Related papers: SelfDocSeg: A Self-Supervised vision-based Approac…

Unsupervised semantic segmentation is a challenging task that segments images into semantic groups without manual annotation. Prior works have primarily focused on leveraging prior knowledge of semantic consistency or priori concepts from…

In many machine learning applications, labeled data is scarce and obtaining more labels is expensive. We introduce a new approach to supervising neural networks by specifying constraints that should hold over the output space, rather than…

Image Segmentation plays an essential role in computer vision and image processing with various applications from medical diagnosis to autonomous car driving. A lot of segmentation algorithms have been proposed for addressing specific…

Deep learning has been widely used in medical image segmentation and other aspects. However, the performance of existing medical image segmentation models has been limited by the challenge of obtaining sufficient high-quality labeled data…

Self-supervised learning (SSL) has produced a diverse landscape of vision transformers (ViTs) whose pretrained representations support a wide range of downstream tasks. Towards a better understanding of these models, a body of work has…

Binarization is a well-known image processing task, whose objective is to separate the foreground of an image from the background. One of the many tasks for which it is useful is that of preprocessing document images in order to identify…

Building a large image dataset with high-quality object masks for semantic segmentation is costly and time consuming. In this paper, we introduce a principled semi-supervised framework that only uses a small set of fully supervised images…

Layout is a fundamental component of any graphic design. Creating large varieties of plausible document layouts can be a tedious task, requiring numerous constraints to be satisfied, including local ones relating different semantic elements…

Visual concept discovery has long been deemed important to improve interpretability of neural networks, because a bank of semantically meaningful concepts would provide us with a starting point for building machine learning models that…

Deep learning is pushing the state-of-the-art in many computer vision applications. However, it relies on large annotated data repositories, and capturing the unconstrained nature of the real-world data is yet to be solved. Semi-supervised…

Audio-Visual Video Parsing is a task to predict the events that occur in video segments for each modality. It often performs in a weakly supervised manner, where only video event labels are provided, i.e., the modalities and the timestamps…

Novel contexts may often arise in complex querying scenarios such as in evidence-based medicine (EBM) involving biomedical literature, that may not explicitly refer to entities or canonical concept forms occurring in any fact- or rule-based…

CLIP has enabled new and exciting joint vision-language applications, one of which is open-vocabulary segmentation, which can locate any segment given an arbitrary text query. In our research, we ask whether it is possible to discover…

Video segmentation -- partitioning video frames into multiple segments or objects -- plays a critical role in a broad range of practical applications, from enhancing visual effects in movie, to understanding scenes in autonomous driving, to…

Dimensionality reduction is often used as an initial step in data exploration, either as preprocessing for classification or regression or for visualization. Most dimensionality reduction techniques to date are unsupervised; they do not…

Localizing keypoints of an object is a basic visual problem. However, supervised learning of a keypoint localization network often requires a large amount of data, which is expensive and time-consuming to obtain. To remedy this, there is an…

While high-resolution pathology images lend themselves well to `data hungry' deep learning algorithms, obtaining exhaustive annotations on these images is a major challenge. In this paper, we propose a self-supervised CNN approach to…

The task of text and sentence classification is associated with the need for large amounts of labelled training data. The acquisition of high volumes of labelled datasets can be expensive or unfeasible, especially for highly-specialised…

Unsupervised word segmentation in audio utterances is challenging as, in speech, there is typically no gap between words. In a preliminary experiment, we show that recent deep self-supervised features are very effective for word…

We present a novel deep neural model for text detection in document images. For robust text detection in noisy scanned documents, the advantages of multi-task learning are adopted by adding an auxiliary task of text enhancement. Namely, our…