Related papers: A Simple Recipe for Language-guided Domain General…

Recurrent neural networks have recently been used for learning to describe images using natural language. However, it has been observed that these models generalize poorly to scenes that were not observed during training, possibly depending…

Learning domain-invariant visual representations is important to train a model that can generalize well to unseen target task domains. Recent works demonstrate that text descriptions contain high-level class-discriminative information and…

Modern deep neural networks suffer from performance degradation when evaluated on testing data under different distributions from training data. Domain generalization aims at tackling this problem by learning transferable knowledge from…

Visual recognition systems are meant to work in the real world. For this to happen, they must work robustly in any visual domain, and not only on the data used during training. Within this context, a very realistic scenario deals with…

This paper offers a new perspective to ease the challenge of domain generalization, which involves maintaining robust results even in unseen environments. Our design focuses on the decision-making process in the final classifier layer.…

Domain-invariant representation learning is a powerful method for domain generalization. Previous approaches face challenges such as high computational demands, training instability, and limited effectiveness with high-dimensional data,…

As a recent noticeable topic, domain generalization aims to learn a generalizable model on multiple source domains, which is expected to perform well on unseen test domains. Great efforts have been made to learn domain-invariant features by…

How well do neural networks generalize? Even for grammar induction tasks, where the target generalization is fully known, previous works have left the question open, testing very limited ranges beyond the training set and using different…

Can a generative model be trained to produce images from a specific domain, guided by a text prompt only, without seeing any image? In other words: can an image generator be trained "blindly"? Leveraging the semantic power of large scale…

We develop an algorithm for adapting a semantic segmentation model that is trained using a labeled source domain to generalize well in an unlabeled target domain. A similar problem has been studied extensively in the unsupervised domain…

Many fine-grained classification tasks, like rare animal identification, have limited training data and consequently classifiers trained on these datasets often fail to generalize to variations in the domain like changes in weather or…

Recent work to enhance data partitioning strategies for more realistic model evaluation face challenges in providing a clear optimal choice. This study addresses these challenges, focusing on morphological segmentation and synthesizing…

Semantic segmentation algorithms require access to well-annotated datasets captured under diverse illumination conditions to ensure consistent performance. However, poor visibility conditions at varying illumination conditions result in…

Recent research has revealed that neural language models at scale suffer from poor temporal generalization capability, i.e., the language model pre-trained on static data from past years performs worse over time on emerging data. Existing…

The problem of domain generalization is to learn, given data from different source distributions, a model that can be expected to generalize well on new target distributions which are only seen through unlabeled samples. In this paper, we…

Language segmentation consists in finding the boundaries where one language ends and another language begins in a text written in more than one language. This is important for all natural language processing tasks. The problem can be solved…

End-to-end trained Recurrent Neural Networks (RNNs) have been successfully applied to numerous problems that require processing sequences, such as image captioning, machine translation, and text recognition. However, RNNs often struggle to…

Domain generalization is the task of learning models that generalize to unseen target domains. We propose a simple yet effective method for domain generalization, named cross-domain ensemble distillation (XDED), that learns domain-invariant…

Fine-tuning large pretrained vision-language models (VLMs) has emerged as a prevalent paradigm for downstream adaptation, yet it faces a critical trade-off between domain specificity and domain generalization (DG) ability. Current methods…

Recent progress has shown that large-scale pre-training using contrastive image-text pairs can be a promising alternative for high-quality visual representation learning from natural language supervision. Benefiting from a broader source of…