Non-Adversarial Image Synthesis With Generative Latent Nearest Neighbors

Hoshen, Yedid; Li, Ké; Malik, Jitendra

doi:10.1109/cvpr.2019.00596

Cited by 39 publications

(32 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…See Section 4.5, Table 2, and Figure 3 for the advantageous performance of our IMLE-GAN. Several follow-up works, e.g., GLANN [20] and conditional IMLE [31], also validate the improved effectiveness of IMLE framework in a reconstructive generation context.…”

Section: Reconstructive Generation: Imlementioning

confidence: 66%

Inclusive GAN: Improving Data and Minority Coverage in Generative Models

Zhou

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Generative Adversarial Networks (GANs) have brought about rapid progress towards generating photorealistic images. Yet the equitable allocation of their modeling capacity among subgroups has received less attention, which could lead to potential biases against underrepresented minorities if left uncontrolled. In this work, we first formalize the problem of minority inclusion as one of data coverage, and then propose to improve data coverage by harmonizing adversarial training with reconstructive generation. The experiments show that our method outperforms the existing state-of-the-art methods in terms of data coverage on both seen and unseen data. We develop an extension that allows explicit control over the minority subgroups that the model should ensure to include, and validate its effectiveness at little compromise from the overall performance on the entire dataset. Code, models, and supplemental videos are available at GitHub.

show abstract

Section: Reconstructive Generation: Imlementioning

confidence: 66%

Inclusive GAN: Improving Data and Minority Coverage in Generative Models

Zhou

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…1 for an example) and/or vanishing generator gradients due to discriminator being way better in distinguishing fake samples and real samples [1]. Non-adversarial approaches [4,11,16] have recently been explored to tackle these challenges. For example, Generative Latent Optimization (GLO) [4] and Generative Latent Nearest Neighbor (GLANN) [11] investigate the importance of inductive bias in convolutional networks by disconnecting the discriminator for a non-adversarial learning protocol of GANs.…”

Section: Mocogan (Adversarial)mentioning

confidence: 99%

“…Non-adversarial approaches [4,11,16] have recently been explored to tackle these challenges. For example, Generative Latent Optimization (GLO) [4] and Generative Latent Nearest Neighbor (GLANN) [11] investigate the importance of inductive bias in convolutional networks by disconnecting the discriminator for a non-adversarial learning protocol of GANs. These works show that without a discriminator, a generator can be learned to map the training images in the given data distribution to a lower dimensional latent space that is learned in conjunction with the weights of the generative network.…”

Section: Mocogan (Adversarial)mentioning

confidence: 99%

“…Some techniques to make the generator agnostic to described problems have been discussed in [27]. The other alternative to the same has given rise to non-adversarial learning of generative networks [4,11]. Both [4,11] showed that properties of convolutional GANs can be mimicked using simple reconstruction losses while discarding the discriminator.…”

Section: Z (T) Lmentioning

confidence: 99%

See 1 more Smart Citation

Non-Adversarial Video Synthesis with Learned Priors

Aich¹,

Gupta²,

Panda³

et al. 2020

Preprint

View full text Add to dashboard Cite

Most of the existing works in video synthesis focus on generating videos using adversarial learning. Despite their success, these methods often require input reference frame or fail to generate diverse videos from the given data distribution, with little to no uniformity in the quality of videos that can be generated. Different from these methods, we focus on the problem of generating videos from latent noise vectors, without any reference input frames. To this end, we develop a novel approach that jointly optimizes the input latent space, the weights of a recurrent neural network and a generator through non-adversarial learning. Optimizing for the input latent space along with the network weights allows us to generate videos in a controlled environment, i.e., we can faithfully generate all videos the model has seen during the learning process as well as new unseen videos. Extensive experiments on three challenging and diverse datasets well demonstrate that our proposed approach generates superior quality videos compared to the existing state-of-the-art methods.

show abstract

“…We can think about techniques of few-shot learning [224] (to train models from a few examples), generative adversarial networks [225] or non-adversarial generative models [226] (for example, to generate data when these are scarce), or Siamese networks [227] (to establish if two images provided as input belong to the same class). Similarly, the use of 3D ConvNets [228] to directly process three-dimensional information is non-existent, as well as the combined use of recurrent and convolutional networks [229] to carry out more complex tasks (such as the textual description of images automatically, i.e., image captioning).…”

mentioning

confidence: 99%

A Survey on Artificial Intelligence Techniques for Biomedical Image Analysis in Skeleton-Based Forensic Human Identification

et al. 2020

View full text Add to dashboard Cite

This paper represents the first survey on the application of AI techniques for the analysis of biomedical images with forensic human identification purposes. Human identification is of great relevance in today’s society and, in particular, in medico-legal contexts. As consequence, all technological advances that are introduced in this field can contribute to the increasing necessity for accurate and robust tools that allow for establishing and verifying human identity. We first describe the importance and applicability of forensic anthropology in many identification scenarios. Later, we present the main trends related to the application of computer vision, machine learning and soft computing techniques to the estimation of the biological profile, the identification through comparative radiography and craniofacial superimposition, traumatism and pathology analysis, as well as facial reconstruction. The potentialities and limitations of the employed approaches are described, and we conclude with a discussion about methodological issues and future research.

show abstract

Non-Adversarial Image Synthesis With Generative Latent Nearest Neighbors

Cited by 39 publications

References 7 publications

Inclusive GAN: Improving Data and Minority Coverage in Generative Models

Inclusive GAN: Improving Data and Minority Coverage in Generative Models

Non-Adversarial Video Synthesis with Learned Priors

A Survey on Artificial Intelligence Techniques for Biomedical Image Analysis in Skeleton-Based Forensic Human Identification

Contact Info

Product

Resources

About