Related papers: SANER: Annotation-free Societal Attribute Neutrali…

Deep learning classifiers achieve state-of-the-art performance in various risk detection applications. They explore rich semantic representations and are supposed to automatically discover risk behaviors. However, due to the lack of…

No-Reference Image Quality Assessment (NR-IQA) focuses on designing methods to measure image quality in alignment with human perception when a high-quality reference image is unavailable. Most state-of-the-art NR-IQA approaches are…

Adversarial attacks pose a critical security threat to real-world AI systems by injecting human-imperceptible perturbations into benign samples to induce misclassification in deep learning models. While existing detection methods, such as…

Large-scale pre-trained multi-modal models (e.g., CLIP) demonstrate strong zero-shot transfer capability in many discriminative tasks. Their adaptation to zero-shot image-conditioned text generation tasks has drawn increasing interest.…

Contrastive Language-Image Pre-training (CLIP) has significantly boosted the performance of various vision-language tasks by scaling up the dataset with image-text pairs collected from the web. However, the presence of intrinsic noise and…

News recommender systems are hindered by the brief lifespan of articles, as they undergo rapid relevance decay. Recent studies have demonstrated the potential of content-based neural techniques in tackling this problem. However, these…

CLIP models perform remarkably well on zero-shot classification and retrieval tasks. But recent studies have shown that learnt representations in CLIP are not well suited for dense prediction tasks like object detection, semantic…

We tackle societal bias in image-text datasets by removing spurious correlations between protected groups and image attributes. Traditional methods only target labeled attributes, ignoring biases from unlabeled ones. Using text-guided…

This paper presents a new framework for open-vocabulary semantic segmentation with the pre-trained vision-language model, named Side Adapter Network (SAN). Our approach models the semantic segmentation task as a region recognition problem.…

Contrastive language-image pre-training (CLIP) is a powerful vision-language model that has shown great benefits for various tasks. However, we have identified some issues with its explainability, which undermine its credibility and limit…

We propose a novel reduction-to-binary (R2B) approach that enforces demographic parity for multiclass classification with non-binary sensitive attributes via a reduction to a sequence of binary debiasing tasks. We prove that R2B satisfies…

Dataset bias is a critical challenge in machine learning since it often leads to a negative impact on a model due to the unintended decision rules captured by spurious correlations. Although existing works often handle this issue based on…

Contrastive Language-Image Pretraining (CLIP) achieves strong generalization in vision-language tasks by aligning images and texts in a shared embedding space. However, recent findings show that CLIP-like models still underutilize…

Language-image pre-training is an effective technique for learning powerful representations in general domains. However, when directly turning to person representation learning, these general pre-training methods suffer from unsatisfactory…

Biases in the dataset often enable the model to achieve high performance on in-distribution data, while poorly performing on out-of-distribution data. To mitigate the detrimental effect of the bias on the networks, previous works have…

As one of the fundamental video tasks in computer vision, Open-Vocabulary Action Recognition (OVAR) recently gains increasing attention, with the development of vision-language pre-trainings. To enable generalization of arbitrary classes,…

The CLIP model has demonstrated significant advancements in aligning visual and language modalities through large-scale pre-training on image-text pairs, enabling strong zero-shot classification and retrieval capabilities on various…

Severe data imbalance naturally exists among web-scale vision-language datasets. Despite this, we find CLIP pre-trained thereupon exhibits notable robustness to the data imbalance compared to supervised learning, and demonstrates…

Real-world datasets inevitably contain biases that arise from different sources or conditions during data collection. Consequently, such inconsistency itself acts as a confounding factor that disturbs the cluster analysis. Existing methods…

Text-driven image manipulation is developed since the vision-language model (CLIP) has been proposed. Previous work has adopted CLIP to design a text-image consistency-based objective to address this issue. However, these methods require…