• Corpus ID: 59316734

CoCoNet: A Collaborative Convolutional Network

@article{Chakraborty2019CoCoNetAC,
  title={CoCoNet: A Collaborative Convolutional Network},
  author={Tapabrata (Rohan) Chakraborty and B. McCane and S. Mills and Umapada Pal},
  journal={ArXiv},
  year={2019},
  volume={abs/1901.09886}
}
We present an end-to-end CNN architecture for fine-grained visual recognition called Collaborative Convolutional Network (CoCoNet. [] Key Method We perform a detailed study of the performance with 1-stage and 2-stage transfer learning and different configurations with benchmark architectures like AlexNet and VggNet. The ablation study shows that the proposed method outperforms its constituent parts considerably and consistently. CoCoNet also outperforms the baseline popular deep learning based fine-grained…

Figures and Tables from this paper

Distance Metric Learned Collaborative Representation Classifier(DML-CRC)
TLDR
The proposed method DML-CRC gives state-of-the-art performance on benchmark fine-grained classification datasets CUB Birds, Oxford Flowers and Oxford-IIIT Pets using the VGG-19 deep network and can be used for other similar classification tasks.
Distance Metric Learned Collaborative Representation Classifier
TLDR
The proposed method DML-CRC gives state-of-the-art performance on benchmark fine-grained classification datasets CUB Birds, Oxford Flowers and Oxford-IIIT Pets using the VGG-19 deep network and can be used for any similar classification tasks.
VISUAL SUPPORT FOR HUMAN-AI CO-COMPOSITION
TLDR
A visual approach for AI-assisted music composition, where the user interactively generates, selects, and adapts short melodies, and an overview over larger numbers of samples, allowing for insights into the AI’s predictions and the sample space.

References

SHOWING 1-10 OF 32 REFERENCES
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
Very Deep Convolutional Networks for Large-Scale Image Recognition
TLDR
This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Improved Bilinear Pooling with CNNs
TLDR
This paper investigates various ways of normalizing second-order statistics of convolutional features to improve their representation power and finds that the matrix square-root normalization offers significant improvements and outperforms alternative schemes such as the matrix logarithm normalization when combined with elementwisesquare-root and l2 normalization.
Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-Grained Image Recognition
TLDR
TASN consists of a trilinear attention module, which generates attention maps by modeling the inter-channel relationships, an attention-based sampler which highlights attended parts with high resolution, and a feature distiller, which distills part features into an object-level feature by weight sharing and feature preserving strategies.
ImageNet classification with deep convolutional neural networks
TLDR
A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.
Bilinear Convolutional Neural Networks for Fine-Grained Visual Recognition
TLDR
A systematic analysis of these networks shows that the bilinear features are highly redundant and can be reduced by an order of magnitude in size without significant loss in accuracy, and are also effective for other image classification tasks such as texture and scene recognition.
Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks
TLDR
An approach is presented that is able to learn part models in a completely unsupervised manner, without part annotations and even without given bounding boxes during learning, to find constellations of neural activation patterns computed using convolutional neural networks.
Cross-X Learning for Fine-Grained Visual Categorization
TLDR
This paper proposes Cross-X learning, a simple yet effective approach that exploits the relationships between different images and between different network layers for robust multi-scale feature learning and involves two novel components: a cross-category cross-semantic regularizer that guides the extracted features to represent semantic parts and aCross-layerRegularizer that improves the robustness of multi- scale features by matching the prediction distribution across multiple layers.
Zero-shot Fine-grained Classification by Deep Feature Learning with Semantics
TLDR
Experimental results on two benchmark datasets demonstrate that the model outperforms the state-of-the-art zero- shot learning models and the features obtained by the feature learning model also yield significant gains when they are used by other zero-shot learning models, which shows the flexility of the model in zero-shots fine-grained classification.
Selective Sparse Sampling for Fine-Grained Image Recognition
TLDR
A simple yet effective framework, called Selective Sparse Sampling, to capture diverse and fine-grained details and outperforms the state-of-the-art methods on challenging benchmarks including CUB-200-2011, FGVC-Aircraft, and Stanford Cars.
...
...