Related papers: Superclass-Guided Representation Disentanglement f…
Self-supervised learning (SSL) has emerged as a powerful technique for learning rich representations from unlabeled data. The data representations are able to capture many underlying attributes of data, and be useful in downstream…
Class-Incremental Learning is a challenging problem in machine learning that aims to extend previously trained neural networks with new classes. This is especially useful if the system is able to classify new objects despite the original…
In many applications, finding adequate labeled data to train predictive models is a major challenge. In this work, we propose methods to use group-level binary labels as weak supervision to train instance-level binary classification models.…
Recent alignment techniques, such as reinforcement learning from human feedback, have been widely adopted to align large language models with human preferences by learning and leveraging reward models. In practice, these models often…
Contrastive vision-language models, such as CLIP, have demonstrated excellent zero-shot capability across semantic recognition tasks, mainly attributed to the training on a large-scale I&1T (one Image with one Text) dataset. This kind of…
Self-supervised learning (SSL) offers a powerful way to learn robust, generalizable representations without labeled data. In music, where labeled data is scarce, existing SSL methods typically use generated supervision and multi-view…
Semi-supervised semantic segmentation (SSSS) faces persistent challenges in effectively leveraging unlabeled data, such as ineffective utilization of pseudo-labels, exacerbation of class imbalance biases, and neglect of prediction…
Classification problems solved with deep neural networks (DNNs) typically rely on a closed world paradigm, and optimize over a single objective (e.g., minimization of the cross-entropy loss). This setup dismisses all kinds of supporting…
Despite the remarkable performance of supervised medical image segmentation models, relying on a large amount of labeled data is impractical in real-world situations. Semi-supervised learning approaches aim to alleviate this challenge using…
The recent success of learning-based algorithms can be greatly attributed to the immense amount of annotated data used for training. Yet, many datasets lack annotations due to the high costs associated with labeling, resulting in degraded…
Aspect Category Detection (ACD) aims to identify implicit and explicit aspects in a given review sentence. The state-of-the-art approaches for ACD use Deep Neural Networks (DNNs) to address the problem as a multi-label classification task.…
Diffusion models have demonstrated remarkable progress in image generation quality, especially when guidance is used to control the generative process. However, guidance requires a large amount of image-annotation pairs for training and is…
Multi-view multi-label learning frequently suffers from simultaneous feature absence and incomplete annotations, due to challenges in data acquisition and cost-intensive supervision. To tackle the complex yet highly practical problem while…
This work presents a new strategy for multi-class classification that requires no class-specific labels, but instead leverages pairwise similarity between examples, which is a weaker form of annotation. The proposed method, meta…
Semantic segmentation of various tissue and nuclei types in histology images is fundamental to many downstream tasks in the area of computational pathology (CPath). In recent years, Deep Learning (DL) methods have been shown to perform well…
Fine-tuning a pretrained language model on a curated dataset can produce spurious correlations between the fine-tuning task and unintended latent factors -- such as misaligned personas or political slant -- that the curation procedure has…
High-quality labeled datasets are essential for deep learning. Traditional manual annotation methods are not only costly and inefficient but also pose challenges in specialized domains where expert knowledge is needed. Self-supervised…
We propose a novel scalable end-to-end pipeline that uses symbolic domain knowledge as constraints for learning a neural network for classifying unlabeled data in a weak-supervised manner. Our approach is particularly well-suited for…
Neural networks trained with (stochastic) gradient descent have an inductive bias towards learning simpler solutions. This makes them highly prone to learning spurious correlations in the training data, that may not hold at test time. In…
How to handle domain shifts when recognizing or segmenting visual data across domains has been studied by learning and vision communities. In this paper, we address domain generalized semantic segmentation, in which the segmentation model…