Fisher vectors meet Neural Networks: A hybrid classification architecture

By Florent Perronnin, Diane Larlus. 2015

172 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Scattering Networks for Hybrid Representation Learning (2018, methodology): “In contrast we use the scattering transform in combination with convolutional architectures and show hybrid results that well exceed those of [43].”
Scaling the Scattering Transform: Deep Hybrid Networks (2017, neutral): “In term of architecture, our hybrid model is analogous, and comparable to that of [30, 28], for which SIFT features are extracted followed by FV [31] encoding.”
End-to-End Learning of Deep Visual Representations for Image Retrieval (2016, methodology): “Other approaches proposed hybrid models also involving an encoding technique such as Perronnin and Larlus (2015) that used the FV or Gong et al (2014) and Paulin et al (2015) that considered VLAD.”
Learnable pooling with Context Gating for video classification (2017, methodology): “Typically, these methods [31], [36] rely on an unsupervised learning of the codebook.”
Gradients as Features for Deep Representation Learning (2020, background): “More recently, FVs have shown promising results with deep models, ﬁrst as an ingredient of a hybrid system (Perronnin & Larlus, 2015), and then as task embeddings for meta-learning (Achille et al., 2019).”
Look Closer to See Better: Recurrent Attention Convolutional Neural Network for Fine-Grained Image Recognition (2017, methodology): “Besides, another method [34] proposes to unify CNN with spatially weighted representation by Fisher Vector [23], which shows superior results on both bird [30] and dog datasets [13].”
Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition (2018, methodology): “The work in [24] exploit unified CNN framework with spatially weighted representation by the Fisher vector [25].”
Deep Image Retrieval: Learning Global Representations for Image Search (2016, methodology): “Other approaches proposed hybrid models involving an encoding technique such as FV [32] or VLAD [15,33], potentially learnt as well [34] as one of their components.”
Sympathy for the Details: Dense Trajectories and Hybrid Classification Architectures for Action Recognition (2016, methodology): “When unsupervised, we fix the weights of the dimensionality reduction layer from the projection matrices learned by PCA dimensionality reduction followed by whitening and `2 normalization [27].”
Shallow Learning For Deep Networks (2018, methodology): “…AlexNet, this model compares favorably to all alternatives to end-to-end supervised CNNs including hand crafted computer vision and unsupervised learning techniques (Noroozi & Favaro, 2016; Perronnin & Larlus, 2015; Sánchez et al., 2013; Oyallon et al., 2017) (full results shown in Table 1).”
SIFT Meets CNN: A Decade Survey of Instance Retrieval (2016, methodology): “By training a classification model on natural images, the intermediate FC layer can be used for retrieval [157].”
Learning Multi-attention Convolutional Neural Network for Fine-Grained Image Recognition (2017, background): “Besides, some methods (e.g., [35]) propose to unify CNN with spatially-weighted representation by Fisher Vector [23], which show superior results on both bird [30] and dog datasets [12].”
Is Second-Order Information Helpful for Large-Scale Visual Recognition? (2017, background): “Perronnin and Larlus [22] design a hybrid network which connects the FV representations upon hand-crafted features with fullyconnected layers.”
3DmFV: Three-Dimensional Point Cloud Classification in Real-Time Using Convolutional Neural Networks (2018, methodology): “In the context of image classiﬁcation, the combination of FVs and DNNs was already considered [38], [39].”