Related papers: Boosting Gesture Recognition with an Automatic Ges…

Most existing distance metric learning approaches use fully labeled data to learn the sample similarities in an embedding space. We present a self-training framework, SLADE, to improve retrieval performance by leveraging additional…

Performances of Handwritten Text Recognition (HTR) models are largely determined by the availability of labeled and representative training samples. However, in many application scenarios labeled samples are scarce or costly to obtain. In…

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…

Labeling a large set of data is expensive. Active learning aims to tackle this problem by asking to annotate only the most informative data from the unlabeled set. We propose a novel active learning approach that utilizes self-supervised…

Many ways of annotating a dataset for machine learning classification tasks that go beyond the usual class labels exist in practice. These are of interest as they can simplify or facilitate the collection of annotations, while not greatly…

Digital data collected over the decades and data currently being produced with use of information technology is vastly the unlabeled data or data without description. The unlabeled data is relatively easy to acquire but expensive to label…

Semi-supervised Camouflaged Object Detection (SSCOD) aims to reduce reliance on costly pixel-level annotations by leveraging limited annotated data and abundant unlabeled data. However, existing SSCOD methods based on Teacher-Student…

This paper presents an AI-assisted auto-labeling system for display panel defect detection that leverages in-context learning capabilities. We adopt and enhance the SegGPT architecture with several domain-specific training techniques and…

Semi-supervised learning has demonstrated promising results in automatic speech recognition (ASR) by self-training using a seed ASR model with pseudo-labels generated for unlabeled data. The effectiveness of this approach largely relies on…

Meta-learning performs adaptation through a limited amount of support set, which may cause a sample bias problem. To solve this problem, transductive meta-learning is getting more and more attention, going beyond the conventional inductive…

Supervised finetuning (SFT) on instruction datasets has played a crucial role in achieving the remarkable zero-shot generalization capabilities observed in modern large language models (LLMs). However, the annotation efforts required to…

In this work, we propose a novel complementary learning approach to enhance test-time adaptation (TTA), which has been proven to exhibit good performance on testing data with distribution shifts such as corruptions. In test-time adaptation…

Online continual learning, the process of training models on streaming data, has gained increasing attention in recent years. However, a critical aspect often overlooked is the label delay, where new data may not be labeled due to slow and…

Animal pose estimation is an important but under-explored task due to the lack of labeled data. In this paper, we tackle the task of animal pose estimation with scarce annotations, where only a small set of labeled data and unlabeled images…

The task of weakly supervised temporal action localization targets at generating temporal boundaries for actions of interest, meanwhile the action category should also be classified. Pseudo-label-based methods, which serve as an effective…

3D Referring Expression Segmentation (3D-RES) typically requires extensive instance-level annotations, which are time-consuming and costly. Semi-supervised learning (SSL) mitigates this by using limited labeled data alongside abundant…

Much recent work on visual recognition aims to scale up learning to massive, noisily-annotated datasets. We address the problem of scaling- up the evaluation of such models to large-scale datasets with noisy labels. Current protocols for…

Food instance segmentation is essential to estimate the serving size of dishes in a food image. The recent cutting-edge techniques for instance segmentation are deep learning networks with impressive segmentation quality and fast…

Semi-supervised 3D object detection (SS3DOD) aims to reduce costly 3D annotations utilizing unlabeled data. Recent studies adopt pseudo-label-based teacher-student frameworks and demonstrate impressive performance. The main challenge of…

Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…