Related papers: U-VAP: User-specified Visual Appearance Personaliz…
We witnessed a massive growth in the supervised learning paradigm in the past decade. Supervised learning requires a large amount of labeled data to reach state-of-the-art performance. However, labeling the samples requires a lot of human…
Person re-identification aims to maintain the identity of an individual in diverse locations through different non-overlapping camera views. The problem is fundamentally challenging due to appearance variations resulting from differing…
Face animation is a challenging task. Existing model-based methods (utilizing 3DMMs or landmarks) often result in a model-like reconstruction effect, which doesn't effectively preserve identity. Conversely, model-free approaches face…
Recent works in self-supervised learning have shown impressive results on single-object images, but they struggle to perform well on complex multi-object images as evidenced by their poor visual grounding. To demonstrate this concretely, we…
Unsupervised domain adaptation (UDA) for semantic segmentation aims to adapt a segmentation model trained on the labeled source domain to the unlabeled target domain. Existing methods try to learn domain invariant features while suffering…
Different users find different images generated for the same prompt desirable. This gives rise to personalized image generation which involves creating images aligned with an individual's visual preference. Current generative models are,…
Data augmentation remains a widely utilized technique in deep learning, particularly in tasks such as image classification, semantic segmentation, and object detection. Among them, Copy-Paste is a simple yet effective method and gain great…
Different from Visual Question Answering task that requires to answer only one question about an image, Visual Dialogue involves multiple questions which cover a broad range of visual content that could be related to any objects,…
Domain adaptation (DA) aims at improving the performance of a model on target domains by transferring the knowledge contained in different but related source domains. With recent advances in deep learning models which are extremely data…
Self-supervised learning has become a popular approach in recent years for its ability to learn meaningful representations without the need for data annotation. This paper proposes a novel image augmentation technique, overlaying images,…
Novel view synthesis from images, for example, with 3D Gaussian splatting, has made great progress. Rendering fidelity and speed are now ready even for demanding virtual reality applications. However, the problem of assisting humans in…
A framework is introduced for planning unmanned aerial vehicle flight paths for visual surveillance of ground targets, each having particular viewing requirements. Specifically, each target is associated with a set of imaging parameters,…
We study the problem of learning disentangled representations for data across multiple domains and its applications in human retargeting. Our goal is to map an input image to an identity-invariant latent representation that captures…
Conventional low-rank adaptation methods build adapters without considering data context, leading to sub-optimal fine-tuning performance and severe forgetting of inherent world knowledge. In this paper, we propose context-oriented…
Adjusting visual parameters such as brightness and contrast is common in our everyday experiences. Finding the optimal parameter setting is challenging due to the large search space and the lack of an explicit objective function, leaving…
Personalizing text-to-image models using a limited set of images for a specific object has been explored in subject-specific image generation. However, existing methods often face challenges in aligning with text prompts due to overfitting…
Self-supervised visual representation learning traditionally focuses on image-level instance discrimination. Our study introduces an innovative, fine-grained dimension by integrating patch-level discrimination into these methodologies. This…
In this paper, we investigate the problem of learning disentangled representations. Given a pair of images sharing some attributes, we aim to create a low-dimensional representation which is split into two parts: a shared representation…
Self-supervised learning approaches for unsupervised domain adaptation (UDA) of semantic segmentation models suffer from challenges of predicting and selecting reasonable good quality pseudo labels. In this paper, we propose a novel…
Unsupervised domain adaptation (UDA) plays a crucial role in object detection when adapting a source-trained detector to a target domain without annotated data. In this paper, we propose a novel and effective four-step UDA approach that…