RegionCL: Exploring Contrastive Region Pairs for Self-supervised Representation Learning

Contrastive learning is an important technique in the field of machine learning for learning data representations. In the field of self-supervised visual representation learning, the strategy of positive and negative sample selection is key to improving the efficiency and effectiveness of model learning. Traditional self-supervised learning methods often employ random sampling strategies to select positive and negative samples, but this approach may result in uneven sample quality when dealing with complex datasets, thereby affecting the learning outcomes. To alleviate this problem, this study is dedicated to exploring more effective strategies for positive and negative sample selection and processing to optimize the self-supervised learning process. To this end, we propose an improved method of self-supervised learning called contrastive learning with enhanced diversity. On the one hand, this method utilizes the weight parameters of the DINO pre-trained model to initialize the feature extraction network of SimCLR, providing more accurate calculations of feature similarity. On the other hand, by setting a threshold on the feature similarity matrix and penalizing (subtracting 0.5 from) similarity scores that do not exceed this threshold, we reduce the excessive impact of high similarity scores on model training, thereby helping the model better distinguish between positive and negative samples. In downstream image classification tasks, we conducted detailed evaluations of the improved model, specifically including fine-tuning and linear evaluation aspects. Experiments show that the proposed approach improves the performance of the loss functions and improves the accuracy of the proposed SimCLR model.

Cherry growth modeling based on Prior Distance Embedding contrastive learning: Pre-training, anomaly detection, semantic segmentation, and temporal modeling

Deep learning has become a valuable tool for the automation of certain medical image segmentation tasks, significantly relieving the workload of medical specialists. Some of these tasks require segmentation to be performed on a subset of the input dimensions, the most common case being 3D→2D. However, the performance of existing methods is strongly conditioned by the amount of labeled data available, as there is currently no data efficient method, e.g. transfer learning, that has been validated on these tasks. In this work, we propose a novel convolutional neural network (CNN) and self-supervised learning (SSL) method for label-efficient 3D→2D segmentation. The CNN is composed of a 3D encoder and a 2D decoder connected by novel 3D→2D blocks. The SSL method consists of reconstructing image pairs of modalities with different dimensionality. The approach has been validated in two tasks with clinical relevance: the en-face segmentation of geographic atrophy and reticular pseudodrusen in optical coherence tomography. Results on different datasets demonstrate that the proposed CNN significantly improves the state of the art in scenarios with limited labeled data by up to 8% in Dice score. Moreover, the proposed SSL method allows further improvement of this performance by up to 23%, and we show that the SSL is beneficial regardless of the network architecture. Our code is available at https://github.com/j-morano/multimodal-ssl-fpn.

Self-supervised learning provides a possible solution to extract effective visual representations from unlabeled histopathological images. However, existing methods either fail to make good use of domain-specific knowledge, or rely on side information like spatial proximity and magnification. In this paper, we propose CS-CO, a hybrid self-supervised visual representation learning method tailored for histopathological images, which integrates advantages of both generative and discriminative models. The proposed method consists of two self-supervised learning stages: cross-stain prediction (CS) and contrastive learning (CO), both of which are designed based on domain-specific knowledge and do not require side information. A novel data augmentation approach, stain vector perturbation, is specifically proposed to serve contrastive learning. Experimental results on the public dataset NCT-CRC-HE-100K demonstrate the superiority of the proposed method for histopathological image visual representation. Under the common linear evaluation protocol, our method achieves 0.915 eight-class classification accuracy with only 1,000 labeled data, which is about 1.3% higher than the fully-supervised ResNet18 classifier trained with the whole 89,434 labeled training data. Our code is available at https://github.com/easonyang1996/CS-CO.

Owing to the prohibitive cost of manual annotation for enormous medical images, self-supervised learning (SSL) has gained substantial attention and shown promise in various medical imaging tasks. Among SSL approaches, contrastive learning has emerged as a prominent one, encouraging models to encode semantic information that remains invariant between different augmented views. However, this invariance can be spurious for medical images, as subtle but critical medical features can be suppressed during augmentations. In this paper, we mitigate this issue by encoding the learned feature embeddings as probability distributions rather than fixed vectors, thus capturing a richer and more nuanced spectrum of information. Furthermore, we propose a unified probabilistic framework that seamlessly integrates multiple SSL approaches. Our method achieves superior performance over the state-of-the-art SSL methods on various downstream tasks across multiple datasets, including medical image segmentation and classification. We further validate the method through additional analyses of robustness to stronger augmentations, label efficiency under limited fine-tuning labels, and computational trade-offs. The code will be released upon the acceptance of the manuscript1.

The success of supervised deep learning heavily depends on large labeled datasets whose construction is often challenging in medical image analysis. Contrastive learning, a variant of self-supervised learning, is a potential solution to alleviate the strong demand for data annotation. In this work, we extend the contrastive learning framework to 3D volumetric medical imaging. Specifically, we propose (1) multiview contrasting strategy to maximize the mutual information between three views of 3D image to learn global representations and (2) long-short spatial contrasting strategy to learn local representations by matching a short spatial clip to a long spatial clip in the latent space. To combine these two strategies, we propose multiview long-short spatial contrastive learning (MLSSCL) framework, which can effectively learn generic 3D representations. Our extensive experiments on two brain Magnetic Resonance Imaging (MRI) datasets demonstrate that MLSSCL significantly outperforms learning from scratch and other self-supervised learning methods on both classification and segmentation tasks.

Pathological diagnosis assists in saving human lives, but such models are annotation hungry and pathological images are notably expensive to annotate. Contrastive learning could be a promising solution that relies only on the unlabeled training data to generate informative representations. However, the majority of current methods in contrastive learning have the following two issues: (1) positive samples produced through random augmentation are less challenging, and (2) false negative pairs problem caused by negative sampling bias. To alleviate the above issues, we propose a novel contrastive learning method called Cluster-Aware Adversarial Contrastive Learning (CA2CL). Specifically, a mixed data augmentation technique is provided to learn more transferable representations by generating more discriminative sample pairs. Furthermore, to mitigate the effects of inherent false negative pairs, we adopt a cluster-aware loss to identify similarities between instances and incorporate them into the process of contrastive learning. Finally, we generate challenging contrastive data pairs by adversarial learning, and adversarially learn robust representations in the representation space without the labeled training data, which aims to maximize the similarity between the augmented sample and the related adversarial sample. Our proposed CA2CL is evaluated on two public datasets: NCT-CRC-HE and PCam for the fine-tuning and linear evaluation tasks and on two other public datasets: GlaS and CARG for the detection and segmentation tasks, respectively. Extensive experimental results demonstrate the superior performance improvement of our method over several Self-supervised learning (SSL) methods and ImageNet pretraining particularly in scenarios with limited data availability for all four tasks.

Behavior sequences are generated by a series of spatio-temporal interactions and have a high-dimensional nonlinear manifold structure. Therefore, it is difficult to learn 3D behavior representations without relying on supervised signals. To this end, self-supervised learning methods can be used to explore the rich information contained in the data itself. Context-context contrastive self-supervised methods construct the manifold embedded in Euclidean space by learning the distance relationship between data, and find the geometric distribution of data. However, traditional Euclidean space is difficult to express context joint features. In order to obtain an effective global representation from the relationship between data under unlabeled conditions, this paper adopts contrastive learning to compare global feature, and proposes a self-supervised learning method based on hyperbolic embedding to mine the nonlinear relationship of behavior trajectories. This method adopts the framework of discarding negative samples, which overcomes the shortcomings of the paradigm based on positive and negative samples that pull similar data away in the feature space. Meanwhile, the output of the network is embedded in a hyperbolic space, and a multi-layer perceptron is added to convert the entire module into a homotopic mapping by using the geometric properties of operations in the hyperbolic space, so as to obtain homotopy invariant knowledge. The proposed method combines the geometric properties of hyperbolic manifolds and the equivariance of homotopy groups to promote better supervised signals for the network, which improves the performance of unsupervised learning.

LPCL: Localized prominence contrastive learning for self-supervised dense visual pre-training

BLoG: Bootstrapped graph representation learning with local and global regularization for recommendation

Spatiotemporal self-supervised predictive learning for atmospheric variable prediction via multi-group multi-attention

Deep one-class probability learning for end-to-end image classification.

Generative and contrastive graph representation learning with message passing.

A large-scale labeled dataset is a key factor for the success of supervised deep learning in most ophthalmic image analysis scenarios. However, limited annotated data is very common in ophthalmic image analysis, since manual annotation is time-consuming and labor-intensive. Self-supervised learning (SSL) methods bring huge opportunities for better utilizing unlabeled data, as they do not require massive annotations. To utilize as many unlabeled ophthalmic images as possible, it is necessary to break the dimension barrier, simultaneously making use of both 2D and 3D images as well as alleviating the issue of catastrophic forgetting. In this paper, we propose a universal self-supervised Transformer framework named Uni4Eye++ to discover the intrinsic image characteristic and capture domain-specific feature embedding in ophthalmic images. Uni4Eye++ can serve as a global feature extractor, which builds its basis on a Masked Image Modeling task with a Vision Transformer architecture. On the basis of our previous work Uni4Eye, we further employ an image entropy guided masking strategy to reconstruct more-informative patches and a dynamic head generator module to alleviate modality confusion. We evaluate the performance of our pre-trained Uni4Eye++ encoder by fine-tuning it on multiple downstream ophthalmic image classification and segmentation tasks. The superiority of Uni4Eye++ is successfully established through comparisons to other state-of-the-art SSL pre-training methods. Our code is available at https://github.com/Davidczy/Uni4Eye++.

Adaptive self-supervised learning for sequential recommendation