Search · four archives
Search · four archives
19 papers · ranked by Valyu relevance
Xinghao Wang, Changtao Miao, Dianmo Sheng, Tao Gong + 5 more
Malicious image manipulation threatens public safety and requires efficient localization methods. Existing approaches depend on costly pixel-level annotations which make training expensive. Existing weakly supervised methods rely only on image-level binary labels and focus on global classification, often overlooking…
Xiao Zhou, Shihong Wang, Weiguo Hu, Zhaohao Xie + 4 more
Small object localization is one of the most challenging tasks owing to the poor visual appearance and noisy representation caused by the intrinsic structure of small targets. Recent advances in localizing small objects are mainly dependent on regression-based counting approaches, which require considerable annotations…
Cai, Qingdong, Abhayaratne, Charith
Class Activation Mapping (CAM) methods are widely applied in weakly supervised learning tasks due to their ability to highlight object regions. However, conventional CAM methods highlight only the most discriminative regions of the target. These highlighted regions often fail to cover the entire object and are…
Christian Hallgrimson, Y. Lydia Li, Claire A. Shou, Ben Cardoen + 5 more
Single-molecule localization microscopy (SMLM) achieves nanoscale imaging of complex protein structures in the cell. However, the ability to capture structural variability across cell conditions (cell lines, gene expression, treatment) from 3D point cloud SMLM data remains limited. We present siMILe, a…
Cai, Qingdong, Abhayaratne, Charith
Class Activation Mapping (CAM) methods are widely applied in weakly supervised learning tasks due to their ability to highlight object regions. However, conventional CAM methods highlight only the most discriminative regions of the target. These highlighted regions often fail to cover the entire object and are…
Anurag Das, Anna Kukleva, Xinting Hu, Yuki M. Asano + 1 more
Semantic segmentation requires dense pixel-level annotations, which are costly and time-consuming to acquire. To address this, we present SeSAM, a framework that uses a foundational segmentation model, i.e. Segment Anything Model (SAM), with weak labels, including coarse masks, scribbles, and points. SAM, originally…
Yingtai Li, Hongchun Zhang, Mengwen Xu, Lidan Zhang + 6 more
The development of generalist artificial intelligence (AI) models for radiology is hindered by a lack of large-scale, three-dimensional (3D) imaging datasets with precise spatial annotations. While numerous datasets provide image-level labels for chest computed tomography (CT), these are insufficient for training…
Meng Xu, Bin Hu, Yingfeng Wang, Patrick Koo + 1 more
Automatic segmentation of breast tumors in ultrasound images can assist physicians in making accurate and effective decisions. However, fully supervised learning methods typically require large amounts of pixel-level annotations, which are often difficult to obtain. Weakly supervised segmentation using image-level…
Aayush Kumar Tyagi, Vaibhav Mishra, Prathosh A.P., Mausam
Cell segmentation in histopathological images is vital for diagnosis, and treatment of several diseases. Annotating data is tedious, and requires medical expertise, making it difficult to employ supervised learning. Instead, we study a weakly supervised setting, where only bounding box supervision is available, and…
Peng Gao, Ke Li, Di Wang, Yongshan Zhu + 3 more
—Cross-resolution land cover mapping aims to produce high-resolution semantic predictions from coarse or lowresolution supervision, yet the severe resolution mismatch makes effective learning highly challenging. Existing weakly supervised approaches often struggle to align fine-grained spatial structures with coarse…
Peishuo Liu, Jiaxin Fan, Mianzhi Pan, Jianbing Zhang
Protein function is often mediated by specific sequence regions, such as domains, motifs and functional sites. Identifying these regions is important for understanding protein mechanisms, annotating newly sequenced proteins and prioritizing residues for experimental validation. However, existing protein function…
Jinlin Chen, Yiquan Wu, Yubin Yuan
The recognition and positioning of characters on the water gauge are important components of artificial intelligence system for reading ship draft weighing. Meanwhile, the manual annotation of oriented objects has a large workload and low accuracy. To address these issues, this paper proposes a novel oriented detection…
Romane Dubois, Lydia Bousset, Stéphane Jumel, Melen Leclerc + 2 more
Accurate segmentation of plant disease symptoms is essential for crop monitoring and phenotyping, yet it typically requires costly pixel-level annotations. Weakly supervised semantic segmentation (WSSS) alleviates this burden using image-level labels, but its performance depends on the quality of spatial priors such as…
Lindenberger, Philipp, Sarlin, Paul-Edouard + 10 more
Pinpointing where in the world an image was taken, down to a scale of meters, remains a challenge in computer vision, especially when scaling beyond city limits [1, [2]]. Achieving such fine-grained ∗ Work done during an internship at Google. geolocalization across vast geographic expanses, like entire continents…
Sandeep Kambhampati, Eric Zimmermann, Emre Hayir, Kevin K. Yang + 2 more
Fluorescent microscopy provides a rich view into how proteins localize within cells, but it remains experimentally infeasible to image human proteins across all of the different factors that can impact localization. We introduce Vermeer, a channel-adaptive autoregressive generative model for in silico generation of…
Robert Hu, Nima N. Naseri, Ophir Shalem, Pablo G. Camara
Quantitative analysis of subcellular protein organization is often confounded by variation in cell morphology, limiting the identification and interpretation of localization patterns in fluorescence microscopy data from morphologically complex cells, such as neurons and glia. We introduce CellAligner, an unsupervised…
Authors not listed
Recent years have seen a growing interest in machine learning approaches for chemical tasks. The best existing methods focus on building base models that combine molecular graphs (“2D structures”) with atomic coordinates in 3D to predict molecular properties, typically through pre-training followed by fine-tuning on…
Authors not listed
Machine olfaction—the artificial replication of the sense of smell—faces significant challenges due to the absence of large, standardized training datasets. Unlike vision, language, and audio models, which benefit from extensive corpora such as ImageNet, GLUE, and AudioSet, olfaction lacks scaled equivalents and…
Authors not listed
Machine learning models are increasingly applied to heterogeneous materials datasets spanning different synthesis routes, measurement protocols, and structural classes. Although multi-task and representation-learning approaches are commonly used to improve predictive performance, the latent representations learned by…