相关论文: Unsupervised Topic Segmentation of Meetings with B…

Temporal segmentation of long videos is an important problem, that has largely been tackled through supervised learning, often requiring large amounts of annotated training data. In this paper, we tackle the problem of self-supervised…

Providing technologies to communities or domains where training data is scarce or protected e.g., for privacy reasons, is becoming increasingly important. To that end, we generalise methods for unsupervised transfer from multiple input…

Semantic segmentation is one of the basic, yet essential scene understanding tasks for an autonomous agent. The recent developments in supervised machine learning and neural networks have enjoyed great success in enhancing the performance…

Unsupervised localization and segmentation are long-standing computer vision challenges that involve decomposing an image into semantically-meaningful segments without any labeled data. These tasks are particularly interesting in an…

Text segmentation aims to divide text into contiguous, semantically coherent segments, while segment labeling deals with producing labels for each segment. Past work has shown success in tackling segmentation and labeling for documents and…

High annotation costs are a major bottleneck for the training of semantic segmentation systems. Therefore, methods working with less annotation effort are of special interest. This paper studies the problem of semi-supervised semantic…

Machine learning has achieved impressive performance in tomographic reconstruction, but supervised training requires paired measurements and ground-truth images that are often unavailable. This has motivated self-supervised approaches,…

The advent of deep learning has led to a significant gain in machine translation. However, most of the studies required a large parallel dataset which is scarce and expensive to construct and even unavailable for some languages. This paper…

Segmentation in medical imaging is an essential and often preliminary task in the image processing chain, driving numerous efforts towards the design of robust segmentation algorithms. Supervised learning methods achieve excellent…

We present an unsupervised word segmentation model, in which the learning objective is to maximize the generation probability of a sentence given its all possible segmentation. Such generation probability can be factorized into the…

Co-part segmentation is an important problem in computer vision for its rich applications. We propose an unsupervised learning approach for co-part segmentation from images. For the training stage, we leverage motion information embedded in…

Reliable perception during fast motion maneuvers or in high dynamic range environments is crucial for robotic systems. Since event cameras are robust to these challenging conditions, they have great potential to increase the reliability of…

Annotation scarcity has become a major obstacle for training powerful deep-learning models for medical image segmentation, restricting their deployment in clinical scenarios. To address it, semi-supervised learning by exploiting abundant…

Bidirectional Encoder Representations from Transformers (BERT) represents the latest incarnation of pretrained language models which have recently advanced a wide range of natural language processing tasks. In this paper, we showcase how…

Current state-of-the-art open-vocabulary segmentation methods typically rely on image-mask-text triplet annotations for supervision. However, acquiring such detailed annotations is labour-intensive and poses scalability challenges in…

Recent speaker diarization studies showed that integration of end-to-end neural diarization (EEND) and clustering-based diarization is a promising approach for achieving state-of-the-art performance on various tasks. Such an approach first…

Producing the embedding of a sentence in an unsupervised way is valuable to natural language matching and retrieval problems in practice. In this work, we conduct a thorough examination of pretrained model based unsupervised sentence…

In semi-supervised semantic segmentation, the Mean Teacher- and co-training-based approaches are employed to mitigate confirmation bias and coupling problems. However, despite their high performance, these approaches frequently involve…

Product embedding serves as a cornerstone for a wide range of applications in eCommerce. The product embedding learned from multiple modalities shows significant improvement over that from a single modality, since different modalities…

In this paper, we present a novel cross-consistency based semi-supervised approach for semantic segmentation. Consistency training has proven to be a powerful semi-supervised learning framework for leveraging unlabeled data under the…