Related papers: Self-supervised Vision Transformers for Joint SAR-…
Current visual representation learning remains bifurcated: vision-language models (e.g., CLIP) excel at global semantic alignment but lack spatial precision, while self-supervised methods (e.g., MAE, DINO) capture intricate local structures…
Contrastive Learning (CL), a leading paradigm in Self-Supervised Learning (SSL), typically relies on pairs of data views generated through augmentation. While multiple augmentations per instance (more than two) improve generalization in…
In the medical domain, acquiring large datasets poses significant challenges due to privacy concerns. Nonetheless, the development of a robust deep-learning model for retinal disease diagnosis necessitates a substantial dataset for…
The image reconstruction process in medical imaging can be treated as solving an inverse problem. The inverse problem is usually solved using time-consuming iterative algorithms with sparsity or other constraints. Recently, deep neural…
Automated medical diagnosis through image-based neural networks has increased in popularity and matured over years. Nevertheless, it is confined by the scarcity of medical images and the expensive labor annotation costs. Self-Supervised…
This paper introduces MixDiff, a new self-supervised learning (SSL) pre-training framework that combines real and synthetic images. Unlike traditional SSL methods that predominantly use real images, MixDiff uses a variant of Stable…
Often, applications of self-supervised learning to 3D medical data opt to use 3D variants of successful 2D network architectures. Although promising approaches, they are significantly more computationally demanding to train, and thus reduce…
Despite the impressive progress of self-supervised learning (SSL), its applicability to low-compute networks has received limited attention. Reported performance has trailed behind standard supervised pre-training by a large margin, barring…
This manuscript introduces SARFormer, a modified Vision Transformer (ViT) architecture designed for processing one or multiple synthetic aperture radar (SAR) images. Given the complex image geometry of SAR data, we propose an acquisition…
Semi-supervised learning (SSL) aims to help reduce the cost of the manual labelling process by leveraging a substantial pool of unlabelled data alongside a limited set of labelled data during the training phase. Since pixel-level manual…
Self-Supervised Learning (SSL) is a reliable learning mechanism in which a robot uses an original, trusted sensor cue for training to recognize an additional, complementary sensor cue. We study for the first time in SSL how a robot's…
Visual Self-Supervised Learning (SSL) currently underperforms Contrastive Language-Image Pretraining (CLIP) in multimodal settings such as Visual Question Answering (VQA). This multimodal gap is often attributed to the semantics introduced…
Self-Supervised Learning (SSL) has become a powerful solution to extract rich representations from unlabeled data. Yet, SSL research is mostly focused on clean, curated and high-quality datasets. As a result, applying SSL on noisy data…
At the core of self-supervised learning for vision is the idea of learning invariant or equivariant representations with respect to a set of data transformations. This approach, however, introduces strong inductive biases, which can render…
Recent advances in self-supervised learning (SSL) have largely closed the gap with supervised ImageNet pretraining. Despite their success these methods have been primarily applied to unlabeled ImageNet images, and show marginal gains when…
Recent advancements in Self-Supervised Learning (SSL) have shown promising results in Speaker Verification (SV). However, narrowing the performance gap with supervised systems remains an ongoing challenge. Several studies have observed that…
State-of-the-art methods for self-supervised learning (SSL) build representations by maximizing the similarity between different transformed "views" of a sample. Without sufficient diversity in the transformations used to create views,…
Wildlife re-identification aims to match individuals of the same species across different observations. Current state-of-the-art (SOTA) models rely on class labels to train supervised models for individual classification. This dependence on…
We investigate whether self-supervised learning (SSL) can improve online reinforcement learning (RL) from pixels. We extend the contrastive reinforcement learning framework (e.g., CURL) that jointly optimizes SSL and RL losses and conduct…
Current self-supervised learning (SSL) methods (e.g., SimCLR, DINO, VICReg,MOCOv3) target primarily on representations at instance level and do not generalize well to dense prediction tasks, such as object detection and segmentation.Towards…