Related papers: Data augmentation to improve robustness of image c…
Decoder-only discrete-token language models have recently achieved significant success in automatic speech recognition. However, systematic analyses of how different modalities impact performance in specific scenarios remain limited. In…
In active learning, the focus is mainly on the selection strategy of unlabeled data for enhancing the generalization capability of the next learning cycle. For this, various uncertainty measurement methods have been proposed. On the other…
Conventional image classifiers are trained by randomly sampling mini-batches of images. To achieve state-of-the-art performance, practitioners use sophisticated data augmentation schemes to expand the amount of training data available for…
This paper deals with enhancement of images with poor contrast and detection of background. Proposes a frame work which is used to detect the background in images characterized by poor contrast. Image enhancement has been carried out by the…
Motion blur is a frequently observed image artifact, especially under insufficient illumination where exposure time has to be prolonged so as to collect more photons for a bright enough image. Rather than simply removing such blurring…
Data augmentation is a powerful technique to increase the diversity of data, which can effectively improve the generalization ability of neural networks in image recognition tasks. Recent data mixing based augmentation strategies have…
Object detection and semantic segmentation with the 3D lidar point cloud data require expensive annotation. We propose a data augmentation method that takes advantage of already annotated data multiple times. We propose an augmentation…
Existing video compression (VC) methods primarily aim to reduce the spatial and temporal redundancies between consecutive frames in a video while preserving its quality. In this regard, previous works have achieved remarkable results on…
End-to-end trainable models have reached the performance of traditional handcrafted compression techniques on videos and images. Since the parameters of these models are learned over large training sets, they are not optimal for any given…
Regional dropout strategies have been proposed to enhance the performance of convolutional neural network classifiers. They have proved to be effective for guiding the model to attend on less discriminative parts of objects (e.g. leg as…
This work presents an analysis of the efficiency of image augmentations for the face recognition problem from limited data. We considered basic manipulations, generative methods, and their combinations for augmentations. Our results show…
This paper presents a comprehensive study and improvement of the Restormer architecture for high-resolution image motion deblurring. We introduce architectural modifications that reduce model complexity by 18.4% while maintaining or…
Deep convolutional neural networks have achieved exceptional results on multiple detection and recognition tasks. However, the performance of such detectors are often evaluated in public benchmarks under constrained and non-realistic…
Data augmentation has proved extremely useful by increasing training data variance to alleviate overfitting and improve deep neural networks' generalization performance. In medical image analysis, a well-designed augmentation policy usually…
Data augmentation has become an integral part of deep learning, as it is known to improve the generalization capabilities of neural networks. Since the most effective set of image transformations differs between tasks and domains, automatic…
Deep neural networks are often not robust to semantically-irrelevant changes in the input. In this work we address the issue of robustness of state-of-the-art deep convolutional neural networks (CNNs) against commonly occurring distortions…
Image-Text Retrieval (ITR) systems are central to multimodal information access, with Vision-Language Models (VLMs) showing strong performance on standard benchmarks. However, these benchmarks predominantly rely on coarse-grained…
Data augmentation has become a de facto component for training high-performance deep image classifiers, but its potential is under-explored for object detection. Noting that most state-of-the-art object detectors benefit from fine-tuning a…
Imitation learning advances robot capabilities by enabling the acquisition of diverse behaviors from human demonstrations. However, large-scale datasets used for policy training often introduce substantial variability in quality, which can…
Visual captioning aims to generate textual descriptions given images or videos. Traditionally, image captioning models are trained on human annotated datasets such as Flickr30k and MS-COCO, which are limited in size and diversity. This…