Related papers: Self-supervised Learning for Semi-supervised Tempo…
Since we can leverage a large amount of unlabeled data without any human supervision to train a model and transfer the knowledge to target tasks, self-supervised learning is a de-facto component for the recent success of deep learning in…
Neural natural language generation (NLG) and understanding (NLU) models are data-hungry and require massive amounts of annotated data to be competitive. Recent frameworks address this bottleneck with generative models that synthesize weak…
Remote sensing projects typically generate large amounts of imagery that can be used to train powerful deep neural networks. However, the amount of labeled images is often small, as remote sensing applications generally require expert…
Semi-Supervised Semantic Segmentation aims at training the segmentation model with limited labeled data and a large amount of unlabeled data. To effectively leverage the unlabeled data, pseudo labeling, along with the teacher-student…
Self-training via pseudo labeling is a conventional, simple, and popular pipeline to leverage unlabeled data. In this work, we first construct a strong baseline of self-training (namely ST) for semi-supervised semantic segmentation via…
The emergent reasoning capabilities of Large Language Models (LLMs) offer a transformative paradigm for analyzing text-attributed graphs. While instruction tuning is the prevailing method for adapting pre-trained LLMs to graph learning…
In this paper, we present a simple and efficient method for training deep neural networks in a semi-supervised setting where only a small portion of training data is labeled. We introduce self-ensembling, where we form a consensus…
Video-language alignment is a crucial multi-modal task that benefits various downstream applications, e.g., video-text retrieval and video question answering. Existing methods either utilize multi-modal information in video-text pairs or…
Recent studies have shown that the benefits provided by self-supervised pre-training and self-training (pseudo-labeling) are complementary. Semi-supervised fine-tuning strategies under the pre-training framework, however, remain…
This paper addresses the problem of temporal sentence grounding (TSG), which aims to identify the temporal boundary of a specific segment from an untrimmed video by a sentence query. Previous works either compare pre-defined candidate…
Semi-supervised learning holds great promise for many real-world applications, due to its ability to leverage both unlabeled and expensive labeled data. However, most semi-supervised learning algorithms still heavily rely on the limited…
Detection of anomalous events in videos is an important problem in applications such as surveillance. Video anomaly detection (VAD) is well-studied in the one-class classification (OCC) and weakly supervised (WS) settings. However, fully…
We study the problem of generating keyphrases that summarize the key points for a given document. While sequence-to-sequence (seq2seq) models have achieved remarkable performance on this task (Meng et al., 2017), model training often relies…
Semi-supervised learning (SSL) has emerged as a promising paradigm for breast ultrasound (BUS) image segmentation, but it often suffers from unstable pseudo labels under extremely limited annotations, leading to inaccurate supervision and…
In low-level video analyses, effective representations are important to derive the correspondences between video frames. These representations have been learned in a self-supervised fashion from unlabeled images or videos, using carefully…
Semi-supervised 3D object detection is a common strategy employed to circumvent the challenge of manually labeling large-scale autonomous driving perception datasets. Pseudo-labeling approaches to semi-supervised learning adopt a…
While modern visual recognition systems have made significant advancements, many continue to struggle with the open problem of learning from few exemplars. This paper focuses on the task of object detection in the setting where object…
Beyond attaining domain generalization (DG), visual recognition models should also be data-efficient during learning by leveraging limited labels. We study the problem of Semi-Supervised Domain Generalization (SSDG) which is crucial for…
Sequence labeling is an important technique employed for many Natural Language Processing (NLP) tasks, such as Named Entity Recognition (NER), slot tagging for dialog systems and semantic parsing. Large-scale pre-trained language models…
Semi-supervised referring expression segmentation (SS-RES) aims to achieve precise pixel-level language grounding under limited annotation, yet suffers from limited supervision and unreliable pseudo-labels when exploiting unlabeled…