Related papers: MixAtlas: Uncertainty-aware Data Mixture Optimizat…

The high costs of annotating large datasets suggests a need for effectively training CNNs with limited data, and data augmentation is a promising direction. We study foundational augmentation techniques, including Mixed Sample Data…

Natural images exhibit label diversity (clean vs. noisy) in noisy-labeled image classification and prevalence diversity (abundant vs. sparse) in long-tailed image classification. Similarly, medical images in universal lesion detection (ULD)…

Background and objective: Employing deep learning models in critical domains such as medical imaging poses challenges associated with the limited availability of training data. We present a strategy for improving the performance and…

Multimodal large language models (MLLMs) show remarkable potential for scientific reasoning, yet their performance in specialized domains such as microscopy remains limited by the scarcity of domain-specific training data and the difficulty…

We introduce MixTraining, a new training paradigm for object detection that can improve the performance of existing detectors for free. MixTraining enhances data augmentation by utilizing augmentations of different strengths while excluding…

Incorporating self-supervised learning (SSL) before standard supervised learning (SL) has become a widely used strategy to enhance model performance, particularly in data-limited scenarios. However, this approach introduces a trade-off…

We present MIX'EM, a novel solution for unsupervised image classification. MIX'EM generates representations that by themselves are sufficient to drive a general-purpose clustering algorithm to deliver high-quality classification. This is…

Increasingly large imitation learning datasets are being collected with the goal of training foundation models for robotics. However, despite the fact that data selection has been of utmost importance in vision and natural language…

Ensembling fine-tuned models initialized from powerful pre-trained weights is a common strategy to improve robustness under distribution shifts, but it comes with substantial computational costs due to the need to train and store multiple…

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Owing to privacy concerns and heavy data transmission, source-free UDA, exploiting the pre-trained source models…

Training NLP systems typically assumes access to annotated data that has a single human label per example. Given imperfect labeling from annotators and inherent ambiguity of language, we hypothesize that single label is not sufficient to…

Large-scale multimodal pre-trained models like CLIP rely heavily on high-quality training data, yet raw web-crawled datasets are often noisy, misaligned, and redundant, leading to inefficient training and suboptimal generalization. Existing…

Hyperscaling of data and parameter count in LLMs is yielding diminishing improvement when weighed against training costs, underlining a growing need for more efficient finetuning and inference without sacrificing performance. This is…

Semi-supervised learning is a challenging problem which aims to construct a model by learning from a limited number of labeled examples. Numerous methods have been proposed to tackle this problem, with most focusing on utilizing the…

Multimodal learning has rapidly advanced visual understanding, largely via multimodal large language models (MLLMs) that use powerful LLMs as cognitive cores. In visual generation, however, these powerful core models are typically reduced…

Data mixing -- determining the ratios of data from different domains -- is a first-order concern for training language models (LMs). While existing mixing methods show promise, they fall short when applied during real-world LM development.…

Data rebalancing techniques, including oversampling and undersampling, are a common approach to addressing the challenges of imbalanced data. To tackle unresolved problems related to both oversampling and undersampling, we propose a new…

We propose a unified cross-domain transfer learning framework that leverages knowledge from multiple heterogeneous medical imaging datasets to improve performance across segmentation, classification, and object detection tasks. Our approach…

Learned reweighting (LRW) approaches to supervised learning use an optimization criterion to assign weights for training instances, in order to maximize performance on a representative validation dataset. We pose and formalize the problem…

To obtain a language model for a target domain (e.g. math), the current paradigm is to pre-train on a vast amount of generic web text and then fine-tune on the relatively limited amount of target data. Typically, generic data is only mixed…