Related papers: Jacquard V2: Refining Datasets using the Human In …
Robotic grasping for a diverse set of objects is essential in many robot manipulation tasks. One promising approach is to learn deep grasping models from large training datasets of object images and grasp labels. However, empirical grasping…
Integrating human expertise into machine learning systems often reduces the role of experts to labeling oracles, a paradigm that limits the amount of information exchanged and fails to capture the nuances of human judgment. We address this…
Modeling complex subjective tasks in Natural Language Processing, such as recognizing emotion and morality, is considerably challenging due to significant variation in human annotations. This variation often reflects reasonable differences…
Current person re-identification (re-id) methods assume that (1) pre-labelled training data are available for every camera pair, (2) the gallery size for re-identification is moderate. Both assumptions scale poorly to real-world…
The ability to estimate the perceptual error between images is an important problem in computer vision with many applications. Although it has been studied extensively, however, no method currently exists that can robustly predict visual…
Human parsing has recently attracted a lot of research interests due to its huge application potentials. However existing datasets have limited number of images and annotations, and lack the variety of human appearances and the coverage of…
Imitation Learning (IL) has emerged as a powerful approach in robotics, allowing robots to acquire new skills by mimicking human actions. Despite its potential, the data collection process for IL remains a significant challenge due to the…
Training data plays an essential role in modern applications of machine learning. However, gathering labeled training data is time-consuming. Therefore, labeling is often outsourced to less experienced users, or completely automated. This…
Business analytics and machine learning have become essential success factors for various industries - with the downside of cost-intensive gathering and labeling of data. Few-shot learning addresses this challenge and reduces data gathering…
Robust grasping in cluttered environments remains an open challenge in robotics. While benchmark datasets have significantly advanced deep learning methods, they mainly focus on simplistic scenes with light occlusion and insufficient…
Inherent morphological characteristics in objects may offer a wide range of plausible grasping orientations that obfuscates the visual learning of robotic grasping. Existing grasp generation approaches are cursed to construct discontinuous…
Reassembling real-world archaeological artifacts from fragmented pieces poses significant challenges due to erosion, missing regions, irregular shapes, and large-scale ambiguity. Traditional jigsaw puzzle solvers, often designed for clean…
Grasping algorithms have evolved from planar depth grasping to utilizing point cloud information, allowing for application in a wider range of scenarios. However, data-driven grasps based on models trained on basic open-source datasets may…
Marine surveys by robotic underwater and surface vehicles result in substantial quantities of coral reef imagery, however labeling these images is expensive and time-consuming for domain experts. Point label propagation is a technique that…
Human explanation (e.g., in terms of feature importance) has been recently used to extend the communication channel between human and agent in interactive machine learning. Under this setting, human trainers provide not only the ground…
The paper presents a technique to improve human detection in still images using deep learning. Our novel method, ViS-HuD, computes visual saliency map from the image. Then the input image is multiplied by the map and product is fed to the…
Data scaling has long remained a critical bottleneck in robot learning. For humanoid robots, human videos and motion data are abundant and widely available, offering a free and large-scale data source. Besides, the semantics related to the…
Document layout analysis (DLA) aims to divide a document image into different types of regions. DLA plays an important role in the document content understanding and information extraction systems. Exploring a method that can use less data…
Despite the significant advancements, existing object removal methods struggle with incomplete removal, incorrect content synthesis and blurry synthesized regions, resulting in low success rates. Such issues are mainly caused by the lack of…
While many recent hand pose estimation methods critically rely on a training set of labelled frames, the creation of such a dataset is a challenging task that has been overlooked so far. As a result, existing datasets are limited to a few…