Related papers: ProtoMIL: Multiple Instance Learning with Prototyp…

Multiple instance learning (MIL) is a key algorithm for classification of whole slide images (WSI). Histology WSIs can have billions of pixels, which create enormous computational and annotation challenges. Typically, such images are…

With the increasing attention to pre-trained vision-language models (VLMs), \eg, CLIP, substantial efforts have been devoted to many downstream tasks, especially in test-time adaptation (TTA). However, previous works focus on learning…

Traditional image-based survival prediction models rely on discriminative patch labeling which make those methods not scalable to extend to large datasets. Recent studies have shown Multiple Instance Learning (MIL) framework is useful for…

We study the problem of learning from aggregate observations where supervision signals are given to sets of instances instead of individual instances, while the goal is still to predict labels of unseen individuals. A well-known example is…

Weakly supervised object detection (WSOD) is a challenging task when provided with image category supervision but required to simultaneously learn object locations and object detectors. Many WSOD approaches adopt multiple instance learning…

Vision-language models (VLMs) like CLIP excel in zero-shot learning but often require resource-intensive training to adapt to new tasks. Prompt learning techniques, such as CoOp and CoCoOp, offer efficient adaptation but tend to overfit to…

Transfer learning from large-scale pre-trained models has become essential for many computer vision tasks. Recent studies have shown that datasets like ImageNet are weakly labeled since images with multiple object classes present are…

This paper presents a novel approach, called Prototype-based Self-Distillation (ProS), for unsupervised face representation learning. The existing supervised methods heavily rely on a large amount of annotated training facial data, which…

Classifying images with an interpretable decision-making process is a long-standing problem in computer vision. In recent years, Prototypical Part Networks has gained traction as an approach for self-explainable neural networks, due to…

Multimodal molecular representation learning, which jointly models molecular graphs and their textual descriptions, enhances predictive accuracy and interpretability by enabling more robust and reliable predictions of drug toxicity,…

In this paper, we propose the MIML (Multi-Instance Multi-Label learning) framework where an example is described by multiple instances and associated with multiple class labels. Compared to traditional learning frameworks, the MIML…

Modern foundation models provide highly expressive visual representations, yet adapting them to high-resolution medical imaging remains challenging due to limited annotations and weak supervision. Mammography, in particular, is…

Multiple instance learning (MIL) has been widely used for representing whole-slide pathology images. However, spatial, semantic, and decision entanglements among instances limit its representation and interpretability. To address these…

Convolutional neural networks can be trained to perform histology slide classification using weak annotations with multiple instance learning (MIL). However, given the paucity of labeled histology data, direct application of MIL can easily…

Positive instance detection, especially for these in positive bags (true positive instances, TPIs), plays a key role for multiple instance learning (MIL) arising from a specific classification problem only provided with bag (a set of…

Multiple Instance Learning (MIL) tasks impose a strict logical constraint: a bag is labeled positive if and only if at least one instance within it is positive. While this iff constraint aligns with many real-world applications, recent work…

Attention-based multiple instance learning (AMIL) algorithms have proven to be successful in utilizing gigapixel whole-slide images (WSIs) for a variety of different computational pathology tasks such as outcome prediction and cancer…

Weakly supervised object detection (WSOD) is a challenging task that requires simultaneously learn object classifiers and estimate object locations under the supervision of image category labels. A major line of WSOD methods roots in…

Weakly Supervised Object Detection (WSOD), using only image-level annotations to train object detectors, is of growing importance in object recognition. In this paper, we propose a novel deep network for WSOD. Unlike previous networks that…

Although interpretable prototype networks have improved the transparency of deep learning image classification, the need for multiple prototypes in collaborative decision-making increases cognitive complexity and hinders user understanding.…