相关论文: Instance-Level Data-Use Auditing of Visual ML Mode…

Instance-level recognition (ILR) concerns distinguishing individual instances from one another, with person re-identification as a prominent example. Despite the impressive visual perception capabilities of modern VLMs, we find their…

Vision-based quality assessment in additive manufacturing often requires dedicated machine learning models and application-specific datasets. However, data collection and model training can be expensive and time-consuming. In this paper, we…

Weakly supervised whole slide image classification is usually formulated as a multiple instance learning (MIL) problem, where each slide is treated as a bag, and the patches cut out of it are treated as instances. Existing methods either…

Multiple Instance Learning (MIL) is a sub-domain of classification problems with positive and negative labels and a "bag" of inputs, where the label is positive if and only if a positive element is contained within the bag, and otherwise is…

Large Multimodal Models (LMMs) have made significant breakthroughs with the advancement of instruction tuning. However, while existing models can understand images and videos at a holistic level, they still struggle with instance-level…

Missing data can pose a challenge for machine learning (ML) modeling. To address this, current approaches are categorized into feature imputation and label prediction and are primarily focused on handling missing data to enhance ML…

Commercial large language models are typically deployed as black-box API services, requiring users to trust providers to execute inference correctly and report token usage honestly. We present IMMACULATE, a practical auditing framework that…

The rise of deep learning (DL) has led to a surging demand for training data, which incentivizes the creators of DL models to trawl through the Internet for training materials. Meanwhile, users often have limited control over whether their…

In multiple instance multiple label learning, each sample, a bag, consists of multiple instances. To alleviate labeling complexity, each sample is associated with a set of bag-level labels leaving instances within the bag unlabeled. This…

LSTMs have a proven track record in analyzing sequential data. But what about unordered instance bags, as found under a Multiple Instance Learning (MIL) setting? While not often used for this, we show LSTMs excell under this setting too. In…

Due to the increasing usage of machine learning (ML) techniques in security- and safety-critical domains, such as autonomous systems and medical diagnosis, ensuring correct behavior of ML systems, especially for different corner cases, is…

Machine learning software is being used in many applications (finance, hiring, admissions, criminal justice) having a huge social impact. But sometimes the behavior of this software is biased and it shows discrimination based on some…

Quality control is a key activity performed by manufacturing companies to verify product conformance to the requirements and specifications. Standardized quality control ensures that all the products are evaluated under the same criteria.…

Data visualizations typically show retrospective views of an existing dataset with little or no focus on repeatability. However, consumers of these tools often use insights gleaned from retrospective visualizations as the basis for…

There is a growing trend of applying machine learning methods to medical datasets in order to predict patients' future status. Although some of these methods achieve high performance, challenges still exist in comparing and evaluating…

Weakly supervised instance labeling using only image-level labels, in lieu of expensive fine-grained pixel annotations, is crucial in several applications including medical image analysis. In contrast to conventional instance segmentation…

Instance-level image classification tasks have traditionally relied on single-instance labels to train models, e.g., few-shot learning and transfer learning. However, set-level coarse-grained labels that capture relationships among…

Large language models (LLMs) have facilitated the generation of high-quality, cost-effective synthetic data for developing downstream models and conducting statistical analyses in various domains. However, the increased reliance on…

This paper presents a CLIP-based unsupervised learning method for annotation-free multi-label image classification, including three stages: initialization, training, and inference. At the initialization stage, we take full advantage of the…

Measuring the perception of visual content is a long-standing problem in computer vision. Many mathematical models have been developed to evaluate the look or quality of an image. Despite the effectiveness of such tools in quantifying…