Related papers: Postmortem Object Type Identification
We propose continual instance learning - a method that applies the concept of continual learning to the task of distinguishing instances of the same object category. We specifically focus on the car object, and incrementally learn to…
Zero-shot cross-modal retrieval (ZS-CMR) deals with the retrieval problem among heterogenous data from unseen classes. Typically, to guarantee generalization, the pre-defined class embeddings from natural language processing (NLP) models…
In this paper, we address the problem of manual debugging, which nowadays remains resource-intensive and in some parts archaic. This problem is especially evident in increasingly complex and distributed software systems. Therefore, our…
Continual Learning is considered a key step toward next-generation Artificial Intelligence. Among various methods, replay-based approaches that maintain and replay a small episodic memory of previous samples are one of the most successful…
Many recent studies have shown that deep neural models are vulnerable to adversarial samples: images with imperceptible perturbations, for example, can fool image classifiers. In this paper, we present the first type-specific approach to…
We propose an axiomatic generic framework for modelling weak memory. We show how to instantiate this framework for SC, TSO, C++ restricted to release-acquire atomics, and Power. For Power, we compare our model to a preceding operational…
We present a type system capable of guaranteeing the memory safety of programs that may involve (sophisticated) pointer manipulation such as pointer arithmetic. With its root in a recently developed framework Applied Type System (ATS), the…
Disentanglement is a runtime property of parallel programs guaranteeing that parallel tasks remain oblivious to each other's allocations. As demonstrated in the MaPLe compiler and run-time system, disentanglement can be exploited for fast…
In recent years malware has become increasingly sophisticated and difficult to detect prior to exploitation. While there are plenty of approaches to malware detection, they all have shortcomings when it comes to identifying malware…
Speculation is provided on how infrastructure choices fit into the materials data ecosystem. Special attention is paid to object storage, the Intel DAOS API, storage-class memory (SCM), and the prospect of non-von Neumann computing. Lastly,…
In this paper, we propose an novel methodology aimed at simulating the learning phenomenon of nystagmus through the application of differential blurring on datasets. Nystagmus is a biological phenomenon that influences human vision…
Forgetting is in common in daily life, and 50-80% everyday's forgetting is due to prospective memory failures, which have significant impacts on our life. More seriously, some of these memory lapses can bring fatal consequences such as…
Many effective supervised discriminative dictionary learning methods have been developed in the literature. However, when training these algorithms, precise ground-truth of the training data is required to provide very accurate point-wise…
This paper presents a method for segmenting iris images obtained from the deceased subjects, by training a deep convolutional neural network (DCNN) designed for the purpose of semantic segmentation. Post-mortem iris recognition has recently…
Online programming courses are becoming more and more popular, but they still have significant drawbacks when compared to the traditional education system, e.g., the lack of feedback. In this study, we apply machine learning methods to…
Writing correct programs for weak memory models such as the C11 memory model is challenging because of the weak consistency guarantees these models provide. The first program logics for the verification of such programs have recently been…
This paper introduces OPTIMUM-DERAM, a highly consistent, scalable, secure, and decentralized shared memory solution. Traditional distributed shared memory implementations offer multi-object support by multi-threading a single object memory…
We present progress on the experimental validation of a fundamental and universally applicable vulnerability analysis framework that is capable of identifying new types of vulnerabilities before attackers innovate attacks. This new…
A method for extracting positive information from negative goals is proposed. It makes use of typed existence properties between arguments of a predicate to rewrite negative goals in a logic program. A typed existence property is a…
In-Memory Computing (IMC) introduces a new paradigm of computation that offers high efficiency in terms of latency and power consumption for AI accelerators. However, the non-idealities and defects of emerging technologies used in advanced…