Related papers: ASPIRE: Language-Guided Data Augmentation for Impr…

Deep neural networks trained with Empirical Risk Minimization (ERM) perform well when both training and test data come from the same domain, but they often fail to generalize to out-of-distribution samples. In image classification, these…

The evaluation of machine-generated image captions poses an interesting yet persistent challenge. Effective evaluation measures must consider numerous dimensions of similarity, including semantic relevance, visual structure, object…

As a fundamental visual attribute, image complexity significantly influences both human perception and the performance of computer vision models. However, accurately assessing and quantifying image complexity remains a challenging task. (1)…

Recently, contrastive learning has achieved great results in self-supervised learning, where the main idea is to push two augmentations of an image (positive pairs) closer compared to other random images (negative pairs). We argue that not…

While image-text foundation models have succeeded across diverse downstream tasks, they still face challenges in the presence of spurious correlations between the input and label. To address this issue, we propose a simple three-step…

Automatic Speech Recognition (ASR) models demonstrate outstanding performance on high-resource languages but face significant challenges when applied to low-resource languages due to limited training data and insufficient cross-lingual…

Machine learning models are increasingly being utilized across various fields and tasks due to their outstanding performance and strong generalization capabilities. Nonetheless, their success hinges on the availability of large volumes of…

Human-centric visual analysis plays a pivotal role in diverse applications, including surveillance, healthcare, and human-computer interaction. With the emergence of large-scale unlabeled human image datasets, there is an increasing need…

Robustness has become a critical attribute for the deployment of RAG systems in real-world applications. Existing research focuses on robustness to explicit noise (e.g., document semantics) but overlooks implicit noise (spurious features).…

Deep neural networks trained via empirical risk minimisation often exhibit significant performance disparities across groups, particularly when group and task labels are spuriously correlated (e.g., "grassy background" and "cows"). Existing…

Although an object may appear in numerous contexts, we often describe it in a limited number of ways. Language allows us to abstract away visual variation to represent and communicate concepts. Building on this intuition, we propose an…

While deep neural networks can achieve state-of-the-art performance in many tasks, these models are more fragile than they appear. They are prone to learning spurious correlations in their training data, leading to surprising failure cases.…

We propose an information-theoretic bias measurement technique through a causal interpretation of spurious correlation, which is effective to identify the feature-level algorithmic bias by taking advantage of conditional mutual information.…

The growing reliance on deep learning models in safety-critical domains such as healthcare and autonomous navigation underscores the need for defenses that are both robust to adversarial perturbations and transparent in their…

Although soft prompt tuning is effective in efficiently adapting Vision-Language (V&L) models for downstream tasks, it shows limitations in dealing with distribution shifts. We address this issue with Attribute-Guided Prompt Tuning (ArGue),…

Data mixing augmentation has proved effective in training deep models. Recent methods mix labels mainly based on the mixture proportion of image pixels. As the main discriminative information of a fine-grained image usually resides in…

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…

Vision-Language Pretraining (VLP) has achieved remarkable success across various downstream tasks, but such gains are largely driven by scaling up on training data. Yet, literature methods treat image-text pairs as isolated training…

Attribute labeling at large scale is typically incomplete and partial, posing significant challenges to model optimization. Existing attribute learning methods often treat the missing labels as negative or simply ignore them all during…

Most unsupervised domain adaptation (UDA) methods assume that labeled source images are available during model adaptation. However, this assumption is often infeasible owing to confidentiality issues or memory constraints on mobile devices.…