End-to-end Learning of a Fisher Vector Encoding for Part Features in Fine-grained Recognition

@inproceedings{Korsch2020EndtoendLO,
  title={End-to-end Learning of a Fisher Vector Encoding for Part Features in Fine-grained Recognition},
  author={Dimitri Korsch and P. Bodesheim and Joachim Denzler},
  booktitle={German Conference on Pattern Recognition},
  year={2020}
}
Part-based approaches for fine-grained recognition do not show the expected performance gain over global methods, although being able to explicitly focus on small details that are relevant for distinguishing highly similar classes. We assume that part-based methods suffer from a missing representation of local features, which is invariant to the order of parts and can handle a varying number of visible parts appropriately. The order of parts is artificial and often only given by ground-truth… 
4 Citations

Re-rank Coarse Classification with Local Region Enhanced Features for Fine-Grained Image Recognition

A retrievalbased coarse-to-fine framework is proposed, where the TopN classification results are rerank by using the local region enhanced embedding features to improve the Top1 accuracy and to obtain the discriminative regions for distinguishing the fine-grained images.

A Novel Plug-in Module for Fine-Grained Visual Classification

A novel plug-in module that can be integrated to many common backbones, including CNN-based or Transformer-based networks to provide strongly discriminative regions and output pixel-level feature maps and fuse filtered features to enhance fine-grained visual classification is proposed.

Fine-Grained Adversarial Semi-Supervised Learning

This article exploits Semi-Supervised Learning (SSL) to increase the amount of training data to improve the performance of Fine-Grained Visual Categorization (FGVC) and shows that the proposed method has better performance than the only previous approach that examined this problem.

Alignment Enhancement Network for Fine-grained Visual Categorization

A novel Alignment Enhancement Network (AENet) is proposed, including two-level alignments, Cross-layer Alignment (CLA) and Cross-image Aligned (CIA), which exploits the cross-layer relationship between low-level spatial information and high-level semantic information, which contributes to cross- layer feature aggregation to improve the capacity of feature representation for input images.

References

SHOWING 1-10 OF 58 REFERENCES

Part-Based R-CNNs for Fine-Grained Category Detection

This work proposes a model for fine-grained categorization that overcomes limitations by leveraging deep convolutional features computed on bottom-up region proposals, and learns whole-object and part detectors, enforces learned geometric constraints between them, and predicts a fine- grained category from a pose-normalized representation.

Bilinear CNN Models for Fine-Grained Visual Recognition

We propose bilinear models, a recognition architecture that consists of two feature extractors whose outputs are multiplied using outer product at each location of the image and pooled to obtain an

Classification-Specific Parts for Improving Fine-Grained Visual Categorization

This work proposes a novel classification-specific part estimation that uses an initial prediction as well as back-propagation of feature importance via gradient computations in order to estimate relevant image regions and shows the effectiveness of the mentioned part selection method in conjunction with the extracted part features.

Re-rank Coarse Classification with Local Region Enhanced Features for Fine-Grained Image Recognition

A retrievalbased coarse-to-fine framework is proposed, where the TopN classification results are rerank by using the local region enhanced embedding features to improve the Top1 accuracy and to obtain the discriminative regions for distinguishing the fine-grained images.

Picking Deep Filter Responses for Fine-Grained Image Recognition

This paper proposes an automatic fine-grained recognition approach which is free of any object / part annotation at both training and testing stages, and conditionally pick deep filter responses to encode them into the final representation, which considers the importance of filter responses themselves.

Nonparametric Part Transfer for Fine-Grained Recognition

An approach for fine-grained recognition based on a new part detection method which transfers part constellations from objects with similar global shapes is presented and the importance of carefully designed visual extraction strategies, including combination of complementary feature types and iterative image segmentation, is shown.

Deep FisherNet for Image Classification

The proposed FisherNet combines CNN training and FV encoding in a single end-to-end structure that observes a clear advantage of FisherNet over plain CNN and standard FV in terms of both classification accuracy and computational efficiency on the challenging PASCAL visual object classes object classification and emotion image classification tasks.

Generalized Orderless Pooling Performs Implicit Salient Matching

This paper generalizes average and bilinear pooling to “α-pooling”, allowing for learning the pooling strategy during training, and presents a novel way to visualize decisions made by these approaches.

Deep Fisher Kernels -- End to End Learning of the Fisher Kernel GMM Parameters

A gradient descent based learning algorithm is introduced that, in contrast to other feature learning techniques, is not just derived from intuition or biological analogy, but has a theoretical justification in the framework of statistical learning theory.

Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification From the Bottom Up

This paper builds complementary parts models in a weakly supervised manner to retrieve information suppressed by dominant object parts detected by convolutional neural networks and builds a bi-directional long short-term memory (LSTM) network to fuze and encode the partial information of these complementary parts into a comprehensive feature for image classification.
...