• Corpus ID: 67026602

Improving Fine-Grained Visual Classification using Pairwise Confusion

@inproceedings{Dubey2017ImprovingFV,
  title={Improving Fine-Grained Visual Classification using Pairwise Confusion},
  author={Abhimanyu Dubey and Otkrist Gupta and Pei Guo and Ryan Farrell and Ramesh Raskar and Nikhil Naik},
  year={2017}
}
Fine-Grained Visual Classification (FGVC) datasets contain small sample sizes, along with significant intra-class variation and inter-class similarity. While prior work has addressed intra-class variation using localization and segmentation techniques, the inter-class similarity may also affect feature learning and reduce classification performance. In this work, we address this problem using a novel optimization procedure for the end-to-end neural network training on FGVC tasks. This procedure… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 58 REFERENCES
Fine-grained pose prediction, normalization, and recognition
TLDR
This work unifies steps in an end-to-end trainable network supervised by keypoint locations and class labels that localizes parts by a fully convolutional network to focus the learning of feature representations for the fine-grained classification task.
Fine-Grained Categorization and Dataset Bootstrapping Using Deep Metric Learning with Humans in the Loop
TLDR
Experimental evaluations show significant performance gain using dataset bootstrapping and demonstrate state-of-the-art results achieved by the proposed deep metric learning methods.
Part-Based R-CNNs for Fine-Grained Category Detection
TLDR
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.
Fine-grained recognition without part annotations
TLDR
This work proposes a method for fine-grained recognition that uses no part annotations, based on generating parts using co-segmentation and alignment, which is combined in a discriminative mixture.
Weakly Supervised Fine-Grained Categorization With Part-Based Image Representation
TLDR
The proposed weakly supervised method achieves comparable or better accuracy than the state-of-the-artweakly supervised methods and most existing annotation-dependent methods on three challenging datasets, suggesting that it is not always necessary to learn expensive object/part detectors in fine-grained image categorization.
A codebook-free and annotation-free approach for fine-grained image categorization
TLDR
This work proposes a codebook-free and annotation-free approach for fine-grained image categorization, and proposes a novel bagging-based algorithm to build a final classifier by aggregating a set of discriminative yet largely uncorrelated classifiers.
Picking Deep Filter Responses for Fine-Grained Image Recognition
TLDR
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.
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
Generalized Orderless Pooling Performs Implicit Salient Matching
TLDR
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.
Mining Discriminative Triplets of Patches for Fine-Grained Classification
TLDR
This work introduces triplets of patches with geometric constraints to improve the accuracy of patch localization, and automatically mine discriminative geometrically-constrained triplets for classification in a patch-based framework that only requires object bounding boxes.
...
...