相关论文: Facing Unknown: Open-World Encrypted Traffic Class…

Despite the success of contrastive learning (CL) in vision and language, its theoretical foundations and mechanisms for building representations remain poorly understood. In this work, we build connections between noise contrastive…

Displaying near-real-time traffic information is a useful feature of digital navigation maps. However, most commercial providers rely on privacy-compromising measures such as deriving location information from cellphones to estimate…

The increasing success of Machine Learning (ML) and Deep Learning (DL) has recently re-sparked interest towards traffic classification. While classification of known traffic is a well investigated subject with supervised classification…

Deep learning models suffer from opaqueness. For Convolutional Neural Networks (CNNs), current research strategies for explaining models focus on the target classes within the associated training dataset. As a result, the understanding of…

Open World Object Detection (OWOD) is a challenging computer vision problem that requires detecting unknown objects and gradually learning the identified unknown classes. However, it cannot distinguish unknown instances as multiple unknown…

Training dense passage representations via contrastive learning has been shown effective for Open-Domain Passage Retrieval (ODPR). Existing studies focus on further optimizing by improving negative sampling strategy or extra pretraining.…

In real-world scenarios classification models are often required to perform robustly when predicting samples belonging to classes that have not appeared during its training stage. Open Set Recognition addresses this issue by devising models…

The primary assumption of conventional supervised learning or classification is that the test samples are drawn from the same distribution as the training samples, which is called closed set learning or classification. In many practical…

Classifying patterns of known classes and rejecting ambiguous and novel (also called as out-of-distribution (OOD)) inputs are involved in open world pattern recognition. Deep neural network models usually excel in closed-set classification…

This paper highlights a shift in how to approach material generation. Instead of material-to-material, we propose a language-to-material generation architecture that utilizes millions of untapped data points. Using a web scraper to collect…

Reliable robot perception requires not only predicting scene structure, but also identifying where predictions should be treated as unreliable due to sparse or missing observations. We present ContraMap, a contrastive continuous mapping…

Reliable detection of out-of-distribution (OOD) inputs is increasingly understood to be a precondition for deployment of machine learning systems. This paper proposes and investigates the use of contrastive training to boost OOD detection…

As the size and source of network traffic increase, so does the challenge of monitoring and analysing network traffic. Therefore, sampling algorithms are often used to alleviate these scalability issues. However, the use of high entropy…

Road detection or traversability analysis has been a key technique for a mobile robot to traverse complex off-road scenes. The problem has been mainly formulated in early works as a binary classification one, e.g. associating pixels with…

Recent studies have shown that Contrastive Language-Image Pre-training (CLIP) models are threatened by targeted data poisoning and backdoor attacks due to massive training image-caption pairs crawled from the Internet. Previous defense…

Deep learning (DL) has been successfully applied to encrypted network traffic classification in experimental settings. However, in production use, it has been shown that a DL classifier's performance inevitably decays over time. Re-training…

Network traffic classification, a task to classify network traffic and identify its type, is the most fundamental step to improve network services and manage modern networks. Classical machine learning and deep learning method have…

Event extraction (EE) has considerably benefited from pre-trained language models (PLMs) by fine-tuning. However, existing pre-training methods have not involved modeling event characteristics, resulting in the developed EE models cannot…

This paper studies learning fair encoders in a self-supervised learning (SSL) setting, in which all data are unlabeled and only a small portion of them are annotated with sensitive attribute. Adversarial fair representation learning is well…

Unsupervised representation learning has recently received lots of interest due to its powerful generalizability through effectively leveraging large-scale unlabeled data. There are two prevalent approaches for this, contrastive learning…