Related papers: LLM-Assisted Semantic Guidance for Sparsely Annota…

Weakly-supervised object localization methods tend to fail for object classes that consistently co-occur with the same background elements, e.g. trains on tracks. We propose a method to overcome these failures by adding a very small amount…

Current state-of-the-art methods for object detection rely on annotated bounding boxes of large data sets for training. However, obtaining such annotations is expensive and can require up to hundreds of hours of manual labor. This poses a…

Remote sensing image segmentation is crucial for environmental monitoring, disaster assessment, and resource management, but its performance largely depends on the quality of the dataset. Although several high-quality datasets are broadly…

Leveraging unlabelled data through weak or distant supervision is a compelling approach to developing more effective text classification models. This paper proposes a simple but effective data augmentation method, which leverages the idea…

Learning from noisy labels (LNL) is a challenge that arises in many real-world scenarios where collected training data can contain incorrect or corrupted labels. Most existing solutions identify noisy labels and adopt active learning to…

The ability to understand visual information from limited labeled data is an important aspect of machine learning. While image-level classification has been extensively studied in a semi-supervised setting, dense pixel-level classification…

Sentence-level classification and sequential labeling are two fundamental tasks in language understanding. While these two tasks are usually modeled separately, in reality, they are often correlated, for example in intent classification and…

Supervised deep learning models depend on massive labeled data. Unfortunately, it is time-consuming and labor-intensive to collect and annotate bitemporal samples containing desired changes. Transfer learning from pre-trained models is…

Weakly-supervised learning approaches have gained significant attention due to their ability to reduce the effort required for human annotations in training neural networks. This paper investigates a framework for weakly-supervised object…

Significant performance improvement has been achieved for fully-supervised video salient object detection with the pixel-wise labeled training datasets, which are time-consuming and expensive to obtain. To relieve the burden of data…

Moving object segmentation is a crucial task for safe and reliable autonomous mobile systems like self-driving cars, improving the reliability and robustness of subsequent tasks like SLAM or path planning. While the segmentation of camera…

Semantic segmentation based on sparse annotation has advanced in recent years. It labels only part of each object in the image, leaving the remainder unlabeled. Most of the existing approaches are time-consuming and often necessitate a…

Semi-supervised object detection (SSOD), leveraging unlabeled data to boost object detectors, has become a hot topic recently. However, existing SSOD approaches mainly focus on horizontal objects, leaving oriented objects common in aerial…

While there are novel point cloud semantic segmentation schemes that continuously surpass state-of-the-art results, the success of learning an effective model usually rely on the availability of abundant labeled data. However, data…

In recent years, Multimodal Large Language Models (MLLMs) have made significant progress in visual question answering tasks. However, directly applying existing fine-tuning methods to remote sensing (RS) images often leads to issues such as…

Existing weakly-supervised semantic segmentation methods using image-level annotations typically rely on initial responses to locate object regions. However, such response maps generated by the classification network usually focus on…

This paper looks at semi-supervised learning (SSL) for image-based text recognition. One of the most popular SSL approaches is pseudo-labeling (PL). PL approaches assign labels to unlabeled data before re-training the model with a…

Accurate segmentation of organelle instances from electron microscopy (EM) images plays an essential role in many neuroscience researches. However, practical scenarios usually suffer from high annotation costs, label scarcity, and large…

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…

Scribble-based weakly-supervised semantic segmentation using sparse scribble supervision is gaining traction as it reduces annotation costs when compared to fully annotated alternatives. Existing methods primarily generate pseudo-labels by…