Search for: All records

Designing and generating new data under targeted properties has been attracting various critical applications such as molecule design, image editing and speech synthesis. Traditional hand-crafted approaches heavily rely on expertise experience and intensive human efforts, yet still suffer from the insufficiency of scientific knowledge and low throughput to support effective and efficient data generation. Recently, the advancement of deep learning has created the opportunity for expressive methods to learn the underlying representation and properties of data. Such capability provides new ways of determining the mutual relationship between the structural patterns and functional properties of the data and leveraging such relationships to generate structural data, given the desired properties. This article is a systematic review that explains this promising research area, commonly known as controllable deep data generation. First, the article raises the potential challenges and provides preliminaries. Then the article formally defines controllable deep data generation, proposes a taxonomy on various techniques and summarizes the evaluation metrics in this specific domain. After that, the article introduces exciting applications of controllable deep data generation, experimentally analyzes and compares existing works. Finally, this article highlights the promising future directions of controllable deep data generation and identifies five potential challenges. 

Visual explanation (attention)-guided learning uses not only labels but also explanations to guide the model reasoning process. While visual attention-guided learning has shown promising results, it requires a large number of explanation annotations that are time-consuming to prepare. However, in many real-world situations, it is usually desired to prompt the model with visual attention without model retraining. For example, when doing AI-assisted cancer classification on a medical image, users (e.g., clinicians) can provide the AI model with visual attention prompts on which areas are indispensable and which are precluded. Despite its promising objectives, achieving visual attention-prompted prediction presents several major challenges: 1) How can the visual prompt be effectively integrated into the model's reasoning process? 2) How should the model handle samples that lack visual prompts? 3) What is the impact on the model's performance when a visual prompt is imperfect? This paper introduces a novel framework for visual attention prompted prediction and learning, utilizing visual prompts to steer the model's reasoning process. To improve performance in non-prompted situations and align it with prompted scenarios, we propose a co-training approach for both non-prompted and prompted models, ensuring they share similar parameters and activation. Additionally, for instances where the visual prompt does not encompass the entire input image, we have developed innovative attention prompt refinement methods. These methods interpolate the incomplete prompts while maintaining alignment with the model's explanations. Extensive experiments on four datasets demonstrate the effectiveness of our proposed framework in enhancing predictions for samples both with and without prompt. 

Stable inheritance of DNA N⁶-methyladenine (6mA) is crucial for its biological functions in eukaryotes. Here, we identify two distinct methyltransferase (MTase) complexes, both sharing the catalytic subunit AMT1, but featuring AMT6 and AMT7 as their unique components, respectively. While the two complexes are jointly responsible for 6mA maintenance methylation, they exhibit distinct enzymology, DNA/chromatin affinity, genomic distribution, and knockout phenotypes. AMT7 complex, featuring high MTase activity and processivity, is connected to transcription-associated epigenetic marks, including H2A.Z and H3K4me3, and is required for the bulk of maintenance methylation. In contrast, AMT6 complex, with reduced activity and processivity, is recruited by PCNA to initiate maintenance methylation immediately after DNA replication. These two complexes coordinate in maintenance methylation. By integrating signals from both replication and transcription, this mechanism ensures the faithful and efficient transmission of 6mA as an epigenetic mark in eukaryotes.