Related papers: Learning from a Generative Oracle: Domain Adaptati…

Deep learning models can achieve high accuracy when trained on large amounts of labeled data. However, real-world scenarios often involve several challenges: Training data may become available in installments, may originate from multiple…

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…

Domain generalization (DG) aims to learn a generalized model to an unseen target domain using only limited source domains. Previous attempts to DG fail to learn domain-invariant representations only from the source domains due to the…

The rapid advancement of generative technologies has made synthetic images nearly indistinguishable from real ones, thereby creating an urgent need for robust detectors to counter misinformation. However, existing methods mainly rely on…

Gradient-based meta-learning techniques are both widely applicable and proficient at solving challenging few-shot learning and fast adaptation problems. However, they have practical difficulties when operating on high-dimensional parameter…

Top-performing deep architectures are trained on massive amounts of labeled data. In the absence of labeled data for a certain task, domain adaptation often provides an attractive option given that labeled data of similar nature but from a…

Paraphrase generation is a longstanding NLP task and achieves great success with the aid of large corpora. However, transferring a paraphrasing model to another domain encounters the problem of domain shifting especially when the data is…

Although LEGO sets have entertained generations of children and adults, the challenge of designing customized builds matching the complexity of real-world or imagined scenes remains too great for the average enthusiast. In order to make…

A practical shortcoming of deep neural networks is their specialization to a single task and domain. While recent techniques in domain adaptation and multi-domain learning enable the learning of more domain-agnostic features, their success…

Unsupervised domain adaptation enables to alleviate the need for pixel-wise annotation in the semantic segmentation. One of the most common strategies is to translate images from the source domain to the target domain and then align their…

Applying an object detector, which is neither trained nor fine-tuned on data close to the final application, often leads to a substantial performance drop. In order to overcome this problem, it is necessary to consider a shift between…

Unlike human learning, machine learning often fails to handle changes between training (source) and test (target) input distributions. Such domain shifts, common in practical scenarios, severely damage the performance of conventional…

The major challenge in today's computer vision scenario is the availability of good quality labeled data. In a field of study like image classification, where data is of utmost importance, we need to find more reliable methods which can…

Generative models are now used to create a variety of high-quality digital artifacts. Yet their use in designing physical objects has received far less attention. In this paper, we advocate for the construction toy, LEGO, as a platform for…

How can we apply human feedback into generative model? As answer of this question, in this paper, we show the method applied on denoising problem and domain adaptation using human feedback. Deep generative models have demonstrated…

Diffusion models excel at generating photo-realistic images but come with significant computational costs in both training and sampling. While various techniques address these computational challenges, a less-explored issue is designing an…

Adapting generative models to specific domains presents an effective solution for satisfying specialized requirements. However, adapting to some complex domains remains challenging, especially when these domains require substantial paired…

The adoption of visual foundation models has become a common practice in computer-aided diagnosis (CAD). While these foundation models provide a viable solution for creating generalist medical AI, privacy concerns make it difficult to…

We propose a synthetic reasoning task, LEGO (Learning Equality and Group Operations), that encapsulates the problem of following a chain of reasoning, and we study how the Transformer architectures learn this task. We pay special attention…

Transferring the knowledge of pretrained networks to new domains by means of finetuning is a widely used practice for applications based on discriminative models. To the best of our knowledge this practice has not been studied within the…