Related papers: Bamboo: Building Mega-Scale Vision Dataset Continu…

Active learning as a paradigm in deep learning is especially important in applications involving intricate perception tasks such as object detection where labels are difficult and expensive to acquire. Development of active learning methods…

Reconstructing 3D objects is an important computer vision task that has wide application in AR/VR. Deep learning algorithm developed for this task usually relies on an unrealistic synthetic dataset, such as ShapeNet and Things3D. On the…

Deep object recognition models have been very successful over benchmark datasets such as ImageNet. How accurate and robust are they to distribution shifts arising from natural and synthetic variations in datasets? Prior research on this…

Object detection has witnessed significant progress by relying on large, manually annotated datasets. Annotating such datasets is highly time consuming and expensive, which motivates the development of weakly supervised and few-shot object…

Images of realistic scenes often contain intra-class objects that are heavily occluded from each other, making the amodal perception task that requires parsing the occluded parts of the objects challenging. Although important for downstream…

Existing 3D pose datasets of object categories are limited to generic object types and lack of fine-grained information. In this work, we introduce a new large-scale dataset that consists of 409 fine-grained categories and 31,881 images…

We present a dataset of 998 3D models of everyday tabletop objects along with their 847,000 real world RGB and depth images. Accurate annotations of camera poses and object poses for each image are performed in a semi-automated fashion to…

Visual Emotion Analysis (VEA) aims at predicting people's emotional responses to visual stimuli. This is a promising, yet challenging, task in affective computing, which has drawn increasing attention in recent years. Most of the existing…

A key requirement for leveraging supervised deep learning methods is the availability of large, labeled datasets. Unfortunately, in the context of RGB-D scene understanding, very little data is available -- current datasets cover a small…

Given multiple datasets with different label spaces, the goal of this work is to train a single object detector predicting over the union of all the label spaces. The practical benefits of such an object detector are obvious and significant…

Common visual recognition tasks such as classification, object detection, and semantic segmentation are rapidly reaching maturity, and given the recent rate of progress, it is not unreasonable to conjecture that techniques for many of these…

Test sets are an integral part of evaluating models and gauging progress in object recognition, and more broadly in computer vision and AI. Existing test sets for object recognition, however, suffer from shortcomings such as bias towards…

Accurate document layout analysis is a key requirement for high-quality PDF document conversion. With the recent availability of public, large ground-truth datasets such as PubLayNet and DocBank, deep-learning models have proven to be very…

High-quality and consistent annotations are fundamental to the successful development of robust machine learning models. Traditional data annotation methods are resource-intensive and inefficient, often leading to a reliance on third-party…

Current approaches for fine-grained recognition do the following: First, recruit experts to annotate a dataset of images, optionally also collecting more structured data in the form of part annotations and bounding boxes. Second, train a…

3D object detection has recently received much attention due to its great potential in autonomous vehicle (AV). The success of deep learning based object detectors relies on the availability of large-scale annotated datasets, which is…

The development of multi-label deep learning models for retinal disease classification is often hindered by the scarcity of large, expertly annotated clinical datasets due to patient privacy concerns and high costs. The recent release of…

Unsupervised and open-vocabulary 3D object detection has recently gained attention, particularly in autonomous driving, where reducing annotation costs and recognizing unseen objects are critical for both safety and scalability. However,…

Despite the numerous developments in object tracking, further development of current tracking algorithms is limited by small and mostly saturated datasets. As a matter of fact, data-hungry trackers based on deep-learning currently rely on…

Large-scale pretraining of visual representations has led to state-of-the-art performance on a range of benchmark computer vision tasks, yet the benefits of these techniques at extreme scale in complex production systems has been relatively…