Related papers: Scaling Backwards: Minimal Synthetic Pre-training?

Recent image generation models such as Stable Diffusion have exhibited an impressive ability to generate fairly realistic images starting from a simple text prompt. Could such models render real images obsolete for training image prediction…

Recent self-supervised representation learning techniques have largely closed the gap between supervised and unsupervised learning on ImageNet classification. While the particulars of pretraining on ImageNet are now relatively well…

The recent advances in image transformers have shown impressive results and have largely closed the gap between traditional CNN architectures. The standard procedure is to train on large datasets like ImageNet-21k and then finetune on…

The impressive performance of deep learning architectures is associated with a massive increase in model complexity. Millions of parameters need to be tuned, with training and inference time scaling accordingly, together with energy…

In this paper, we address a key scientific problem in machine learning: Given a training set for an image classification task, can we train a generative model on this dataset to enhance the classification performance? (i.e., closed-set…

Formula-driven supervised learning (FDSL) is a pre-training method that relies on synthetic images generated from mathematical formulae such as fractals. Prior work on FDSL has shown that pre-training vision transformers on such synthetic…

Research in self-supervised learning (SSL) with natural images has progressed rapidly in recent years and is now increasingly being applied to and benchmarked with datasets containing remotely sensed imagery. A common benchmark case is to…

Thanks to the recent development of deep generative models, it is becoming possible to generate high-quality images with both fidelity and diversity. However, the training of such generative models requires a large dataset. To reduce the…

Robot perception systems need to perform reliable image segmentation in real-time on noisy, raw perception data. State-of-the-art segmentation approaches use large CNN models and carefully constructed datasets; however, these models focus…

Visual representation learning hold great promise for robotics, but is severely hampered by the scarcity and homogeneity of robotics datasets. Recent works address this problem by pre-training visual representations on large-scale but…

Meta learning approaches to few-shot classification are computationally efficient at test time, requiring just a few optimization steps or single forward pass to learn a new task, but they remain highly memory-intensive to train. This…

Pre-training general-purpose visual features with convolutional neural networks without relying on annotations is a challenging and important task. Most recent efforts in unsupervised feature learning have focused on either small or highly…

We present a method for synthesizing naturally looking images of multiple people interacting in a specific scenario. These images benefit from the advantages of synthetic data: being fully controllable and fully annotated with any type of…

Indoor scene understanding is central to applications such as robot navigation and human companion assistance. Over the last years, data-driven deep neural networks have outperformed many traditional approaches thanks to their…

The finding that very large networks can be trained efficiently and reliably has led to a paradigm shift in computer vision from engineered solutions to learning formulations. As a result, the research challenge shifts from devising…

Conventional wisdom suggests that pre-training Vision Transformers (ViT) improves downstream performance by learning useful representations. Is this actually true? We investigate this question and find that the features and representations…

Many real-world applications require recognition models that are robust to different operational conditions and modalities, but at the same time run on small embedded devices, with limited hardware. While for normal size models,…

Transfer learning represents a recent paradigm shift in the way we build artificial intelligence (AI) systems. In contrast to training task-specific models, transfer learning involves pre-training deep learning models on a large corpus of…

Humans can robustly learn novel visual concepts even when images undergo various deformations and lose certain information. Mimicking the same behavior and synthesizing deformed instances of new concepts may help visual recognition systems…

We address two questions for training a convolutional neural network (CNN) for hyperspectral image classification: i) is it possible to build a pre-trained network? and ii) is the pre-training effective in furthering the performance? To…