Related papers: The Contextual Loss for Image Transformation with …

Unpaired image-to-image translation aims to find a mapping between the source domain and the target domain. To alleviate the problem of the lack of supervised labels for the source images, cycle-consistency based methods have been proposed…

Conventional object detection models require large amounts of training data. In comparison, humans can recognize previously unseen objects by merely knowing their semantic description. To mimic similar behaviour, zero-shot object detection…

Current text conditioned image generation methods output realistic looking images, but they fail to capture specific styles. Simply finetuning them on the target style datasets still struggles to grasp the style features. In this work, we…

Convolutional Neural Networks (CNNs) frequently "cheat" by exploiting superficial correlations, raising concerns about whether they make predictions for the right reasons. Inspired by cognitive science, which highlights the role of…

Multilingual alignment of sentence representations has mostly required bitexts to bridge the gap between languages. We investigate whether visual information can bridge this gap instead. Image caption datasets are very easy to create…

Previous work has proposed many new loss functions and regularizers that improve test accuracy on image classification tasks. However, it is not clear whether these loss functions learn better representations for downstream tasks. This…

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,…

Domain shift is a very challenging problem for semantic segmentation. Any model can be easily trained on synthetic data, where images and labels are artificially generated, but it will perform poorly when deployed on real environments. In…

Can we construct an explainable face recognition network able to learn a facial part-based feature like eyes, nose, mouth and so forth, without any manual annotation or additionalsion datasets? In this paper, we propose a generic…

In this paper, we introduce a model designed to improve the prediction of image-text alignment, targeting the challenge of compositional understanding in current visual-language models. Our approach focuses on generating high-quality…

Cross-domain image-to-image translation should satisfy two requirements: (1) preserve the information that is common to both domains, and (2) generate convincing images covering variations that appear in the target domain. This is…

Contextualized end-to-end automatic speech recognition has been an active research area, with recent efforts focusing on the implicit learning of contextual phrases based on the final loss objective. However, these approaches ignore the…

Pair-wise loss is an approach to metric learning that learns a semantic embedding by optimizing a loss function that encourages images from the same semantic class to be mapped closer than images from different classes. The literature…

Digital histology images are amenable to the application of convolutional neural network (CNN) for analysis due to the sheer size of pixel data present in them. CNNs are generally used for representation learning from small image patches…

Algorithmic image-based diagnosis and prognosis of neurodegenerative diseases on longitudinal data has drawn great interest from computer vision researchers. The current state-of-the-art models for many image classification tasks are based…

Unsupervised image-to-image translation aims at learning the mapping from the source to target domain without using paired images for training. An essential yet restrictive assumption for unsupervised image translation is that the two…

Convolutional Neural Networks (CNNs) were the driving force behind many advancements in Computer Vision research in recent years. This progress has spawned many practical applications and we see an increased need to efficiently move CNNs to…

Automatic building extraction from aerial imagery has several applications in urban planning, disaster management, and change detection. In recent years, several works have adopted deep convolutional neural networks (CNNs) for building…

In text-to-image diffusion models, the cross-attention map of each text token indicates the specific image regions attended. Comparing these maps of syntactically related tokens provides insights into how well the generated image reflects…

Although self-supervised learning enables us to bootstrap the training by exploiting unlabeled data, the generic self-supervised methods for natural images do not sufficiently incorporate the context. For medical images, a desirable method…