Related papers: TripletGAN: Training Generative Model with Triplet…
Face recognition has witnessed significant progress due to the advances of deep convolutional neural networks (CNNs), the central task of which is how to improve the feature discrimination. To this end, several margin-based (\textit{e.g.},…
In this paper, we address the incremental classifier learning problem, which suffers from catastrophic forgetting. The main reason for catastrophic forgetting is that the past data are not available during learning. Typical approaches keep…
In standard generative adversarial network (SGAN), the discriminator estimates the probability that the input data is real. The generator is trained to increase the probability that fake data is real. We argue that it should also…
The vanilla GAN (Goodfellow et al. 2014) suffers from mode collapse deeply, which usually manifests as that the images generated by generators tend to have a high similarity amongst them, even though their corresponding latent vectors have…
We propose a new algorithm to incorporate class conditional information into the critic of GANs via a multi-class generalization of the commonly used Hinge loss that is compatible with both supervised and semi-supervised settings. We study…
With the maturity of Artificial Intelligence (AI) technology, Large Scale Visual Geo-Localization (LSVGL) is increasingly important in urban computing, where the task is to accurately and efficiently recognize the geo-location of a given…
Recently, generative adversarial networks (GANs) have shown promising performance in generating realistic images. However, they often struggle in learning complex underlying modalities in a given dataset, resulting in poor-quality generated…
Learning from triplet comparison data has been extensively studied in the context of metric learning, where we want to learn a distance metric between two instances, and ordinal embedding, where we want to learn an embedding in an Euclidean…
Facial expressions convey massive information and play a crucial role in emotional expression. Deep neural network (DNN) accompanied by deep metric learning (DML) techniques boost the discriminative ability of the model in facial expression…
Mode collapse is a critical problem in training generative adversarial networks. To alleviate mode collapse, several recent studies introduce new objective functions, network architectures or alternative training schemes. However, their…
Recent deep generative models (DGMs) such as generative adversarial networks (GANs) and diffusion probabilistic models (DPMs) have shown their impressive ability in generating high-fidelity photorealistic images. Although looking appealing…
Deep metric learning objectives (e.g., triplet loss) require storing and comparing high-dimensional embeddings, making the per-batch loss buffer scale as $O(S\cdot D)$, where $S$ is the number of samples in a batch and $D$ is the feature…
Deep metric learning aims to learn an embedding space where the distance between data reflects their class equivalence, even when their classes are unseen during training. However, the limited number of classes available in training…
We present a continual learning approach for generative adversarial networks (GANs), by designing and leveraging parameter-efficient feature map transformations. Our approach is based on learning a set of global and task-specific…
Generative neural samplers are probabilistic models that implement sampling using feedforward neural networks: they take a random input vector and produce a sample from a probability distribution defined by the network weights. These models…
Modifications on triplet loss that rescale the back-propagated gradients of special pairs have made significant progress on local descriptor learning. However, current gradient modulation strategies are mainly static so that they would…
Generative adversarial networks constitute a powerful approach to generative modeling. While generated samples often are indistinguishable from real data, there is no guarantee that they will follow the true data distribution. For…
We present a new stage-wise learning paradigm for training generative adversarial networks (GANs). The goal of our work is to progressively strengthen the discriminator and thus, the generators, with each subsequent stage without changing…
A unifying $\alpha$-parametrized generator loss function is introduced for a dual-objective generative adversarial network (GAN), which uses a canonical (or classical) discriminator loss function such as the one in the original GAN…
Generative Adversarial Networks have shown impressive results for the task of object translation, including face-to-face translation. A key component behind the success of recent approaches is the self-consistency loss, which encourages a…