Related papers: MoPro: Webly Supervised Learning with Momentum Pro…

Monocular 3D object detection typically relies on pseudo-labeling techniques to reduce dependency on real-world annotations. Recent advances demonstrate that deterministic linguistic cues can serve as effective auxiliary weak supervision…

Recently, video recognition is emerging with the help of multi-modal learning, which focuses on integrating distinct modalities to improve the performance or robustness of the model. Although various multi-modal learning methods have been…

Deep neural network-based classifiers trained with the categorical cross-entropy (CCE) loss are sensitive to label noise in the training data. One common type of method that can mitigate the impact of label noise can be viewed as supervised…

Existing popular unsupervised embedding learning methods focus on enhancing the instance-level local discrimination of the given unlabeled images by exploring various negative data. However, the existed sample outliers which exhibit large…

Learning visual knowledge from massive weakly-labeled web videos has attracted growing research interests thanks to the large corpus of easily accessible video data on the Internet. However, for video action recognition, the action of…

In the context of noisy partial label learning (NPLL), each training sample is associated with a set of candidate labels annotated by multiple noisy annotators. With the emergence of high-performance pre-trained vision-language models…

Prompt learning is a parameter-efficient approach for vision-language models, yet its robustness under label noise is less investigated. Visual content contains richer and more reliable semantic information, which remains more robust under…

Representation Learning is a significant and challenging task in multimodal learning. Effective modality representations should contain two parts of characteristics: the consistency and the difference. Due to the unified multimodal…

Self-supervised learning can be used for mitigating the greedy needs of Vision Transformer networks for very large fully-annotated datasets. Different classes of self-supervised learning offer representations with either good contextual…

Given the difficulty of manually annotating motion in video, the current best motion estimation methods are trained with synthetic data, and therefore struggle somewhat due to a train/test gap. Self-supervised methods hold the promise of…

Contrastive learning is a form of self-supervision that can leverage unlabeled data to produce pretrained models. While contrastive learning has demonstrated promising results on natural image classification tasks, its application to…

Real-world data inevitably contains noisy labels, which induce the poor generalization of deep neural networks. It is known that the network typically begins to rapidly memorize false-labeled samples after a certain point of training. Thus,…

Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…

Limited availability of labeled physiological data often prohibits the use of powerful supervised deep learning models in the biomedical machine intelligence domain. We approach this problem and propose a novel encoding framework that…

Pseudo-labeling (PL) has been shown to be effective in semi-supervised automatic speech recognition (ASR), where a base model is self-trained with pseudo-labels generated from unlabeled data. While PL can be further improved by iteratively…

Deep learning on an edge device requires energy efficient operation due to ever diminishing power budget. Intentional low quality data during the data acquisition for longer battery life, and natural noise from the low cost sensor degrade…

Self-supervised learning (SSL) techniques have recently produced outstanding results in learning visual representations from unlabeled videos. Despite the importance of motion in supervised learning techniques for action recognition, SSL…

Prompt-based methods have been successfully applied to multilingual pretrained language models for zero-shot cross-lingual understanding. However, most previous studies primarily focused on sentence-level classification tasks, and only a…

Real world learning scenarios involve a nonstationary distribution of classes with sequential dependencies among the samples, in contrast to the standard machine learning formulation of drawing samples independently from a fixed, typically…

Multimodal emotion recognition study is hindered by the lack of labelled corpora in terms of scale and diversity, due to the high annotation cost and label ambiguity. In this paper, we propose a pre-training model \textbf{MEmoBERT} for…