Related papers: Towards Using Unlabeled Data in a Sparse-coding Fr…
Supervised contour detection methods usually require many labeled training images to obtain satisfactory performance. However, a large set of annotated data might be unavailable or extremely labor intensive. In this paper, we investigate…
Building robust and generic object detection frameworks requires scaling to larger label spaces and bigger training datasets. However, it is prohibitively costly to acquire annotations for thousands of categories at a large scale. We…
Dictionary learning and sparse coding have been widely studied as mechanisms for unsupervised feature learning. Unsupervised learning could bring enormous benefit to the processing of hyperspectral images and to other remote sensing data…
Unlike images or videos data which can be easily labeled by human being, sensor data annotation is a time-consuming process. However, traditional methods of human activity recognition require a large amount of such strictly labeled data for…
Sensor data streams from wearable devices and smart environments are widely studied in areas like human activity recognition (HAR), person identification, or health monitoring. However, most of the previous works in activity and sensor…
In the fast-evolving field of artificial intelligence, where models are increasingly growing in complexity and size, the availability of labeled data for training deep learning models has become a significant challenge. Addressing complex…
In this study, a novel method to obtain user-dependent human activity recognition models unobtrusively by exploiting the sensors of a smartphone is presented. The recognition consists of two models: sensor fusion-based user-independent…
We propose a novel system for unsupervised skeleton-based action recognition. Given inputs of body keypoints sequences obtained during various movements, our system associates the sequences with actions. Our system is based on an…
The recent emergence of Distributed Acoustic Sensing (DAS) technology has facilitated the effective capture of traffic-induced seismic data. The traffic-induced seismic wave is a prominent contributor to urban vibrations and contain crucial…
State-of-the-art deep neural networks require large-scale labeled training data that is often expensive to obtain or not available for many tasks. Weak supervision in the form of domain-specific rules has been shown to be useful in such…
Self-training, a semi-supervised learning algorithm, leverages a large amount of unlabeled data to improve learning when the labeled data are limited. Despite empirical successes, its theoretical characterization remains elusive. To the…
We present a new flavor of Variational Autoencoder (VAE) that interpolates seamlessly between unsupervised, semi-supervised and fully supervised learning domains. We show that unlabeled datapoints not only boost unsupervised tasks, but also…
Most existing distance metric learning approaches use fully labeled data to learn the sample similarities in an embedding space. We present a self-training framework, SLADE, to improve retrieval performance by leveraging additional…
Using deep learning, we now have the ability to create exceptionally good semantic segmentation systems; however, collecting the prerequisite pixel-wise annotations for training images remains expensive and time-consuming. Therefore, it…
We investigate the use of sparse coding and dictionary learning in the context of multitask and transfer learning. The central assumption of our learning method is that the tasks parameters are well approximated by sparse linear…
Event cameras are activity-driven bio-inspired vision sensors, thereby resulting in advantages such as sparsity,high temporal resolution, low latency, and power consumption. Given the different sensing modality of event camera and high…
Smartphones, wearables, and Internet of Things (IoT) devices produce a wealth of data that cannot be accumulated in a centralized repository for learning supervised models due to privacy, bandwidth limitations, and the prohibitive cost of…
Reliable perception during fast motion maneuvers or in high dynamic range environments is crucial for robotic systems. Since event cameras are robust to these challenging conditions, they have great potential to increase the reliability of…
Most of the proposed person re-identification algorithms conduct supervised training and testing on single labeled datasets with small size, so directly deploying these trained models to a large-scale real-world camera network may lead to…
Most existing crowd counting systems rely on the availability of the object location annotation which can be expensive to obtain. To reduce the annotation cost, one attractive solution is to leverage a large number of unlabeled images to…