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

Increasing the mini-batch size for stochastic gradient descent offers significant opportunities to reduce wall-clock training time, but there are a variety of theoretical and systems challenges that impede the widespread success of this…

In this paper, we study the applicability of active learning in operative scenarios: more particularly, we consider the well-known contradiction between the active learning heuristics, which rank the pixels according to their uncertainty,…

Service robots can help with many of our daily tasks, especially in those cases where it is inconvenient or unsafe for us to intervene: e.g., under extreme weather conditions or when social distance needs to be maintained. However, before…

LiDAR 3D object detection models are inevitably biased towards their training dataset. The detector clearly exhibits this bias when employed on a target dataset, particularly towards object sizes. However, object sizes vary heavily between…

Transfer learning is an exciting area of Natural Language Processing that has the potential to both improve model performance and increase data efficiency. This study explores the effects of varying quantities of target task training data…

With the growing adoption of AI image generation, in conjunction with the ever-increasing environmental resources demanded by AI, we are urged to answer a fundamental question: What is the environmental impact hidden behind each image we…

Computing has a huge memory problem. The memory system, consisting of multiple technologies at different levels, is responsible for most of the energy consumption, performance bottlenecks, robustness problems, monetary cost, and hardware…

While the importance of automatic image analysis is continuously increasing, recent meta-research revealed major flaws with respect to algorithm validation. Performance metrics are particularly key for meaningful, objective, and transparent…

Image retargeting effectively resizes images by preserving the recognizability of important image regions. Most of retargeting methods rely on good importance maps as a cue to retain or remove certain regions in the input image. In…

To improve the performance on a target task, researchers have fine-tuned language models with an intermediate task before the target task of interest. However, previous works have focused on the pre-trained language models and downstream…

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…

Pixels in image sensors have progressively become smaller, driven by the goal of producing higher-resolution imagery. However, ceteris paribus, a smaller pixel accumulates less light, making image quality worse. This interplay of…

This paper tackles the problem of dynamic scene deblurring. Although end-to-end fully convolutional designs have recently advanced the state-of-the-art in non-uniform motion deblurring, their performance-complexity trade-off is still…

Face recognition approaches often rely on equal image resolution for verifying faces on two images. However, in practical applications, those image resolutions are usually not in the same range due to different image capture mechanisms or…

How to robustly rank the aesthetic quality of given images has been a long-standing ill-posed topic. Such challenge stems mainly from the diverse subjective opinions of different observers about the varied types of content. There is a…

This paper's primary objective is to develop a robust generalist perception model capable of addressing multiple tasks under constraints of computational resources and limited training data. We leverage text-to-image diffusion models…

This paper presents a simple and effective visual prompting method for adapting pre-trained models to downstream recognition tasks. Our method includes two key designs. First, rather than directly adding together the prompt and the image,…

Modern vision models typically rely on fine-tuning general-purpose models pre-trained on large, static datasets. These general-purpose models only capture the knowledge within their pre-training datasets, which are tiny, out-of-date…

We present a refinement framework to boost the performance of pre-trained semi-supervised video object segmentation (VOS) models. Our work is based on scale inconsistency, which is motivated by the observation that existing VOS models…

With the increasing adoption of iris recognition systems and the expansion of large-scale enrollment databases, there is a growing need to efficiently assess iris image quality at the time of acquisition, particularly to model user…