Related papers: Curriculum Learning with Diversity for Supervised …

Data selection in instruction tuning emerges as a pivotal process for acquiring high-quality data and training instruction-following large language models (LLMs), but it is still a new and unexplored research area for vision-language models…

Image captioning models require the high-level generalization ability to describe the contents of various images in words. Most existing approaches treat the image-caption pairs equally in their training without considering the differences…

Curriculum learning and self-paced learning are the training strategies that gradually feed the samples from easy to more complex. They have captivated increasing attention due to their excellent performance in robotic vision. Most recent…

Image-caption pretraining has been quite successfully used for downstream vision tasks like zero-shot image classification and object detection. However, image-caption pretraining is still a hard problem -- it requires multiple concepts…

We present a simple yet efficient approach capable of training deep neural networks on large-scale weakly-supervised web images, which are crawled raw from the Internet by using text queries, without any human annotation. We develop a…

Traditional methods for view-invariant learning rely on controlled multi-view training data with minimal scene clutter. However, they struggle with in-the-wild videos that exhibit extreme viewpoint differences and share little visual…

Recent automatic curriculum learning algorithms, and in particular Teacher-Student algorithms, rely on the notion of learning progress, making the assumption that the good next tasks are the ones on which the learner is making the fastest…

Not all instances in a data set are equally beneficial for inferring a model of the data. Some instances (such as outliers) are detrimental to inferring a model of the data. Several machine learning techniques treat instances in a data set…

Deep learning architectures exhibit a critical drop of performance due to catastrophic forgetting when they are required to incrementally learn new tasks. Contemporary incremental learning frameworks focus on image classification and object…

In this work, we study different approaches to self-supervised pretraining of object detection models. We first design a general framework to learn a spatially consistent dense representation from an image, by randomly sampling and…

Coreset selection aims to identify a small yet highly informative subset of data, thereby enabling more efficient model training while reducing storage overhead. Recently, this capability has been leveraged to tackle the challenges of…

We introduce the problem of curriculum discovery and describe a curriculum learning framework capable of discovering effective curricula in a curriculum space based on prior knowledge about sample difficulty. Using annotation entropy and…

Learning visual representations with self-supervised learning has become popular in computer vision. The idea is to design auxiliary tasks where labels are free to obtain. Most of these tasks end up providing data to learn specific kinds of…

The immense success of deep learning based methods in computer vision heavily relies on large scale training datasets. These richly annotated datasets help the network learn discriminative visual features. Collecting and annotating such…

Common cross-validation (CV) methods like k-fold cross-validation or Monte-Carlo cross-validation estimate the predictive performance of a learner by repeatedly training it on a large portion of the given data and testing on the remaining…

This paper presents a simple unsupervised visual representation learning method with a pretext task of discriminating all images in a dataset using a parametric, instance-level classifier. The overall framework is a replica of a supervised…

The ability to cheaply train text classifiers is critical to their use in information retrieval, content analysis, natural language processing, and other tasks involving data which is partly or fully textual. An algorithm for sequential…

Curriculum learning is often employed in deep reinforcement learning to let the agent progress more quickly towards better behaviors. Numerical methods for curriculum learning in the literature provides only initial heuristic solutions,…

Vision-language instruction tuning achieves two main purposes: learning visual concepts and learning visual skills. In this paper, we found that vision-language benchmarks fall into the dichotomy of mainly benefiting from training on…

Curriculum Data Augmentation (CDA) improves neural models by presenting synthetic data with increasing difficulties from easy to hard. However, traditional CDA simply treats the ratio of word perturbation as the difficulty measure and goes…