Related papers: Critic Loss for Image Classification
To train robust deep neural networks (DNNs), we systematically study several target modification approaches, which include output regularisation, self and non-self label correction (LC). Two key issues are discovered: (1) Self LC is the…
In Continual Learning (CL), a neural network is trained on a stream of data whose distribution changes over time. In this context, the main problem is how to learn new information without forgetting old knowledge (i.e., Catastrophic…
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…
Interpreting and explaining the behavior of deep neural networks is critical for many tasks. Explainable AI provides a way to address this challenge, mostly by providing per-pixel relevance to the decision. Yet, interpreting such…
Cross-entropy loss is the standard metric used to train classification models in deep learning and gradient boosting. It is well-known that this loss function fails to account for similarities between the different values of the target. We…
Deep neural networks (DNNs) have the capacity to fit extremely noisy labels nonetheless they tend to learn data with clean labels first and then memorize those with noisy labels. We examine this behavior in light of the Shannon entropy of…
Deep neural network-based medical image classifications often use "hard" labels for training, where the probability of the correct category is 1 and those of others are 0. However, these hard targets can drive the networks over-confident…
Semi-supervised learning has substantially advanced medical image segmentation since it alleviates the heavy burden of acquiring the costly expert-examined annotations. Especially, the consistency-based approaches have attracted more…
Although deep learning performs really well in a wide variety of tasks, it still suffers from catastrophic forgetting -- the tendency of neural networks to forget previously learned information upon learning new tasks where previous data is…
Image captioning, a popular topic in computer vision, has achieved substantial progress in recent years. However, the distinctiveness of natural descriptions is often overlooked in previous work. It is closely related to the quality of…
Both generative learning and discriminative learning have recently witnessed remarkable progress using Deep Neural Networks (DNNs). For structured input synthesis and structured output prediction problems (e.g., layout-to-image synthesis…
The pursuit of decision safety in clinical applications highlights the potential of concept-based methods in medical imaging. While these models offer active interpretability, they often suffer from concept leakages, where unintended…
In the presence of noisy labels, designing robust loss functions is critical for securing the generalization performance of deep neural networks. Cross Entropy (CE) loss has been shown to be not robust to noisy labels due to its…
This paper considers contrastive training for cross-modal 0-shot transfer wherein a pre-trained model in one modality is used for representation learning in another domain using pairwise data. The learnt models in the latter domain can then…
The task of image captioning aims to generate captions directly from images via the automatically learned cross-modal generator. To build a well-performing generator, existing approaches usually need a large number of described images,…
Although deep learning-based segmentation models have achieved impressive performance on public benchmarks, generalizing well to unseen environments remains a major challenge. To improve the model's generalization ability to the new domain…
Proper losses such as cross-entropy incentivize classifiers to produce class probabilities that are well-calibrated on the training data. Due to the generalization gap, these classifiers tend to become overconfident on the test data,…
In this paper, we are concerned with image classification with deep convolutional neural networks (CNNs). We focus on the following question: given a set of candidate CNN models, how to select the right one with the best generalization…
Graph contrastive learning (GCL) aims to contrast positive-negative counterparts to learn the node embeddings, whereas graph data augmentation methods are employed to generate these positive-negative samples. The variation, quantity, and…
Convolutional Neural Networks (CNNs) provide excellent performance when used for image classification. The classical method of training CNNs is by labeling images in a supervised manner as in "input image belongs to this label" (Positive…