Deep discriminative image feature learning for cross-modal semantics understanding

While Generative Adversarial Networks (GANs) have shown promising performance in image generation, they suffer from numerous issues such as mode collapse and training instability. To stabilize GAN training and improve image synthesis quality with diversity, we propose a simple yet effective approach as Contrastive Distance Learning GAN (CDL-GAN) in this paper. Specifically, we add Consistent Contrastive Distance (CoCD) and Characteristic Contrastive Distance (ChCD) into a principled framework to improve GAN performance. The CoCD explicitly maximizes the ratio of the distance between generated images and the increment between noise vectors to strengthen image feature learning for the generator. The ChCD measures the sampling distance of the encoded images in Euler space to boost feature representations for the discriminator. We model the framework by employing Siamese Network as a module into GANs without any modification on the backbone. Both qualitative and quantitative experiments conducted on three public datasets demonstrate the effectiveness of our method.

Download Full-text

Cross-modal transfer with neural word vectors for image feature learning

2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) ◽

10.1109/icassp.2017.7952690 ◽

2017 ◽

Cited By ~ 1

Author(s):

Go Irie ◽

Taichi Asami ◽

Shuhei Tarashima ◽

Takayuki Kurozumi ◽

Tetsuya Kinebuchi

Keyword(s):

Feature Learning ◽

Image Feature

Download Full-text

Multi-View Autoencoder for Image Feature Learning with Structured Nonnegative Low Rank

2018 25th IEEE International Conference on Image Processing (ICIP) ◽

10.1109/icip.2018.8451827 ◽

2018 ◽

Author(s):

Zheng Fang ◽

Sen Zhou ◽

Jing Li

Keyword(s):

Feature Learning ◽

Image Feature ◽

Low Rank

Download Full-text

Fast Image Search with Pixel-Based Deep Learning Framework via Efficient Compact Binary Code and Addictive Latent Layer

International Journal of Pattern Recognition and Artificial Intelligence ◽

10.1142/s0218001418590048 ◽

2017 ◽

Vol 32 (03) ◽

pp. 1859004 ◽

Cited By ~ 1

Author(s):

Jun Yi Li ◽

Jian Hua Li

Keyword(s):

Deep Learning ◽

Nearest Neighbor ◽

Feature Learning ◽

Nearest Neighbor Search ◽

Feature Representation ◽

Image Feature ◽

Retrieval Algorithm ◽

Image Search ◽

Learning Framework ◽

Compact Binary

As we know, the nearest neighbor search is a good and effective method for good-sized image search. This paper mainly introduced how to learn an outstanding image feature representation form and a series of compact binary Hash coding functions under deep learning framework. Our concept is that binary codes can be obtained using a hidden layer to present some latent concepts dominating the class labels with usable data labels. Our method is effective in obtaining hash codes and image representations, so it is suitable for good-sized dataset. It is demonstrated in our experiment that the performances of the proposed algorithms were then verified on three different databases, MNIST, CIFAR-10 and Caltech-101. The experimental results reveal that two-proposed image Hash retrieval algorithm based on pixel-level automatic feature learning show higher search accuracy than the other algorithms; moreover, these two algorithms were proved to be more favorable in scalability and generality.

Download Full-text