paper-with-me

Papers

Sparse Network Inversion for Key Instance Detection in Multiple Instance Learning

2020-09-07 · Beomjo Shin, Junsu Cho, Hwanjo Yu, Seungjin Choi

Multiple Instance Learning (MIL) involves predicting a single label for a bag of instances, given positive or negative labels at bag-level, without accessing to label for each instance in the training phase. Since a positive bag contains both positive and negative instances, it is often required to detect positive instances (key instances) when a set of instances is categorized as a positive bag. The attention-based deep MIL model is a recent advance in both bag-level classification and key instance detection (KID). However, if the positive and negative instances in a positive bag are not clearly distinguishable, the attention-based deep MIL model has limited KID performance as the attention scores are skewed to few positive instances. In this paper, we present a method to improve the attention-based deep MIL model in the task of KID. The main idea is to use the neural network inversion to find which instances made contribution to the bag-level prediction produced by the trained MIL model. Moreover, we incorporate a sparseness constraint into the neural network inversion, leading to the sparse network inversion which is solved by the proximal gradient method. Numerical experiments on an MNIST-based image MIL dataset and two real-world histopathology datasets verify the validity of our method, demonstrating the KID performance is significantly improved while the performance of bag-level prediction is maintained.

📄 PDF Abstract BibTeX arXiv:2009.02909

Code (0)

등록된 구현이 없습니다.

Tasks

Multiple Instance Learning

Similar Papers 제목 키워드 기반

Multiple Instance Neural Networks Based on Sparse Attention for Cancer Detection using T-cell Receptor Sequences

2022-08-09 · Younghoon Kim, Tao Wang, Danyi Xiong, Xinlei Wang 외

Early detection of cancers has been much explored due to its paramount importance in biomedical fields. Among different types of data used to answer this biological question, studies based on T cell receptors (TCRs) are …

Multiple Instance Learning

Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusion

2022-11-19 · Xuewu Lin, Tianwei Lin, Zixiang Pei, Lichao Huang 외

Bird-eye-view (BEV) based methods have made great progress recently in multi-view 3D detection task. Comparing with BEV based methods, sparse based methods lag behind in performance, but still have lots of non-negligible…

3D Object Detectionobject-detectionObject DetectionRobust Camera Only 3D Object Detection

HINTED: Hard Instance Enhanced Detector with Mixed-Density Feature Fusion for Sparsely-Supervised 3D Object Detection

2024-01-01 · CVPR 2024 1 · Qiming Xia, Wei Ye, Hai Wu, Shijia Zhao 외

Current sparsely-supervised object detection methods largely depend on high threshold settings to derive high-quality pseudo labels from detector predictions. However hard instances within point clouds frequently dis…

3D Object Detectionobject-detectionObject Detection

SC-MIL: Sparsely Coded Multiple Instance Learning for Whole Slide Image Classification

2023-10-31 · Peijie Qiu, Pan Xiao, Wenhui Zhu, Yalin Wang 외

Multiple Instance Learning (MIL) has been widely used in weakly supervised whole slide image (WSI) classification. Typical MIL methods include a feature embedding part, which embeds the instances into features via a pre-…

Dictionary Learningimage-classificationImage ClassificationMultiple Instance Learning

PGID: Progressive Guided Inversion and Denoising for Robust Watermark Detection

2026-05-10 · Minh Quoc Duong, Chun Tong Lei, Chun Pong Lau arxiv

With the proliferation of AI-generated images, digital watermarking has become an essential safeguard for protecting intellectual property and mitigating malicious exploitation. Recent works on semantic watermarking have…