Related papers: BakuFlow: A Streamlining Semi-Automatic Label Gene…

Vision-language models (VLMs) have revolutionized machine learning by leveraging large pre-trained models to tackle various downstream tasks. Although label, training, and data efficiency have improved, many state-of-the-art VLMs still…

Reducing the amount of labels required to train convolutional neural networks without performance degradation is key to effectively reduce human annotation efforts. We propose Reliable Label Bootstrapping (ReLaB), an unsupervised…

Obtaining the ground truth labels from a video is challenging since the manual annotation of pixel-wise flow labels is prohibitively expensive and laborious. Besides, existing approaches try to adapt the trained model on synthetic datasets…

Modern machine learning methods require significant amounts of labelled data, making the preparation process time-consuming and resource-intensive. In this paper, we propose to consider the process of prototyping a tool for annotating and…

Scene flow estimation is a crucial component in the development of autonomous driving and 3D robotics, providing valuable information for environment perception and navigation. Despite the advantages of learning-based scene flow estimation…

In the field of image classification, existing methods often struggle with biased or ambiguous data, a prevalent issue in real-world scenarios. Current strategies, including semi-supervised learning and class blending, offer partial…

Producing densely annotated data is a difficult and tedious task for medical imaging applications. To address this problem, we propose a novel approach to generate supervision for semi-supervised semantic segmentation. We argue that…

In the past decade, deep neural networks have achieved significant progress in point cloud learning. However, collecting large-scale precisely-annotated training data is extremely laborious and expensive, which hinders the scalability of…

Multi-label image classification is a fundamental but challenging task towards general visual understanding. Existing methods found the region-level cues (e.g., features from RoIs) can facilitate multi-label classification. Nevertheless,…

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…

Semantic annotations are indispensable to train or evaluate perception models, yet very costly to acquire. This work introduces a fully automated 2D/3D labeling framework that, without any human intervention, can generate labels for RGB-D…

Despite strong results on many tasks, multimodal large language models (MLLMs) still underperform on visual mathematical problem solving, especially in reliably perceiving and interpreting diagrams. Inspired by human problem-solving, we…

Oil painting, as a high-level medium that blends human abstract thinking with artistic expression, poses substantial challenges for digital generation and editing due to its intricate brushstroke dynamics and stylized characteristics.…

Fully automatic semantic segmentation of highly specific semantic classes and complex shapes may not meet the accuracy standards demanded by scientists. In such cases, human-centered AI solutions, able to assist operators while preserving…

A popular approach to decrease the need for costly manual annotation of large data sets is weak supervision, which introduces problems of noisy labels, coverage and bias. Methods for overcoming these problems have either relied on…

Training deep neural networks is challenging when large and annotated datasets are unavailable. Extensive manual annotation of data samples is time-consuming, expensive, and error-prone, notably when it needs to be done by experts. To…

The Audio-Visual Video Parsing task aims to identify and temporally localize the events that occur in either or both the audio and visual streams of audible videos. It often performs in a weakly-supervised manner, where only video event…

This work proposes a new image analysis tool called Label Consistent Transform Learning (LCTL). Transform learning is a recent unsupervised representation learning approach; we add supervision by incorporating a label consistency…

Recently, Flow Matching models have pushed the boundaries of high-fidelity data generation across a wide range of domains. It typically employs a single large network to learn the entire generative trajectory from noise to data. Despite…

Recent advances in deep learning significantly boost the performance of salient object detection (SOD) at the expense of labeling larger-scale per-pixel annotations. To relieve the burden of labor-intensive labeling, deep unsupervised SOD…