Related papers: Weakly supervised collective feature learning from…

This paper presents a novel semantic scene change detection scheme with only weak supervision. A straightforward approach for this task is to train a semantic change detection network directly from a large-scale dataset in an end-to-end…

Traditional image tagging and retrieval algorithms have limited value as a result of being trained with heavily curated datasets. These limitations are most evident when arbitrary search words are used that do not intersect with training…

The need for labeled data is among the most common and well-known practical obstacles to deploying deep learning algorithms to solve real-world problems. The current generation of learning algorithms requires a large volume of data labeled…

Despite the impressive improvements achieved by unsupervised deep neural networks in computer vision and NLP tasks, such improvements have not yet been observed in ranking for information retrieval. The reason may be the complexity of the…

We present an approach to learn a dense pixel-wise labeling from image-level tags. Each image-level tag imposes constraints on the output labeling of a Convolutional Neural Network (CNN) classifier. We propose Constrained CNN (CCNN), a…

Food classification from images is a fine-grained classification problem. Manual curation of food images is cost, time and scalability prohibitive. On the other hand, web data is available freely but contains noise. In this paper, we…

Scene labeling is a challenging classification problem where each input image requires a pixel-level prediction map. Recently, deep-learning-based methods have shown their effectiveness on solving this problem. However, we argue that the…

Serial femtosecond crystallography at X-ray free electron laser facilities opens a new era for the determination of crystal structure. However, the data processing of those experiments is facing unprecedented challenge, because the total…

Self-supervised learning holds promise in leveraging large numbers of unlabeled data. However, its success heavily relies on the highly-curated dataset, e.g., ImageNet, which still needs human cleaning. Directly learning representations…

Labeling medical images depends on professional knowledge, making it difficult to acquire large amount of annotated medical images with high quality in a short time. Thus, making good use of limited labeled samples in a small dataset to…

Training deep networks with limited labeled data while achieving a strong generalization ability is key in the quest to reduce human annotation efforts. This is the goal of semi-supervised learning, which exploits more widely available…

Learning semantic segmentation models under image-level supervision is far more challenging than under fully supervised setting. Without knowing the exact pixel-label correspondence, most weakly-supervised methods rely on external models to…

Most of the approaches for discovering visual attributes in images demand significant supervision, which is cumbersome to obtain. In this paper, we aim to discover visual attributes in a weakly supervised setting that is commonly…

Training deep neural networks requires massive amounts of training data, but for many tasks only limited labeled data is available. This makes weak supervision attractive, using weak or noisy signals like the output of heuristic methods or…

Learning from weakly-supervised data is one of the main challenges in machine learning and computer vision, especially for tasks such as image semantic segmentation where labeling is extremely expensive and subjective. In this paper, we…

Humans are able to recognize structured relations in observation, allowing us to decompose complex scenes into simpler parts and abstract the visual world in multiple levels. However, such hierarchical reasoning ability of human perception…

Social media is daily creating massive multimedia content with paired image and text, presenting the pressing need to automate the vision and language understanding for various multimodal classification tasks. Compared to the commonly…

Self-Supervised learning from multimodal image and text data allows deep neural networks to learn powerful features with no need of human annotated data. Web and Social Media platforms provide a virtually unlimited amount of this multimodal…

Manually annotating complex scene point cloud datasets is both costly and error-prone. To reduce the reliance on labeled data, a new model called SnapshotNet is proposed as a self-supervised feature learning approach, which directly works…

Currently, existing efforts in Weakly Supervised Semantic Segmentation (WSSS) based on Convolutional Neural Networks (CNNs) have predominantly focused on enhancing the multi-label classification network stage, with limited attention given…