Related papers: Joint Generative and Contrastive Learning for Unsu…
Collecting well-annotated image datasets to train modern machine learning algorithms is prohibitively expensive for many tasks. One appealing alternative is rendering synthetic data where ground-truth annotations are generated…
Unsupervised visible-infrared person re-identification (USVI-ReID) aims to match specified people in infrared images to visible images without annotations, and vice versa. USVI-ReID is a challenging yet under-explored task. Most existing…
Person re-identification (re-ID) aims at matching images of the same identity across camera views. Due to varying distances between cameras and persons of interest, resolution mismatch can be expected, which would degrade person re-ID…
Unsupervised representation learning has recently received lots of interest due to its powerful generalizability through effectively leveraging large-scale unlabeled data. There are two prevalent approaches for this, contrastive learning…
Anomaly detection from graph data has drawn much attention due to its practical significance in many critical applications including cybersecurity, finance, and social networks. Existing data mining and machine learning methods are either…
In recent years, supervised learning with convolutional networks (CNNs) has seen huge adoption in computer vision applications. Comparatively, unsupervised learning with CNNs has received less attention. In this work we hope to help bridge…
A good representation for arbitrarily complicated data should have the capability of semantic generation, clustering and reconstruction. Previous research has already achieved impressive performance on either one. This paper aims at…
The success of contrastive learning depends on the construction and utilization of high-quality positive pairs. However, current methods face critical limitations on two fronts: on the construction side, both handcrafted and generative…
Generative Adversarial Networks (GANs) have been shown to produce realistically looking synthetic images with remarkable success, yet their performance seems less impressive when the training set is highly diverse. In order to provide a…
Leveraging supervised information can lead to superior retrieval performance in the image hashing domain but the performance degrades significantly without enough labeled data. One effective solution to boost performance is to employ…
While deep neural networks have achieved remarkable success in various computer vision tasks, they often fail to generalize to new domains and subtle variations of input images. Several defenses have been proposed to improve the robustness…
In this work, we study the image transformation problem, which targets at learning the underlying transformations (e.g., the transition of seasons) from a collection of unlabeled images. However, there could be countless of transformations…
Disentangled generative models map a latent code vector to a target space, while enforcing that a subset of the learned latent codes are interpretable and associated with distinct properties of the target distribution. Recent advances have…
Generative Adversarial Networks have become one of the most studied frameworks for unsupervised learning due to their intuitive formulation. They have also been shown to be capable of generating convincing examples in limited domains, such…
Unsupervised person re-identification (ReID) aims at learning discriminative identity features without annotations. Recently, self-supervised contrastive learning has gained increasing attention for its effectiveness in unsupervised…
Mainstream 3D representation learning approaches are built upon contrastive or generative modeling pretext tasks, where great improvements in performance on various downstream tasks have been achieved. However, we find these two paradigms…
Unsupervised person re-ID is the task of identifying people on a target data set for which the ID labels are unavailable during training. In this paper, we propose to unify two trends in unsupervised person re-ID: clustering & fine-tuning…
Current 3D GAN inversion methods for human heads typically use only one single frontal image to reconstruct the whole 3D head model. This leaves out meaningful information when multi-view data or dynamic videos are available. Our method…
Generative Adversarial Networks (GANs) produce impressive results on unconditional image generation when powered with large-scale image datasets. Yet generated images are still easy to spot especially on datasets with high variance (e.g.…
Recent research has shown that it is possible to find interpretable directions in the latent spaces of pre-trained Generative Adversarial Networks (GANs). These directions enable controllable image generation and support a wide range of…