Related papers: Are All Training Examples Created Equal? An Empiri…
Standard evaluations of Bayesian deep learning methods assume that metric estimates are reliable, but we show this assumption fails under data scarcity. Method rankings are not only unreliable at small $n$, but also dataset-dependent in…
The paper provides a survey of the development of machine-learning techniques for video analysis. The survey provides a summary of the most popular deep learning methods used for human activity recognition. We discuss how popular…
In the era of "big data", it is becoming more of a challenge to not only build state-of-the-art predictive models, but also gain an understanding of what's really going on in the data. For example, it is often of interest to know which, if…
Collecting more diverse and representative training data is often touted as a remedy for the disparate performance of machine learning predictors across subpopulations. However, a precise framework for understanding how dataset properties…
Object grasping is critical for many applications, which is also a challenging computer vision problem. However, for the clustered scene, current researches suffer from the problems of insufficient training data and the lacking of…
Full-parameter fine-tuning of large language models is constrained by substantial GPU memory requirements. Low-rank adaptation methods mitigate this challenge by updating only a subset of parameters. However, these approaches often limit…
During the operation of a system including a deep neural network (DNN), new input values that were not included in the training dataset are given to the DNN. In such a case, the DNN may be incrementally trained with the new input values;…
Machine learning has revolutionized numerous domains, playing a crucial role in driving advancements and enabling data-centric processes. The significance of data in training models and shaping their performance cannot be overstated. Recent…
With the proliferation of algorithmic decision-making, increased scrutiny has been placed on these systems. This paper explores the relationship between the quality of the training data and the overall fairness of the models trained with…
While large text-to-image models are able to synthesize "novel" images, these images are necessarily a reflection of the training data. The problem of data attribution in such models -- which of the images in the training set are most…
We propose a new metric ($m$-coherence) to experimentally study the alignment of per-example gradients during training. Intuitively, given a sample of size $m$, $m$-coherence is the number of examples in the sample that benefit from a small…
Learning curves are a measure for how the performance of machine learning models improves given a certain volume of training data. Over a wide variety of applications and models it was observed that learning curves follow -- to a large…
In the Internet, ubiquitous presence of redundant, unedited, raw videos has made video summarization an important problem. Traditional methods of video summarization employ a heuristic set of hand-crafted features, which in many cases fail…
The deep neural networks used in modern computer vision systems require enormous image datasets to train them. These carefully-curated datasets typically have a million or more images, across a thousand or more distinct categories. The…
The era of huge data necessitates highly efficient machine learning algorithms. Many common machine learning algorithms, however, rely on computationally intensive subroutines that are prohibitively expensive on large datasets. Oftentimes,…
Self-supervised learning for pre-training (SSP) can help the network learn better low-level features, especially when the size of the training set is small. In contrastive pre-training, the network is pre-trained to distinguish between…
Deep learning is now the gold standard in computer vision-based quality inspection systems. In order to detect defects, supervised learning is often utilized, but necessitates a large amount of annotated images, which can be costly:…
Synthetic training data has gained prominence in numerous learning tasks and scenarios, offering advantages such as dataset augmentation, generalization evaluation, and privacy preservation. Despite these benefits, the efficiency of…
Fine-grained visual categorization is a classification task for distinguishing categories with high intra-class and small inter-class variance. While global approaches aim at using the whole image for performing the classification,…
Deep learning has achieved remarkable results in many computer vision tasks. Deep neural networks typically rely on large amounts of training data to avoid overfitting. However, labeled data for real-world applications may be limited. By…