Related papers: Does progress on ImageNet transfer to real-world d…

Is he/she my type or not? The answer to this question depends on the personal preferences of the one asking it. The individual process of obtaining a full answer may generally be difficult and time consuming, but often an approximate answer…

Successfully training end-to-end deep networks for real motion deblurring requires datasets of sharp/blurred image pairs that are realistic and diverse enough to achieve generalization to real blurred images. Obtaining such datasets remains…

With the rapid advancement of generative models, highly realistic image synthesis has posed new challenges to digital security and media credibility. Although AI-generated image detection methods have partially addressed these concerns, a…

Models trained on synthetic images often face degraded generalization to real data. As a convention, these models are often initialized with ImageNet pre-trained representation. Yet the role of ImageNet knowledge is seldom discussed despite…

This paper deals with deep transductive learning, and proposes TransBoost as a procedure for fine-tuning any deep neural model to improve its performance on any (unlabeled) test set provided at training time. TransBoost is inspired by a…

What can neural networks learn about the visual world when provided with only a single image as input? While any image obviously cannot contain the multitudes of all existing objects, scenes and lighting conditions - within the space of all…

Saliency map estimation in computer vision aims to estimate the locations where people gaze in images. Since people tend to look at objects in images, the parameters of the model pretrained on ImageNet for image classification are useful…

Capturing and labeling camera images in the real world is an expensive task, whereas synthesizing labeled images in a simulation environment is easy for collecting large-scale image data. However, learning from only synthetic images may not…

As the most basic application and implementation of deep learning, image classification has grown in popularity. Various datasets are provided by renowned data science communities for benchmarking machine learning algorithms and pre-trained…

This paper considers image change detection with only a small number of samples, which is a significant problem in terms of a few annotations available. A major impediment of image change detection task is the lack of large annotated…

In medical image segmentation tasks, the scarcity of labeled training data poses a significant challenge when training deep neural networks. When using U-Net-style architectures, it is common practice to address this problem by pretraining…

There is evidence that transformers offer state-of-the-art recognition performance on tasks involving overhead imagery (e.g., satellite imagery). However, it is difficult to make unbiased empirical comparisons between competing deep…

In this work we examine the performance enhancement in classification of medical imaging data when image features are combined with associated non-image data. We compare the performance of eight state-of-the-art deep neural networks in…

Recent advances in image-based saliency prediction are approaching gold standard performance levels on existing benchmarks. Despite this success, we show that predicting fixations across multiple saliency datasets remains challenging due to…

Motivation: In recent years, image-based biological assays have steadily become high-throughput, sparking a need for fast automated methods to extract biologically-meaningful information from hundreds of thousands of images. Taking…

Recent text-to-image (T2I) generation models have achieved remarkable sucess by training on billion-scale datasets, following a `bigger is better' paradigm that prioritizes data quantity over availability (closed vs open source) and…

This paper addresses the task of relative camera pose estimation from raw image pixels, by means of deep neural networks. The proposed RPNet network takes pairs of images as input and directly infers the relative poses, without the need of…

Deep learning approaches have become the standard solution to many problems in computer vision and robotics, but obtaining sufficient training data in high enough quality is challenging, as human labor is error prone, time consuming, and…

Much progress has been made on the task of learning-based 3D point cloud registration, with existing methods yielding outstanding results on standard benchmarks, such as ModelNet40, even in the partial-to-partial matching scenario.…

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,…