Divide and Conquer Self-Supervised Learning for High-Content Imaging

• URL: http://arxiv.org/abs/2503.07444v1
• Date: Mon, 10 Mar 2025 15:24:36 GMT
• Title: Divide and Conquer Self-Supervised Learning for High-Content Imaging
• Authors: Lucas Farndale, Paul Henderson, Edward W Roberts, Ke Yuan,
• Abstract summary: Split Component Embedding Registration (SpliCER) is a novel architecture which splits the image into sections and distils information from each section to guide the model to learn more subtle and complex features without compromising on simpler features.<n>SpliCER offers a powerful new tool for representation learning, enabling models to uncover complex features which could be overlooked by other methods.
• Score: 6.880995184251855
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Self-supervised representation learning methods often fail to learn subtle or complex features, which can be dominated by simpler patterns which are much easier to learn. This limitation is particularly problematic in applications to science and engineering, as complex features can be critical for discovery and analysis. To address this, we introduce Split Component Embedding Registration (SpliCER), a novel architecture which splits the image into sections and distils information from each section to guide the model to learn more subtle and complex features without compromising on simpler features. SpliCER is compatible with any self-supervised loss function and can be integrated into existing methods without modification. The primary contributions of this work are as follows: i) we demonstrate that existing self-supervised methods can learn shortcut solutions when simple and complex features are both present; ii) we introduce a novel self-supervised training method, SpliCER, to overcome the limitations of existing methods, and achieve significant downstream performance improvements; iii) we demonstrate the effectiveness of SpliCER in cutting-edge medical and geospatial imaging settings. SpliCER offers a powerful new tool for representation learning, enabling models to uncover complex features which could be overlooked by other methods.

Related papers

• I-Con: A Unifying Framework for Representation Learning [23.13433942006414]
  We introduce a single information-theoretic equation that generalizes a large collection of modern loss functions in machine learning. We show that several broad classes of machine learning methods are precisely minimizing an integrated KL divergence between two conditional distributions. This viewpoint exposes a hidden information geometry underlying clustering, spectral methods, dimensionality reduction, contrastive learning, and supervised learning.
  arXiv  Detail & Related papers  (2025-04-23T17:59:01Z)
• Equivariant Representation Learning for Augmentation-based Self-Supervised Learning via Image Reconstruction [3.7003845808210594]
  We propose integrating an image reconstruction task as an auxiliary component in augmentation-based self-supervised learning algorithms.<n>Our method implements a cross-attention mechanism to blend features learned from two augmented views, subsequently reconstructing one of them.<n>Results consistently demonstrate significant improvements over standard augmentation-based self-supervised learning methods.
  arXiv  Detail & Related papers  (2024-12-04T13:47:37Z)
• Understanding Visual Feature Reliance through the Lens of Complexity [14.282243225622093]
  We introduce a new metric for quantifying feature complexity, based on $mathscrV$-information. We analyze the complexities of 10,000 features, represented as directions in the penultimate layer, that were extracted from a standard ImageNet-trained vision model.
  arXiv  Detail & Related papers  (2024-07-08T16:21:53Z)
• An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognition [49.45660055499103]
  Zero-shot human skeleton-based action recognition aims to construct a model that can recognize actions outside the categories seen during training. Previous research has focused on aligning sequences' visual and semantic spatial distributions. We introduce a new loss function sampling method to obtain a tight and robust representation.
  arXiv  Detail & Related papers  (2024-06-02T06:53:01Z)
• Visual Imitation Learning with Calibrated Contrastive Representation [44.63125396964309]
  Adversarial Imitation Learning (AIL) allows the agent to reproduce expert behavior with low-dimensional states and actions. This paper proposes a simple and effective solution by incorporating contrastive representative learning into visual AIL framework.
  arXiv  Detail & Related papers  (2024-01-21T04:18:30Z)
• VILLS -- Video-Image Learning to Learn Semantics for Person Re-Identification [51.89551385538251]
  We propose VILLS (Video-Image Learning to Learn Semantics), a self-supervised method that jointly learns spatial and temporal features from images and videos. VILLS first designs a local semantic extraction module that adaptively extracts semantically consistent and robust spatial features. Then, VILLS designs a unified feature learning and adaptation module to represent image and video modalities in a consistent feature space.
  arXiv  Detail & Related papers  (2023-11-27T19:30:30Z)
• Epistemic Graph: A Plug-And-Play Module For Hybrid Representation Learning [46.48026220464475]
  Humans exhibit hybrid learning, seamlessly integrating structured knowledge for cross-domain recognition or relying on a smaller amount of data samples for few-shot learning. We introduce a novel Epistemic Graph Layer (EGLayer) to enable hybrid learning, enhancing the exchange of information between deep features and a structured knowledge graph.
  arXiv  Detail & Related papers  (2023-05-30T04:10:15Z)
• Combining Reconstruction and Contrastive Methods for Multimodal Representations in RL [16.792949555151978]
  Learning self-supervised representations using reconstruction or contrastive losses improves performance and sample complexity of image-based and multimodal reinforcement learning (RL) Here, different self-supervised loss functions have distinct advantages and limitations depending on the information density of the underlying sensor modality. We propose Contrastive Reconstructive Aggregated representation Learning (CoRAL), a unified framework enabling us to choose the most appropriate self-supervised loss for each sensor modality.
  arXiv  Detail & Related papers  (2023-02-10T15:57:20Z)
• Interactive Feature Embedding for Infrared and Visible Image Fusion [94.77188069479155]
  General deep learning-based methods for infrared and visible image fusion rely on the unsupervised mechanism for vital information retention. We propose a novel interactive feature embedding in self-supervised learning framework for infrared and visible image fusion.
  arXiv  Detail & Related papers  (2022-11-09T13:34:42Z)
• Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning [53.17258888552998]
  This work proposes an exploration variant of the basic $Q$-learning protocol with linear function approximation. We show that the performance of the algorithm degrades very gracefully under a novel and more permissive notion of approximation error.
  arXiv  Detail & Related papers  (2022-06-01T23:26:51Z)
• An Empirical Investigation of Representation Learning for Imitation [76.48784376425911]
  Recent work in vision, reinforcement learning, and NLP has shown that auxiliary representation learning objectives can reduce the need for large amounts of expensive, task-specific data. We propose a modular framework for constructing representation learning algorithms, then use our framework to evaluate the utility of representation learning for imitation.
  arXiv  Detail & Related papers  (2022-05-16T11:23:42Z)
• Progressive Self-Guided Loss for Salient Object Detection [102.35488902433896]
  We present a progressive self-guided loss function to facilitate deep learning-based salient object detection in images. Our framework takes advantage of adaptively aggregated multi-scale features to locate and detect salient objects effectively.
  arXiv  Detail & Related papers  (2021-01-07T07:33:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.