Related papers: Online progressive instance-balanced sampling for …
Multiple instance learning (MIL) has emerged as a powerful framework for weakly supervised whole slide image (WSI) classification, enabling slide-level predictions without requiring detailed patch-level annotations. Despite its success, a…
Multi-Instance Learning (MIL) has shown impressive performance for histopathology whole slide image (WSI) analysis using bags or pseudo-bags. It involves instance sampling, feature representation, and decision-making. However, existing…
Patch-level image representation is very important for object classification and detection, since it is robust to spatial transformation, scale variation, and cluttered background. Many existing methods usually require fine-grained…
Weakly-supervised temporal action localization aims to localize and recognize actions in untrimmed videos with only video-level category labels during training. Without instance-level annotations, most existing methods follow the…
Multiple Instance Learning (MIL) recently provides an appealing way to alleviate the drifting problem in visual tracking. Following the tracking-by-detection framework, an online MILBoost approach is developed that sequentially chooses weak…
In this paper, we explore the mask representation in instance segmentation with Point-of-Interest (PoI) features. Differentiating multiple potential instances within a single PoI feature is challenging because learning a high-dimensional…
Multiple instance learning (MIL) was a weakly supervised learning approach that sought to assign binary class labels to collections of instances known as bags. However, due to their weak supervision nature, the MIL methods were susceptible…
Using search engines for web image retrieval is a tempting alternative to manual curation when creating an image dataset, but their main drawback remains the proportion of incorrect (noisy) samples retrieved. These noisy samples have been…
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…
Whole slide image (WSI) classification often relies on deep weakly supervised multiple instance learning (MIL) methods to handle gigapixel resolution images and slide-level labels. Yet the decent performance of deep learning comes from…
To imitate the ability of keeping learning of human, continual learning which can learn from a never-ending data stream has attracted more interests recently. In all settings, the online class incremental learning (OCIL), where incoming…
Detecting novel objects from few examples has become an emerging topic in computer vision recently. However, these methods need fully annotated training images to learn new object categories which limits their applicability in real world…
Classical object detectors are incapable of detecting novel class objects that are not encountered before. Regarding this issue, Open-Vocabulary Object Detection (OVOD) is proposed, which aims to detect the objects in the candidate class…
Efficient and reliable methods for training of object detectors are in higher demand than ever, and more and more data relevant to the field is becoming available. However, large datasets like Open Images Dataset v4 (OID) are sparsely…
This paper tackles two key challenges: detecting small, dense, and overlapping objects (a major hurdle in computer vision) and improving the quality of noisy images, especially those encountered in industrial environments. [1, 2]. Our focus…
Ensemble technique and under-sampling technique are both effective tools used for imbalanced dataset classification problems. In this paper, a novel ensemble method combining the advantages of both ensemble learning for biasing classifiers…
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.…
Coherent diffraction imaging (CDI) is high-resolution lensless microscopy that has been applied to image a wide range of specimens using synchrotron radiation, X-ray free electron lasers, high harmonic generation, soft X-ray laser and…
Learning neural implicit fields of 3D shapes is a rapidly emerging field that enables shape representation at arbitrary resolutions. Due to the flexibility, neural implicit fields have succeeded in many research areas, including shape…
Various multi-instance learning (MIL) based approaches have been developed and successfully applied to whole-slide pathological images (WSI). Existing MIL methods emphasize the importance of feature aggregators, but largely neglect the…