Unsupervised Domain Adaptation demonstrates great potential to mitigate domain shifts by transferring models from labeled source domains to unlabeled target domains. While Unsupervised Domain Adaptation has been applied to a wide variety of complex vision tasks, only few works focus on lane detection for autonomous driving. This can be attributed to the lack of publicly available datasets. To facilitate research in these directions, we propose CARLANE, a 3-way sim-to-real domain adaptation benchmark for 2D lane detection. CARLANE encompasses the single-target datasets MoLane and TuLane and the multi-target dataset MuLane. These datasets are built from three different domains, which cover diverse scenes and contain a total of 163K unique images, 118K of which are annotated. In addition we evaluate and report systematic baselines, including our own method, which builds upon Prototypical Cross-domain Self-supervised Learning. We find that false positive and false negative rates of the eva
3 PAPERS • 3 BENCHMARKS
Created from endoscopic video feeds of real-world surgical procedures. Overall, the data consists of 307 images, each of which is annotated for the organs and different surgical instruments present in the scene.
3 PAPERS • NO BENCHMARKS YET
Description GBUSV is a un-annotated dataset consisting of ultrasound videos of of patients with either of a malignant or a non-malignant gallbladder. The ultrasound videos were obtained from patients referred to the radiology department of PGIMER, Chandigarh (a high-input hospital in Northern India) for abdominal ultrasound examinations of suspected gallbladder pathologies. Patients were at fasting of at least 6 hours. A 1-5 MHz curved array transducer (C-1-5D, Logiq S8, GE Healthcare) was used. The scanning intended to include the entire gallbladder and the lesion or pathology. The length of the video sequences varies from 43 to 888 frames. The dataset consists of 32 malignant and 32 non-malignant videos containing a total of 12,251 and 3,549 frames, respectively. The video frames are cropped from the center to anonymize the patient information and annotations. The processed frame sizes are of size 360x480 pixels.
2 PAPERS • NO BENCHMARKS YET
An experimental and synthetic (simulated) OA raw signals and reconstructed image domain datasets rendered with different experimental parameters and tomographic acquisition geometries.
Icon645 is a large-scale dataset of icon images that cover a wide range of objects:
1 PAPER • NO BENCHMARKS YET
Read more about the dataset here: https://github.com/ServiceNow/seasonal-contrast
We introduce the trapped yeast cell (TYC) dataset, a novel dataset for understanding instance-level semantics and motions of cells in microstructures. We release $105$ dense annotated high-resolution brightfield microscopy images, including about $19$k instance masks. We also release $261$ curated video clips composed of $1293$ high-resolution microscopy images to facilitate unsupervised understanding of cell motions and morphology.