Search for: All records

As machine learning methods become more powerful and capture more nuances of human behavior, biases in the dataset can shape what the model learns and is evaluated on. This paper explores and attempts to quantify the uncertainties and biases due to annotator demographics when creating sentiment analysis datasets. We ask >1000 crowdworkers to provide their demographic information and annotations for multimodal sentiment data and its component modalities. We show that demographic differences among annotators impute a significant effect on their ratings, and that these effects also occur in each component modality. We compare predictions of different state-of-the-art multimodal machine learning algorithms against annotations provided by different demographic groups, and find that changing annotator demographics can cause >4.5 in accuracy difference when determining positive versus negative sentiment. Our findings underscore the importance of accounting for crowdworker attributes, such as demographics, when building datasets, evaluating algorithms, and interpreting results for sentiment analysis.

 

Rejecting cosmic rays (CRs) is essential for the scientific interpretation of CCD-captured data, but detecting CRs in single-exposure images has remained challenging. Conventional CR detectors require experimental parameter tuning for different instruments, and recent deep-learning methods only produce instrument-specific models that suffer from performance loss on telescopes not included in the training data. We present Cosmic-CoNN, a generic CR detector deployed for 24 telescopes at the Las Cumbres Observatory, which has been made possible by the three contributions in this work: (1) We build a large and diverse ground-based CR data set leveraging thousands of images from a global telescope network. (2) We propose a novel loss function and a neural network optimized for telescope imaging data to train generic CR-detection models. At 95% recall, our model achieves a precision of 93.70% on Las Cumbres imaging data and maintains a consistent performance on new ground-based instruments never used for training. Specifically, the Cosmic-CoNN model trained on the Las Cumbres CR data set maintains high precisions of 92.03% and 96.69% on Gemini GMOS-N/S 1 × 1 and 2 × 2 binning images, respectively. (3) We build a suite of tools including an interactive CR mask visualization and editing interface, console commands, and Python APIs to make automatic, robust CR detection widely accessible by the community of astronomers. Our data set, open-source code base, and trained models are available athttps://github.com/cy-xu/cosmic-conn.

 

Recent volumetric 3D reconstruction methods can produce very accurate results, with plausible geometry even for unobserved surfaces. However, they face an undesirable trade-off when it comes to multi-view fusion. They can fuse all available view information by global averaging, thus losing fine detail, or they can heuristically cluster views for local fusion, thus restricting their ability to consider all views jointly. Our key insight is that greater detail can be retained without restricting view diversity by learning a view-fusion function conditioned on camera pose and image content. We propose to learn this multi-view fusion using a transformer. To this end, we introduce VoRTX, 1 an end-to-end volumetric 3D reconstruction network using transformers for wide-baseline, multi-view feature fusion. Our model is occlusion-aware, leveraging the transformer architecture to predict an initial, projective scene geometry estimate. This estimate is used to avoid back-projecting image features through surfaces into occluded regions. We train our model on ScanNet and show that it produces better reconstructions than state-of-the-art methods. We also demonstrate generalization without any fine-tuning, outperforming the same state-of-the-art methods on two other datasets, TUM-RGBD and ICL-NUIM. 

We present 3DVNet, a novel multi-view stereo (MVS) depth-prediction method that combines the advantages of previous depth-based and volumetric MVS approaches. Our key idea is the use of a 3D scene-modeling network that iteratively updates a set of coarse depth predictions, resulting in highly accurate predictions which agree on the underlying scene geometry. Unlike existing depth-prediction techniques, our method uses a volumetric 3D convolutional neural network (CNN) that operates in world space on all depth maps jointly. The network can therefore learn meaningful scene-level priors. Furthermore, unlike existing volumetric MVS techniques, our 3D CNN operates on a feature-augmented point cloud, allowing for effective aggregation of multi-view information and flexible iterative refinement of depth maps. Experimental results show our method exceeds state-of-the-art accuracy in both depth prediction and 3D reconstruction metrics on the ScanNet dataset, as well as a selection of scenes from the TUM-RGBD and ICL-NUIM datasets. This shows that our method is both effective and generalizes to new settings.