Related papers: Dissecting the impact of different loss functions …
We propose a novel locally adaptive learning estimator for enhancing the inter- and intra- discriminative capabilities of Deep Neural Networks, which can be used as improved loss layer for semantic image segmentation tasks. Most loss layers…
Scene graphs are a powerful structured representation of the underlying content of images, and embeddings derived from them have been shown to be useful in multiple downstream tasks. In this work, we employ a graph convolutional network to…
There are two popular loss functions used for vision-language retrieval, i.e., triplet loss and contrastive learning loss, both of them essentially minimize the difference between the similarities of negative pairs and positive pairs. More…
Current research in Computer Vision has shown that Convolutional Neural Networks (CNN) give state-of-the-art performance in many classification tasks and Computer Vision problems. The embedding of CNN, which is the internal representation…
Recent works have studied implicit biases in deep learning, especially the behavior of last-layer features and classifier weights. However, they usually need to simplify the intermediate dynamics under gradient flow or gradient descent due…
Nowadays, deep learning is the standard approach for a wide range of problems, including biometrics, such as face recognition and speech recognition, etc. Biometric problems often use deep learning models to extract features from images,…
This paper presents a new regularization method to train a fully convolutional network for semantic tissue segmentation in histopathological images. This method relies on the benefit of unsupervised learning, in the form of image…
Zero-shot learning methods rely on fixed visual and semantic embeddings, extracted from independent vision and language models, both pre-trained for other large-scale tasks. This is a weakness of current zero-shot learning frameworks as…
Image colorization aims to add color information to a grayscale image in a realistic way. Recent methods mostly rely on deep learning strategies. While learning to automatically colorize an image, one can define well-suited objective…
Deformable registration has been one of the pillars of biomedical image computing. Conventional approaches refer to the definition of a similarity criterion that, once endowed with a deformation model and a smoothness constraint, determines…
Deep neural networks have dramatically advanced the state of the art for many areas of machine learning. Recently they have been shown to have a remarkable ability to generate highly complex visual artifacts such as images and text rather…
In this paper, we propose a learning-based image fragment pair-searching and -matching approach to solve the challenging restoration problem. Existing works use rule-based methods to match similar contour shapes or textures, which are…
Recent deep learning based approaches have shown remarkable success on object segmentation tasks. However, there is still room for further improvement. Inspired by generative adversarial networks, we present a generic end-to-end adversarial…
Beyond minimizing a single training loss, many deep learning estimation pipelines rely on an auxiliary objective to quantify and encourage desirable properties of the model (e.g. performance on another dataset, robustness, agreement with a…
Today, deep convolutional neural networks (CNNs) have demonstrated state-of-the-art performance for medical image segmentation, on various imaging modalities and tasks. Despite early success, segmentation networks may still generate…
This paper proposes a new way to learn Physics-Informed Neural Network loss functions using Generalized Additive Models. We apply our method by meta-learning parametric partial differential equations, PDEs, on Burger's and 2D Heat…
In the context of pose-invariant object recognition and retrieval, we demonstrate that it is possible to achieve significant improvements in performance if both the category-based and the object-identity-based embeddings are learned…
Learning the similarity between images constitutes the foundation for numerous vision tasks. The common paradigm is discriminative metric learning, which seeks an embedding that separates different training classes. However, the main…
In most machine learning training paradigms a fixed, often handcrafted, loss function is assumed to be a good proxy for an underlying evaluation metric. In this work we assess this assumption by meta-learning an adaptive loss function to…
In this article, we propose a method to design loss functions based on component trees which can be optimized by gradient descent algorithms and which are therefore usable in conjunction with recent machine learning approaches such as…