Related papers: Contrastive ECOC: Learning Output Codes for Advers…

Large-scale multi-label text classification (LMTC) aims to associate a document with its relevant labels from a large candidate set. Most existing LMTC approaches rely on massive human-annotated training data, which are often costly to…

Analysis of cardiac ultrasound images is commonly performed in routine clinical practice for quantification of cardiac function. Its increasing automation frequently employs deep learning networks that are trained to predict disease or…

Annotation of large-scale 3D data is notoriously cumbersome and costly. As an alternative, weakly-supervised learning alleviates such a need by reducing the annotation by several order of magnitudes. We propose COARSE3D, a novel…

Object detection has advanced significantly in the closed-set setting, but real-world deployment remains limited by two challenges: poor generalization to unseen categories and insufficient robustness under adverse conditions. Prior…

Classification and clustering algorithms have been proved to be successful individually in different contexts. Both of them have their own advantages and limitations. For instance, although classification algorithms are more powerful than…

Contrastive learning (CL) has recently been applied to adversarial learning tasks. Such practice considers adversarial samples as additional positive views of an instance, and by maximizing their agreements with each other, yields better…

Simplicial complexes prove effective in modeling data with multiway dependencies, such as data defined along the edges of networks or within other higher-order structures. Their spectrum can be decomposed into three interpretable subspaces…

Binary code similarity detection (BCSD) serves as a fundamental technique for various software engineering tasks, e.g., vulnerability detection and classification. Attacks against such models have therefore drawn extensive attention, aiming…

Understanding the vulnerability of large-scale pre-trained vision-language models like CLIP against adversarial attacks is key to ensuring zero-shot generalization capacity on various downstream tasks. State-of-the-art defense mechanisms…

As an algorithmic framework for learning to learn, meta-learning provides a promising solution for few-shot text classification. However, most existing research fail to give enough attention to class labels. Traditional basic framework…

Learning and predicting the performance of a configurable software system helps to provide better quality assurance. One important engineering decision therein is how to encode the configuration into the model built. Despite the presence of…

We investigate the possibility of forcing a self-supervised model trained using a contrastive predictive loss to extract slowly varying latent representations. Rather than producing individual predictions for each of the future…

Large-scale pre-trained models such as CodeBERT, GraphCodeBERT have earned widespread attention from both academia and industry. Attributed to the superior ability in code representation, they have been further applied in multiple…

Abstract syntax trees (ASTs) play a crucial role in source code representation. However, due to the large number of nodes in an AST and the typically deep AST hierarchy, it is challenging to learn the hierarchical structure of an AST…

Sensitivity to adversarial noise hinders deployment of machine learning algorithms in security-critical applications. Although many adversarial defenses have been proposed, robustness to adversarial noise remains an open problem. The most…

Given a similarity metric, contrastive methods learn a representation in which examples that are similar are pushed together and examples that are dissimilar are pulled apart. Contrastive learning techniques have been utilized extensively…

One-Class Classification (OCC) is a special case of multi-class classification, where data observed during training is from a single positive class. The goal of OCC is to learn a representation and/or a classifier that enables recognition…

Contrastive learning (CL) methods effectively learn data representations in a self-supervision manner, where the encoder contrasts each positive sample over multiple negative samples via a one-vs-many softmax cross-entropy loss. By…

The performance of sentence encoders can be significantly improved through the simple practice of fine-tuning using contrastive loss. A natural question arises: what characteristics do models acquire during contrastive learning? This paper…

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…