Related papers: Size matters: performance declines if your pixels …

This work investigates the ``small-vs-large gap'', where repeating on fewer samples can lead to compute saving during training compared to using a larger dataset. This is observed across algorithmic tasks, architectures and optimizers and…

Energy systems models, critical for power sector decision support, incur non-linear memory and runtime penalties when scaling up under typical formulations. Even hardware improvements cannot make large models tractable, requiring omission…

In previous works, a mobile application was developed using an unmodified commercial off-the-shelf smartphone to recognize whole-body exercises. The working principle was based on the ultrasound Doppler sensing with the device built-in…

Having a sufficient quantity of quality data is a critical enabler of training effective machine learning models. Being able to effectively determine the adequacy of a dataset prior to training and evaluating a model's performance would be…

We study the scaling properties of latent diffusion models (LDMs) with an emphasis on their sampling efficiency. While improved network architecture and inference algorithms have shown to effectively boost sampling efficiency of diffusion…

Overlay measurements are a critical part of modern semiconductor fabrication, but overlay targets have not scaled down in the way devices have. In this work, we produce overlay targets with very small footprint, consisting of just a few…

Uncertainty visualizations often emphasize point estimates to support magnitude estimates or decisions through visual comparison. However, when design choices emphasize means, users may overlook uncertainty information and misinterpret…

Generalization of deep-learning-based (DL) computer vision algorithms to various image perturbations is hard to establish and remains an active area of research. The majority of past analyses focused on the images already captured, whereas…

Graphical perception studies typically measure visualization encoding effectiveness using the error of an "average observer", leading to canonical rankings of encodings for numerical attributes: e.g., position > area > angle > volume. Yet…

Current automatic vision systems face two major challenges: scalability and extreme variability of appearance. First, the computational time required to process an image typically scales linearly with the number of pixels in the image,…

Precise perception of the environment is essential in highly automated driving systems, which rely on machine learning tasks such as object detection and segmentation. Compression of sensor data is commonly used for data handling, while…

Reducing the data footprint of visual content via image compression is essential to reduce storage requirements, but also to reduce the bandwidth and latency requirements for transmission. In particular, the use of compressed images allows…

Metric magnitude is a measure of the "size" of point clouds with many desirable geometric properties. It has been adapted to various mathematical contexts and recent work suggests that it can enhance machine learning and optimization…

Increased access to mobile devices motivates the need to design communicative visualizations that are responsive to varying screen sizes. However, relatively little design guidance or tooling is currently available to authors. We contribute…

Scale is often attributed as one of the factors that cause an increase in the performance of LLMs, resulting in models with billion and trillion parameters. One of the limitations of such large models is the high computational requirements…

Deep neural networks have been used in various fields, but their internal behavior is not well known. In this study, we discuss two counterintuitive behaviors of convolutional neural networks (CNNs). First, we evaluated the size of the…

Despite extensive research into adversarial attacks, we do not know how adversarial attacks affect image pixels. Knowing how image pixels are affected by adversarial attacks has the potential to lead us to better adversarial defenses.…

Power consumption plays a crucial role in on-device streaming speech recognition, significantly influencing the user experience. This study explores how the configuration of weight parameters in speech recognition models affects their…

Recent developments in large-scale machine learning suggest that by scaling up data, model size and training time properly, one might observe that improvements in pre-training would transfer favorably to most downstream tasks. In this work,…

Training large-scale models under given resources requires careful design of parallelism strategies. In particular, the efficiency notion of critical batch size (CBS), concerning the compromise between time and compute, marks the threshold…