Related papers: Co-training for On-board Deep Object Detection
Co-training is a popular semi-supervised learning framework to utilize a large amount of unlabeled data in addition to a small labeled set. Co-training methods exploit predicted labels on the unlabeled data and select samples based on…
Semi-supervised object detection has recently achieved substantial progress. As a mainstream solution, the self-labeling-based methods train the detector on both labeled data and unlabeled data with pseudo labels predicted by the detector…
Although having achieved great success in medical image segmentation, deep learning-based approaches usually require large amounts of well-annotated data, which can be extremely expensive in the field of medical image analysis. Unlabeled…
Despite their irresistible success, deep learning algorithms still heavily rely on annotated data. On the other hand, unsupervised settings pose many challenges, especially about determining the right inductive bias in diverse scenarios.…
Noisy labels, resulting from mistakes in manual labeling or webly data collecting for supervised learning, can cause neural networks to overfit the misleading information and degrade the generalization performance. Self-supervised learning…
Assessing the blurriness of an object image is fundamentally important to improve the performance for object recognition and retrieval. The main challenge lies in the lack of abundant images with reliable labels and effective learning…
This manuscript presents a series of my selected contributions to the topic of label-efficient learning in computer vision and remote sensing. The central focus of this research is to develop and adapt methods that can learn effectively…
While multi-class 3D detectors are needed in many robotics applications, training them with fully labeled datasets can be expensive in labeling cost. An alternative approach is to have targeted single-class labels on disjoint data samples.…
Active learning approaches in computer vision generally involve querying strong labels for data. However, previous works have shown that weak supervision can be effective in training models for vision tasks while greatly reducing annotation…
Accurate identification of important objects in the scene is a prerequisite for safe and high-quality decision making and motion planning of intelligent agents (e.g., autonomous vehicles) that navigate in complex and dynamic environments.…
Object category localization is a challenging problem in computer vision. Standard supervised training requires bounding box annotations of object instances. This time-consuming annotation process is sidestepped in weakly supervised…
Due to the costliness of labelled data in real-world applications, semi-supervised object detectors, underpinned by pseudo labelling, are appealing. However, handling confusing samples is nontrivial: discarding valuable confusing samples…
This paper proposes MCSSL, a self-supervised learning approach for building custom object detection models in multi-camera networks. MCSSL associates bounding boxes between cameras with overlapping fields of view by leveraging epipolar…
Few-shot learning and self-supervised learning address different facets of the same problem: how to train a model with little or no labeled data. Few-shot learning aims for optimization methods and models that can learn efficiently to…
Partially-supervised learning can be challenging for segmentation due to the lack of supervision for unlabeled structures, and the methods directly applying fully-supervised learning could lead to incompatibility, meaning ground truth is…
Retail scenes usually contain densely packed high number of objects in each image. Standard object detection techniques use fully supervised training methodology. This is highly costly as annotating a large dense retail object detection…
Co-training, extended from self-training, is one of the frameworks for semi-supervised learning. Without natural split of features, single-view co-training works at the cost of training extra classifiers, where the algorithm should be…
Object detectors usually achieve promising results with the supervision of complete instance annotations. However, their performance is far from satisfactory with sparse instance annotations. Most existing methods for sparsely annotated…
Semi-supervised learning approaches train on small sets of labeled data along with large sets of unlabeled data. Self-training is a semi-supervised teacher-student approach that often suffers from the problem of "confirmation bias" that…
Generalising deep models to new data from new centres (termed here domains) remains a challenge. This is largely attributed to shifts in data statistics (domain shifts) between source and unseen domains. Recently, gradient-based…