The ability to extract invariant visual features of objects from complex scenes and identify the same objects in different scenes is inborn for humans. To endow AI systems with such capability, we introduce a novel compositional scene understanding method known as Compositional Scene understanding via Global Object-centric representations (CSGOs). CSGO achieves comprehensive scene understanding, including the discovery and identification of objects, by leveraging a set of learnable global object-centric representations in an unsupervised manner. CSGO comprises three components: 1) Local Object-Centric Learning, which is responsible for extracting localized and scene-specific object-centric representations to discover objects; 2) Image Decoding, facilitating the reconstruction of object and scene images using the obtained object-centric representation as input; and 3) Global Object-Centric Learning, identifying the object across diverse scenes according to a set of learnable global object-centric representations, which indicates the scene-free intrinsic attributes (i.e., appearance and shape) of objects. Experimental results on three synthetic datasets and one real-world scene dataset demonstrate that CSGO has excellent object identification and attribute disentanglement abilities. Furthermore, the scene decomposition performance (indicating object discovery performance) of CSGO is superior to comparison methods.

Visual scenes are extremely diverse, not only because there are infinite possible combinations of objects and backgrounds but also because the observations of the same scene may vary greatly with the change of viewpoints. When observing a multi-object visual scene from multiple viewpoints, humans can perceive the scene compositionally from each viewpoint while achieving the so-called "object constancy" across different viewpoints, even though the exact viewpoints are untold. This ability is essential for humans to identify the same object while moving and to learn from vision efficiently. It is intriguing to design models that have a similar ability. In this article, we consider a novel problem of learning compositional scene representations from multiple unspecified (i.e., unknown and unrelated) viewpoints without using any supervision and propose a deep generative model which separates latent representations into a viewpoint-independent part and a viewpoint-dependent part to solve this problem. During the inference, latent representations are randomly initialized and iteratively updated by integrating the information in different viewpoints with neural networks. Experiments on several specifically designed synthetic datasets have shown that the proposed method can effectively learn from multiple unspecified viewpoints.

Visual scenes are composed of visual concepts and have the property of combinatorial explosion. An important reason for humans to efficiently learn from diverse visual scenes is the ability of compositional perception, and it is desirable for artificial intelligence to have similar abilities. Compositional scene representation learning is a task that enables such abilities. In recent years, various methods have been proposed to apply deep neural networks, which have been proven to be advantageous in representation learning, to learn compositional scene representations via reconstruction, advancing this research direction into the deep learning era. Learning via reconstruction is advantageous because it may utilize massive unlabeled data and avoid costly and laborious data annotation. In this survey, we first outline the current progress on reconstruction-based compositional scene representation learning with deep neural networks, including development history and categorizations of existing methods from the perspectives of the modeling of visual scenes and the inference of scene representations; then provide benchmarks, including an open source toolbox to reproduce the benchmark experiments, of representative methods that consider the most extensively studied problem setting and form the foundation for other methods; and finally discuss the limitations of existing methods and future directions of this research topic.

Prior research has introduced the Single-Instruction-Multiple-Data paradigm for DNA computing (SIMD DNA). It offers the potential for storing information and performing in-memory computations on DNA, with massive parallelism. This paper introduces three new SIMD DNA operations: sorting, shifting, and searching. Each is a fundamental operation in computer science. Our implementations demonstrate the effectiveness of parallel pairwise operations with this new paradigm.

Ever since Watson and Crick first described the molecular structure of DNA, its information-bearing potential has been apparent to computer scientists. This has led to a concerted effort in academia and industry to deliver practical DNA data storage systems. This paper presents a novel approach for both storage and computation with DNA. Data is stored in the form of analog values of the relative concentration of different DNA molecules. Computation is in the form of cas-cadable NAND operations, effected via toehold-mediated strand displacement reactions operating on these concentration values. Results were verified with the “Peppercorn Enumerator,” a recent software tool for analyzing domain-level strand displacement. In all cases, the relative error in output concentration was less than 0.03%. The approach is robust to encoding errors and cross-hybridization. It does not rely on long DNA strands, which are expensive to synthesize. It opens new avenues for storage and computing, including the implementation of a wide range of useful mathematical functions in vitro.

In this paper, we introduce a novel scheme for computing polynomial functions on a substrate of nicked DNA. We first discuss a fractional encoding of data, based on the concentration of nicked double DNA strands. Then we show how to perform multiplication on this representation. Next we describe the read-out process, effected by releasing single strands. We show how to perform simple mathematical operations such as addition and subtraction, as well as how to scale constant values using probabilistic switches. We also describe two complex operations: calculating a vector dot product and computing a general polynomial function. We conclude by discussing potential applications of our scheme, practical challenges, and future research directions.