deep Learning for Unmanned Aerial Vehicle-Based Object Detection and Tracking: A survey (2021, background): “It is worth mentioning that some rotation-invariant methods based on theoretical analysis can cover the intrinsic properties of rotations [109], [110] to extract real rotation-invariant features.”
Learning Rotation-Invariant and Fisher Discriminative Convolutional Neural Networks for Object Detection (2019, unknown): “According to Table 2, our RI-CNN feature with a simple linear SVM classifier (i) significantly improves the performance of the traditional CNN model with the AlexNet architecture [6] fine-tuned on the aerial car dataset, which is also the baseline of our method, and (ii) outperforms all other recent”
Local Group Invariant Representations via Orbit Embeddings (2016, methodology): “The proposed LGIKA outperforms most of the competing methods including deep architectures like rotation-invariant convolutional RBM (RC-RBM) [40], transformation invariant RBM (TI-RBM) [43], and regular deep CNN (Z2-CNN) [11].”
Learning rotation invariant convolutional filters for texture classification (2016, background): “In [15], [16], [17], the authors propose to learn unsupervised rotation equivariant features by tying the weights of a Convolutional Restricted Boltzmann Machine (C-RBM).”
RIFD-CNN: Rotation-Invariant and Fisher Discriminative Convolutional Neural Networks for Object Detection (2016, methodology): “RC-RBM [46] + Gradients IHOF [46] + linear SVM 77.”
Deep Rotation Equivariant Network (2017, methodology): “Later, a following work by [12] incorporate linear transformation invariance into c-RBMs, yielding features that have a notion of transformation performed.”
Learning Image Representations Tied to Egomotion from Unlabeled Video (2017, background): “While prior work (Kivinen and Williams 2011; Schmidt and Roth 2012) focuses on equivariance where g is a 2D image warp, we explore the case where g ∈ P is an egomotion pattern (cf.”
Learning image representations equivariant to ego-motion (2015, background): “Furthermore, while equivariance is explored in some recent work, unlike our idea, it typically focuses on 2D image transformations as opposed to 3D ego-motion [12] [24] and considers existing features [28] [15].”
Learning Image Representations Tied to Ego-Motion (2015, background): “While prior work [14, 26] focuses on equivariance where g is a 2D image warp, we explore the case where g ∈ P is an ego-motion pattern (cf.”