Related papers: Towards Reliable Zero Shot Classification in Self-…

Zero-shot anomaly detection (ZSAD) aims to detect anomalies without any target domain training samples, relying solely on external auxiliary data. Existing CLIP-based methods attempt to activate the model's ZSAD potential via handcrafted or…

Semantic segmentation is a fundamental task in medical image analysis and autonomous driving and has a problem with the high cost of annotating the labels required in training. To address this problem, semantic segmentation methods based on…

Contrastive Language-Image Pre-training (CLIP) has been the cornerstone for zero-shot classification, text-image retrieval, and text-image generation by aligning image and text modalities. Despite its widespread adoption, a significant…

We propose a novel taxonomy for bias evaluation of discriminative foundation models, such as Contrastive Language-Pretraining (CLIP), that are used for labeling tasks. We then systematically evaluate existing methods for mitigating bias in…

Methods based on Contrastive Language-Image Pre-training (CLIP) are nowadays extensively used in support of vision-and-language tasks involving remote sensing data, such as cross-modal retrieval. The adaptation of CLIP to this specific…

Recent advancements in large-scale visual-language pre-trained models have led to significant progress in zero-/few-shot anomaly detection within natural image domains. However, the substantial domain divergence between natural and medical…

Vision-language models like CLIP have demonstrated remarkable zero-shot capabilities in classification and retrieval. However, these models often struggle with compositional reasoning - the ability to understand the relationships between…

Zero-shot inference, where pre-trained models perform tasks without specific training data, is an exciting emergent ability of large models like CLIP. Although there has been considerable exploration into enhancing zero-shot abilities in…

Conformal prediction has emerged as an effective strategy for uncertainty quantification by modifying a model to output sets of labels instead of a single label. These prediction sets come with the guarantee that they contain the true label…

Large-scale vision 2D vision language models, such as CLIP can be aligned with a 3D encoder to learn generalizable (open-vocabulary) 3D vision models. However, current methods require supervised pre-training for such alignment, and the…

Medical imaging classifiers can achieve high predictive accuracy, but quantifying their uncertainty remains an unresolved challenge, which prevents their deployment in medical clinics. We present an algorithm that can modify any classifier…

In the field of medical decision-making, precise anomaly detection in medical imaging plays a pivotal role in aiding clinicians. However, previous work is reliant on large-scale datasets for training anomaly detection models, which…

Few-shot object detection, which focuses on detecting novel objects with few labels, is an emerging challenge in the community. Recent studies show that adapting a pre-trained model or modified loss function can improve performance. In this…

Commit Classification (CC) is an important task in software maintenance, which helps software developers classify code changes into different types according to their nature and purpose. It allows developers to understand better how their…

Contrastive Language-Image Pre-training (CLIP) stands as one of the most effective and scalable methods for training transferable vision models using paired image and text data. CLIP models are trained using contrastive loss, which…

Zero-shot anomaly segmentation using pre-trained foundation models is a promising approach that enables effective algorithms without expensive, domain-specific training or fine-tuning. Ensuring that these methods work across various…

In semi-supervised learning, the paradigm of self-training refers to the idea of learning from pseudo-labels suggested by the learner itself. Across various domains, corresponding methods have proven effective and achieve state-of-the-art…

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…

Despite the recent success of image-text contrastive models like CLIP and SigLIP, these models often struggle with vision-centric tasks that demand high-fidelity image understanding, such as counting, depth estimation, and fine-grained…

Multi-modal models require aligned, shared embedding spaces. However, common CLIP-based approaches need large amounts of samples and do not natively support 3D or tabular data, both of which are crucial in the medical domain. To address…