Related papers: Supervised contrastive learning from weakly-labele…

Simplicial complexes prove effective in modeling data with multiway dependencies, such as data defined along the edges of networks or within other higher-order structures. Their spectrum can be decomposed into three interpretable subspaces…

Automatic music transcription is considered to be one of the hardest problems in music information retrieval, yet recent deep learning approaches have achieved substantial improvements on transcription performance. These approaches commonly…

Despite great improvements in semantic segmentation, challenges persist because of the lack of local/global contexts and the relationship between them. In this paper, we propose Contextrast, a contrastive learning-based semantic…

In speaker verification, contrastive learning is gaining popularity as an alternative to the traditionally used classification-based approaches. Contrastive methods can benefit from an effective use of hard negative pairs, which are…

In this work, we propose CLUDA, a simple, yet novel method for performing unsupervised domain adaptation (UDA) for semantic segmentation by incorporating contrastive losses into a student-teacher learning paradigm, that makes use of…

Conventional semi-supervised contrastive learning methods assign pseudo-labels only to samples whose highest predicted class probability exceeds a predefined threshold, and then perform supervised contrastive learning using those selected…

The challenges in applying contrastive learning to speaker verification (SV) are that the softmax-based contrastive loss lacks discriminative power and that the hard negative pairs can easily influence learning. To overcome the first…

Text segmentation is a challenging vision task with many downstream applications. Current text segmentation methods require pixel-level annotations, which are expensive in the cost of human labor and limited in application scenarios. In…

In this paper, we tackle the new Language-Based Audio Retrieval task proposed in DCASE 2022. Firstly, we introduce a simple, scalable architecture which ties both the audio and text encoder together. Secondly, we show that using this…

How can you sample good negative examples for contrastive learning? We argue that, as with metric learning, contrastive learning of representations benefits from hard negative samples (i.e., points that are difficult to distinguish from an…

Learnable keypoint detectors and descriptors are beginning to outperform classical hand-crafted feature extraction methods. Recent studies on self-supervised learning of visual representations have driven the increasing performance of…

Current debiasing approaches often result a degradation in model capabilities such as factual accuracy and knowledge retention. Through systematic evaluation across multiple benchmarks, we demonstrate that existing debiasing methods face…

This paper investigates the combination of intensity-based distance maps with boundary loss for point-supervised semantic segmentation. By design the boundary loss imposes a stronger penalty on the false positives the farther away from the…

Off-road semantic segmentation with fine-grained labels is necessary for autonomous vehicles to understand driving scenes, as the coarse-grained road detection can not satisfy off-road vehicles with various mechanical properties.…

Obtaining manual annotations for large datasets for supervised training of deep learning (DL) models is challenging. The availability of large unlabeled datasets compared to labeled ones motivate the use of self-supervised pretraining to…

Weak-strong consistency learning strategies are widely employed in semi-supervised medical image segmentation to train models by leveraging limited labeled data and enforcing weak-to-strong consistency. However, existing methods primarily…

Large medical imaging datasets can be cheaply and quickly annotated with low-confidence, weak labels (e.g., radiological scores). Access to high-confidence labels, such as histology-based diagnoses, is rare and costly. Pretraining…

We present an approach for jointly matching and segmenting object instances of the same category within a collection of images. In contrast to existing algorithms that tackle the tasks of semantic matching and object co-segmentation in…

Complex data mining has wide application value in many fields, especially in the feature extraction and classification tasks of unlabeled data. This paper proposes an algorithm based on self-supervised learning and verifies its…

Pre-training a recognition model with contrastive learning on a large dataset of unlabeled data has shown great potential to boost the performance of a downstream task, e.g., image classification. However, in domains such as medical…