Related papers: Benchmarking a Benchmark: How Reliable is MS-COCO?

This paper considers the task of matching images and sentences by learning a visual-textual embedding space for cross-modal retrieval. Finding such a space is a challenging task since the features and representations of text and image are…

Annotated images are required for both supervised model training and evaluation in image classification. Manually annotating images is arduous and expensive, especially for multi-labeled images. A recent trend for conducting such laboursome…

Despite the recent trend of developing and applying neural source code models to software engineering tasks, the quality of such models is insufficient for real-world use. This is because there could be noise in the source code corpora used…

Contextual information is a valuable cue for Deep Neural Networks (DNNs) to learn better representations and improve accuracy. However, co-occurrence bias in the training dataset may hamper a DNN model's generalizability to unseen scenarios…

Underwater image enhancement is such an important vision task due to its significance in marine engineering and aquatic robot. It is usually work as a pre-processing step to improve the performance of high level vision tasks such as…

ImageNet-1K serves as the primary dataset for pretraining deep learning models for computer vision tasks. ImageNet-21K dataset, which is bigger and more diverse, is used less frequently for pretraining, mainly due to its complexity, low…

The purpose of this project was to collect and analyse data about the comparability and real-life applicability of published results focusing on Microsoft Windows malware, more specifically the impact of dataset size and testing dataset…

This paper presents a systematic literature review of image datasets for document image analysis, focusing on historical documents, such as handwritten manuscripts and early prints. Finding appropriate datasets for historical document…

High-quality pixel-level annotations of medical images are essential for supervised segmentation tasks, but obtaining such annotations is costly and requires medical expertise. To address this challenge, we propose a novel coarse-to-fine…

Dataset bias is a well known problem in object recognition domain. This issue, nonetheless, is rarely explored in face alignment research. In this study, we show that dataset plays an integral part of face alignment performance.…

Over the last years, word and sentence embeddings have established as text preprocessing for all kinds of NLP tasks and improved the performances significantly. Unfortunately, it has also been shown that these embeddings inherit various…

Meta-learning provides a popular and effective family of methods for data-efficient learning of new tasks. However, several important issues in meta-learning have proven hard to study thus far. For example, performance degrades in…

Training models on highly unbalanced data is admitted to be a challenging task for machine learning algorithms. Current studies on deep learning mainly focus on data sets with balanced class labels or unbalanced data, but with massive…

In this paper, we design a benchmark task and provide the associated datasets for recognizing face images and link them to corresponding entity keys in a knowledge base. More specifically, we propose a benchmark task to recognize one…

Constructing an organized dataset comprised of a large number of images and several captions for each image is a laborious task, which requires vast human effort. On the other hand, collecting a large number of images and sentences…

There are several issues with the existing general machine translation or natural language generation evaluation metrics, and question-answering (QA) systems are indifferent in that context. To build robust QA systems, we need the ability…

With the rapidly increasing interest in machine learning based solutions for automatic image annotation, the availability of reference annotations for algorithm training is one of the major bottlenecks in the field. Crowdsourcing has…

In recent years, image and video manipulations with Deepfake have become a severe concern for security and society. Many detection models and datasets have been proposed to detect Deepfake data reliably. However, there is an increased…

We propose a meta-learning method for learning from multiple noisy annotators. In many applications such as crowdsourcing services, labels for supervised learning are given by multiple annotators. Since the annotators have different skills…

We present a novel data-efficient semi-supervised framework to improve the generalization of image captioning models. Constructing a large-scale labeled image captioning dataset is an expensive task in terms of labor, time, and cost. In…