Related papers: PCL: Proposal Cluster Learning for Weakly Supervis…
Multiple instance learning (MIL) problem is currently solved from either bag-classification or instance-classification perspective, both of which ignore important information contained in some instances and result in limited performance.…
Weakly-supervised instance segmentation aims to detect and segment object instances precisely, given imagelevel labels only. Unlike previous methods which are composed of multiple offline stages, we propose Sequential Label Propagation and…
Recently, unsupervised salient object detection (USOD) has gained increasing attention due to its annotation-free nature. However, current methods mainly focus on specific tasks such as RGB and RGB-D, neglecting the potential for task…
Most existing weakly supervised localization (WSL) approaches learn detectors by finding positive bounding boxes based on features learned with image-level supervision. However, those features do not contain spatial location related…
The human vision and perception system is inherently incremental where new knowledge is continually learned over time whilst existing knowledge is retained. On the other hand, deep learning networks are ill-equipped for incremental…
The detection of induced pluripotent stem cell (iPSC) colonies often needs the precise extraction of the colony features. However, existing computerized systems relied on segmentation of contours by preprocessing for classifying the colony…
Fully-supervised salient object detection (SOD) methods have made great progress, but such methods often rely on a large number of pixel-level annotations, which are time-consuming and labour-intensive. In this paper, we focus on a new…
Weakly supervised multiple instance learning (MIL) is a challenging task given that only bag-level labels are provided, while each bag typically contains multiple instances. This topic has been extensively studied in histopathological image…
Fine-grained object categorization aims for distinguishing objects of subordinate categories that belong to the same entry-level object category. The task is challenging due to the facts that (1) training images with ground-truth labels are…
We present Deeply Supervised Object Detector (DSOD), a framework that can learn object detectors from scratch. State-of-the-art object objectors rely heavily on the off-the-shelf networks pre-trained on large-scale classification datasets…
Multi-instance learning (MIL) deals with objects represented as bags of instances and can predict instance labels from bag-level supervision. However, significant performance gaps exist between instance-level MIL algorithms and supervised…
Weakly supervised object localization (WSOL) is a challenging problem which aims to localize objects with only image-level labels. Due to the lack of ground truth bounding boxes, class labels are mainly employed to train the model. This…
After learning a new object category from image-level annotations (with no object bounding boxes), humans are remarkably good at precisely localizing those objects. However, building good object localizers (i.e., detectors) currently…
Conventional training of deep neural networks requires a large number of the annotated image which is a laborious and time-consuming task, particularly for rare objects. Few-shot object detection (FSOD) methods offer a remedy by realizing…
Despite the substantial progress of active learning for image recognition, there still lacks an instance-level active learning method specified for object detection. In this paper, we propose Multiple Instance Active Object Detection…
Few-shot object detection (FSOD) aims to detect objects using only a few examples. How to adapt state-of-the-art object detectors to the few-shot domain remains challenging. Object proposal is a key ingredient in modern object detectors.…
Recent advances of deep learning have achieved remarkable performances in various challenging computer vision tasks. Especially in object localization, deep convolutional neural networks outperform traditional approaches based on extraction…
Semi-supervised object detection (SSOD) aims to boost detection performance by leveraging extra unlabeled data. The teacher-student framework has been shown to be promising for SSOD, in which a teacher network generates pseudo-labels for…
In this work, we propose Adversarial Complementary Learning (ACoL) to automatically localize integral objects of semantic interest with weak supervision. We first mathematically prove that class localization maps can be obtained by directly…
Weakly supervised object detection (WSOD) is a challenging task, in which image-level labels (e.g., categories of the instances in the whole image) are used to train an object detector. Many existing methods follow the standard multiple…