Related papers: Speeding Up Image Classifiers with Little Companio…

For many machine learning problems, data is abundant and it may be prohibitive to make multiple passes through the full training set. In this context, we investigate strategies for dynamically increasing the effective sample size, when…

We propose a novel image sampling method for differentiable image transformation in deep neural networks. The sampling schemes currently used in deep learning, such as Spatial Transformer Networks, rely on bilinear interpolation, which…

The expanding scale of large neural network models introduces significant challenges, driving efforts to reduce memory usage and enhance computational efficiency. Such measures are crucial to ensure the practical implementation and…

Recent advances in visual generation have made significant strides in producing content of exceptional quality. However, most methods suffer from a fundamental problem - a bottleneck of inference computational efficiency. Most of these…

Model efficiency has become increasingly important in computer vision. In this paper, we systematically study neural network architecture design choices for object detection and propose several key optimizations to improve efficiency.…

Multi-scale resolution training has seen an increased adoption across multiple vision tasks, including classification and detection. Training with smaller resolutions enables faster training at the expense of a drop in accuracy. Conversely,…

Deep convolution networks have proved very successful with big datasets such as the 1000-classes ImageNet. Results show that the error rate increases slowly as the size of the dataset increases. Experiments presented here may explain why…

Visual prompting has recently emerged as an efficient strategy to adapt vision models using lightweight, learnable parameters injected into the input space. However, prior work mainly targets large Vision Transformers and high-resolution…

For the past 5 years, the ILSVRC competition and the ImageNet dataset have attracted a lot of interest from the Computer Vision community, allowing for state-of-the-art accuracy to grow tremendously. This should be credited to the use of…

The problem of high-dimensional and large-scale representation of visual data is addressed from an unsupervised learning perspective. The emphasis is put on discrete representations, where the description length can be measured in bits and…

Machine learning for image classification is an active and rapidly developing field. With the proliferation of classifiers of different sizes and different architectures, the problem of choosing the right model becomes more and more…

Data-augmentation is key to the training of neural networks for image classification. This paper first shows that existing augmentations induce a significant discrepancy between the typical size of the objects seen by the classifier at…

There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the…

In this work, we perform a wide variety of experiments with different deep learning architectures on datasets of limited size. According to our study, we show that model complexity is a critical factor when only a few samples per class are…

Large-scale distributed training of deep neural networks results in models with worse generalization performance as a result of the increase in the effective mini-batch size. Previous approaches attempt to address this problem by varying…

Novel computer vision architectures monopolize the spotlight, but the impact of the model architecture is often conflated with simultaneous changes to training methodology and scaling strategies. Our work revisits the canonical ResNet (He…

Visual Language Models (VLMs) are now increasingly being merged with Large Language Models (LLMs) to enable new capabilities, particularly in terms of improved interactivity and open-ended responsiveness. While these are remarkable…

3D imaging enables accurate diagnosis by providing spatial information about organ anatomy. However, using 3D images to train AI models is computationally challenging because they consist of 10x or 100x more pixels than their 2D…

Existing approaches to improve the performances of convolutional neural networks by optimizing the local architectures or deepening the networks tend to increase the size of models significantly. In order to deploy and apply the neural…

This paper presents a comprehensive evaluation of lightweight deep learning models for image classification, emphasizing their suitability for deployment in resource-constrained environments such as low-memory devices. Five state-of-the-art…