Enhancing Instance-Level Image Classification with Set-Level Labels
Not on the map. Why?
Abstract (arXiv)
Instance-level image classification tasks have traditionally relied on single-instance labels to train models, e.g., few-shot learning and transfer learning. However, set-level coarse-grained labels that capture relationships among instances can provide richer information in real-world scenarios. In this paper, we present a novel approach to enhance instance-level image classification by leveraging set-level labels. We provide a theoretical analysis of the proposed method, including recognition conditions for fast excess risk rate, shedding light on the theoretical foundations of our approach. We conducted experiments on two distinct categories of datasets: natural image datasets and histopathology image datasets. Our experimental results demonstrate the effectiveness of our approach, showcasing improved classification performance compared to traditional single-instance label-based methods. Notably, our algorithm achieves 13% improvement in classification accuracy compared to the strongest baseline on the histopathology image classification benchmarks. Importantly, our experimental findings align with the theoretical analysis, reinforcing the robustness and reliability of our proposed method. This work bridges the gap between instance-level and set-level image classification, offering a promising avenue for advancing the capabilities of image classification models with set-level coarse-grained labels.
Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 62 of its 80 references that are in the map. First posted on arXiv 9 Nov 2023.
Builds on
62 of 80 references.
References · 62
- 2017Attention Is All You Needcited by 60,106
- 2015Deep Residual Learning for Image Recognitioncited by 51,950
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,588
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,043
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,009
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,492
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,991
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,870
- 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,730
- 2017Prototypical Networks for Few-shot Learningcited by 3,011
- 2020Exploring Simple Siamese Representation Learningcited by 2,860
- 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,850
38 more
- 2020Supervised Contrastive Learningcited by 2,811
- 2017Billion-scale similarity search with GPUscited by 2,490
- 2013Visualizing and Understanding Convolutional Networkscited by 2,282
- 2016Matching Networks for One Shot Learningcited by 2,251
- 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,841
- 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,612
- 2017Deep Setscited by 1,404
- 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,141
- 2018Attention-based Deep Multiple Instance Learningcited by 1,083
- 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,023
- 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 916
- 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 808
- 2020Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Imagescited by 739
- 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 733
- 2019A Closer Look at Few-shot Classificationcited by 683
- 2019Data-Efficient Image Recognition with Contrastive Predictive Codingcited by 673
- 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
- 2021TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classificationcited by 551
- 2017Large Batch Training of Convolutional Networkscited by 529
- 2018Meta-Learning with Latent Embedding Optimizationcited by 476
- 2020Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learningcited by 474
- 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
- 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 436
- 2013DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognitioncited by 423
- 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
- 2017A simple neural network module for relational reasoningcited by 345
- 2017A Structured Self-attentive Sentence Embeddingcited by 318
- 2015Order Matters: Sequence to sequence for setscited by 236
- 2020Few-Shot Learning via Learning the Representation, Provablycited by 213
- 2018Low-Shot Learning from Imaginary Datacited by 181
- 2020Whole Slide Images based Cancer Survival Prediction using Attention Guided Deep Multiple Instance Learning Networkscited by 178
- 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
- 2021Whole Slide Images are 2D Point Clouds: Context-Aware Survival Prediction using Patch-based Graph Convolutional Networkscited by 124
- 2016Towards a Neural Statisticiancited by 119
- 2019Finding Task-Relevant Features for Few-Shot Learning by Category Traversalcited by 101
- 2020BYOL works even without batch statisticscited by 95
- 2020Deep Learning-based Computational Pathology Predicts Origins for Cancers of Unknown Primarycited by 89
- 2020Multi-scale Domain-adversarial Multiple-instance CNN for Cancer Subtype Classification with Unannotated Histopathological Imagescited by 81
50 most cited of 62 All 62 (JSON)
Built on by
Not cited yet.