Related papers: Correct-N-Contrast: A Contrastive Approach for Imp…
The paradigm of worst-group loss minimization has shown its promise in avoiding to learn spurious correlations, but requires costly additional supervision on spurious attributes. To resolve this, recent works focus on developing weaker…
Contrastive learning is a major studied topic in metric learning. However, sampling effective contrastive pairs remains a challenge due to factors such as limited batch size, imbalanced data distribution, and the risk of overfitting. In…
Weakly Supervised Object Detection (WSOD) with only image-level annotation has recently attracted wide attention. Many existing methods ignore the inter-image relationship of instances which share similar characteristics while can certainly…
This paper proposes an attack-independent (non-adversarial training) technique for improving adversarial robustness of neural network models, with minimal loss of standard accuracy. We suggest creating a neighborhood around each training…
Deep neural networks are vulnerable to adversarial noise. Adversarial Training (AT) has been demonstrated to be the most effective defense strategy to protect neural networks from being fooled. However, we find AT omits to learning robust…
Training accurate deep neural networks (DNNs) in the presence of noisy labels is an important and challenging task. Though a number of approaches have been proposed for learning with noisy labels, many open issues remain. In this paper, we…
Previous deep learning approaches for survival analysis have primarily relied on ranking losses to improve discrimination performance, which often comes at the expense of calibration performance. To address such an issue, we propose a novel…
Learning good representations involves capturing the diverse ways in which data samples relate. Contrastive loss - an objective matching related samples - underlies methods from self-supervised to multimodal learning. Contrastive losses,…
Training images with data transformations have been suggested as contrastive examples to complement the testing set for generalization performance evaluation of deep neural networks (DNNs). In this work, we propose a practical framework…
Anomaly detection aims at identifying deviant samples from the normal data distribution. Contrastive learning has provided a successful way to sample representation that enables effective discrimination on anomalies. However, when…
Recently, graph contrastive learning (GCL) has emerged as one of the optimal solutions for node-level and supervised tasks. However, for structure-related and unsupervised tasks such as graph clustering, current GCL algorithms face…
Graph contrastive learning (GCL) has been widely applied to text classification tasks due to its ability to generate self-supervised signals from unlabeled data, thus facilitating model training. However, existing GCL-based text…
Unsupervised image clustering methods often introduce alternative objectives to indirectly train the model and are subject to faulty predictions and overconfident results. To overcome these challenges, the current research proposes an…
Noise contrastive estimation (NCE) is a popular method for training energy-based models (EBM) with intractable normalisation terms. The key idea of NCE is to learn by comparing unnormalised log-likelihoods of the reference and noisy…
We introduce a novel self-supervised deep clustering approach tailored for unstructured data without requiring prior knowledge of the number of clusters, termed Adaptive Self-supervised Robust Clustering (ASRC). In particular, ASRC…
Convolutional neural networks (CNNs) have made significant advancement, however, they are widely known to be vulnerable to adversarial attacks. Adversarial training is the most widely used technique for improving adversarial robustness to…
Adversarial training has been proven to be an effective technique for improving the adversarial robustness of models. However, there seems to be an inherent trade-off between optimizing the model for accuracy and robustness. To this end, we…
Contrastive learning has been applied to Human Activity Recognition (HAR) based on sensor data owing to its ability to achieve performance comparable to supervised learning with a large amount of unlabeled data and a small amount of labeled…
Contrastive learning is an efficient approach to self-supervised representation learning. Although recent studies have made progress in the theoretical understanding of contrastive learning, the investigation of how to characterize the…
Ensemble Adversarial Training (EAT) attempts to enhance the robustness of models against adversarial attacks by leveraging multiple models. However, current EAT strategies tend to train the sub-models independently, ignoring the cooperative…