相关论文: Detecting Performance Degradation under Data Shift…

The safety alignment ability of Vision-Language Models (VLMs) is prone to be degraded by the integration of the vision module compared to its LLM backbone. We investigate this phenomenon, dubbed as ''safety alignment degradation'' in this…

Pre-trained vision-language models (VLMs) have shown impressive performance on various downstream tasks by utilizing knowledge learned from large data. In general, the performance of VLMs on target tasks can be further improved by prompt…

Vision-language models such as CLIP have shown great impact on diverse downstream tasks for zero-shot or label-free predictions. However, when it comes to low-level vision such as image restoration their performance deteriorates…

Chronic pain is a global health challenge affecting millions of individuals, making it essential for physicians to have reliable and objective methods to measure the functional impact of clinical treatments. Traditionally used methods, like…

This paper deals with system representations in finite-sample signal subspaces and their application to data-driven fault detection. The first part addresses concepts of finite-sample image and kernel system representations and, associated…

LayerNorm is pivotal in Vision Transformers (ViTs), yet its fine-tuning dynamics under data scarcity and domain shifts remain underexplored. This paper shows that shifts in LayerNorm parameters after fine-tuning (LayerNorm shifts) are…

Vision foundation models trained on discretely sampled images achieve strong performance on classification benchmarks, yet whether their representations encode the continuous processes underlying their training data remains unclear. This…

Data contamination undermines the validity of Large Language Model evaluation by enabling models to rely on memorized benchmark content rather than true generalization. While prior work has proposed contamination detection methods, these…

With the advent of Vision-Language Models (VLMs), medical artificial intelligence (AI) has experienced significant technological progress and paradigm shifts. This survey provides an extensive review of recent advancements in Medical…

Vision-language foundation models (VLMs) show promise for diverse imaging tasks but often underperform on medical benchmarks. Prior efforts to improve performance include model finetuning, which requires large domain-specific datasets and…

In robot scientific laboratories, visual anomaly detection is important for the timely identification and resolution of potential faults or deviations. It has become a key factor in ensuring the stability and safety of experimental…

Distribution shift, a change in the statistical properties of data over time, poses a critical challenge for deep learning anomaly detection systems. Existing anomaly detection systems often struggle to adapt to these shifts. Specifically,…

Vision-language models (VLMs) are gaining attention in medical image analysis. These are pre-trained on large, heterogeneous data sources, yielding rich and transferable representations. Notably, the combination of modality-specialized VLMs…

Trained on a vast amount of data, Large Language models (LLMs) have achieved unprecedented success and generalization in modeling fairly complex textual inputs in the abstract space, making them powerful tools for zero-shot learning. Such…

General-purpose Large Vision-Language Models (LVLMs), despite their massive scale, often falter in dermatology due to "diffuse attention" - the inability to disentangle subtle pathological lesions from background noise. In this paper, we…

Classifier predictions often rely on the assumption that new observations come from the same distribution as training data. When the underlying distribution changes, so does the optimal classification rule, and performance may degrade. We…

Image classification is one of the most fundamental capabilities of machine vision intelligence. In this work, we revisit the image classification task using visually-grounded language models (VLMs) such as GPT-4V and LLaVA. We find that…

Deep learning-based methods have become the de facto standard for industrial defect detection. However, their data-hungry nature and inherent "black-box" characteristics often lead to performance bottlenecks and limited trustworthiness in…

A failure detection system is the first step towards predictive maintenance strategies. A popular data-driven method to detect incipient failures and anomalies is the training of normal behaviour models by applying a machine learning…

Prompt injection poses a critical threat to the safe deployment of large language models, yet existing detection approaches are typically evaluated under limited settings that do not reflect real-world operating constraints. In this work,…