Related papers: How and When to Flatten Java Classes?
The idea behind object-centric representation learning is that natural scenes can better be modeled as compositions of objects and their relations as opposed to distributed representations. This inductive bias can be injected into neural…
When programming resource-scarce embedded smart devices, the designer often requires both the low-level system programming features of a language such as C and higher level capability typical of a language like Java. The choice of a…
A type system is introduced for a generic Object Oriented programming language in order to infer resource upper bounds. A sound andcomplete characterization of the set of polynomial time computable functions is obtained. As a consequence,…
Generics have been added to Java so as to increase the expressiveness of its type system. Generics in Java, however, include some features---such as Java wildcards, $F$-bounded generics, and Java erasure---that have been hard to analyze and…
Insufficient requirements reusability, understandability and verifiability jeopardize software projects. Empirical studies show little success in improving these qualities separately. Applying object-oriented thinking to requirements leads…
Modern java programs consist of large number of classes as well as vast amount of objects instantiated during program execution. Software developers are always keen to know the number of objects created for each class. This information is…
For the right application, the use of programming paradigms such as functional or logic programming can enormously increase productivity in software development. But these powerful paradigms are tied to exotic programming languages, while…
Transfer learning has recently become the dominant paradigm of machine learning. Pre-trained models fine-tuned for downstream tasks achieve better performance with fewer labelled examples. Nonetheless, it remains unclear how to develop…
Fine-tuning is arguably the most straightforward way to tailor a pre-trained model (e.g., a foundation model) to downstream applications, but it also comes with the risk of losing valuable knowledge the model had learned in pre-training.…
Finetuning from a pretrained deep model is found to yield state-of-the-art performance for many vision tasks. This paper investigates many factors that influence the performance in finetuning for object detection. There is a long-tailed…
We revisit the well-known object-pool design pattern in Java. In the last decade, the pattern has attracted a lot of criticism regarding its validity when used for light-weight objects that are only meant to hold memory rather than any…
The aim of object-centric vision is to construct an explicit representation of the objects in a scene. This representation is obtained via a set of interchangeable modules called \emph{slots} or \emph{object files} that compete for local…
The performance of value classes is highly dependent on how they are represented in the virtual machine. Value class instances are immutable, have no identity, and can only refer to other value objects or primitive values and since they…
Resource-aware type systems statically approximate not only the expected result type of a program, but also the way external resources are used, e.g., how many times the value of a variable is needed. We extend the type system of…
Balancing sensitivity to new tasks and stability for retaining past knowledge is crucial in continual learning (CL). Recently, sharpness-aware minimization has proven effective in transfer learning and has also been adopted in continual…
In this paper, we study how object-oriented classes are used across thousands of software packages. We concentrate on "usage diversity'", defined as the different statically observable combinations of methods called on the same object. We…
The main goal of concept-oriented programming (COP) is describing how objects are represented and accessed. It makes references (object locations) first-class elements of the program responsible for many important functions which are…
The advancement in computing power has significantly reduced the training times for deep learning, fostering the rapid development of networks designed for object recognition. However, the exploration of object utility, which is the…
We present a novel approach to detect refactoring opportunities by measuring the participation of references between types in instances of patterns representing design flaws. This technique is validated using an experiment where we analyse…
Classification is a major tool of statistics and machine learning. A classification method first processes a training set of objects with given classes (labels), with the goal of afterward assigning new objects to one of these classes. When…