Related papers: Saliency Guided Self-attention Network for Weakly …
State-of-the-art approaches for semantic segmentation rely on deep convolutional neural networks trained on fully annotated datasets, that have been shown to be notoriously expensive to collect, both in terms of time and money. To remedy…
Recent years have seen a rapid growth in new approaches improving the accuracy of semantic segmentation in a weakly supervised setting, i.e. with only image-level labels available for training. However, this has come at the cost of…
Semantic segmentation plays an important role in intelligent vehicles, providing pixel-level semantic information about the environment. However, the labeling budget is expensive and time-consuming when semantic segmentation model is…
Scene text recognition is a challenging task due to the complex backgrounds and diverse variations of text instances. In this paper, we propose a novel Semantic GAN and Balanced Attention Network (SGBANet) to recognize the texts in scene…
Weakly-Supervised Concealed Object Segmentation (WSCOS) aims to segment objects well blended with surrounding environments using sparsely-annotated data for model training. It remains a challenging task since (1) it is hard to distinguish…
Deep learning has revolutionized medical imaging, but its effectiveness is severely limited by insufficient labeled training data. This paper introduces a novel GAN-based semi-supervised learning framework specifically designed for low…
Weakly supervised semantic segmentation (WSSS) in histopathology seeks to reduce annotation cost by learning from image-level labels, yet it remains limited by inter-class homogeneity, intra-class heterogeneity, and the region-shrinkage…
Attention mechanism plays a dominant role in the sequence generation models and has been used to improve the performance of machine translation and abstractive text summarization. Different from neural machine translation, in the task of…
Scribble-based weakly-supervised semantic segmentation using sparse scribble supervision is gaining traction as it reduces annotation costs when compared to fully annotated alternatives. Existing methods primarily generate pseudo-labels by…
Given a grayscale photograph, the colorization system estimates a visually plausible colorful image. Conventional methods often use semantics to colorize grayscale images. However, in these methods, only classification semantic information…
In this work, we study the problem of training deep networks for semantic image segmentation using only a fraction of annotated images, which may significantly reduce human annotation efforts. Particularly, we propose a strategy that…
Developments in weakly supervised and self-supervised models could enable speech technology in low-resource settings where full transcriptions are not available. We consider whether keyword localisation is possible using two forms of weak…
Optical coherence tomography (OCT) is one of the non-invasive and easy-to-acquire biomarkers (the thickness of the retinal layers, which is detectable within OCT scans) being investigated to diagnose Alzheimer's disease (AD). This work aims…
We present a novel confidence refinement scheme that enhances pseudo labels in semi-supervised semantic segmentation. Unlike existing methods, which filter pixels with low-confidence predictions in isolation, our approach leverages the…
Compared with laborious pixel-wise dense labeling, it is much easier to label data by scribbles, which only costs 1$\sim$2 seconds to label one image. However, using scribble labels to learn salient object detection has not been explored.…
Weakly-supervised instance segmentation (WSIS) has been considered as a more challenging task than weakly-supervised semantic segmentation (WSSS). Compared to WSSS, WSIS requires instance-wise localization, which is difficult to extract…
We propose weakly supervised language localization networks (WSLLN) to detect events in long, untrimmed videos given language queries. To learn the correspondence between visual segments and texts, most previous methods require temporal…
Weakly supervised semantic segmentation (WSSS) in medical imaging struggles with effectively using sparse annotations. One promising direction for WSSS leverages gaze annotations, captured via eye trackers that record regions of interest…
Weakly-supervised semantic segmentation (WSSS) has recently gained much attention for its promise to train segmentation models only with image-level labels. Existing WSSS methods commonly argue that the sparse coverage of CAM incurs the…
Salient object detection aims at detecting the most visually distinct objects and producing the corresponding masks. As the cost of pixel-level annotations is high, image tags are usually used as weak supervisions. However, an image tag can…