Related papers: BiSSL: Enhancing the Alignment Between Self-Superv…
Self-Supervised Learning (SSL) models rely on a pretext task to learn representations. Because this pretext task differs from the downstream tasks used to evaluate the performance of these models, there is an inherent misalignment or…
Self-supervised Learning (SSL) aims to learn transferable feature representations for downstream applications without relying on labeled data. The Barlow Twins algorithm, renowned for its widespread adoption and straightforward…
Semi-supervised learning (SSL) algorithms struggle to perform well when exposed to imbalanced training data. In this scenario, the generated pseudo-labels can exhibit a bias towards the majority class, and models that employ these…
Self-supervised vision-language pretraining from pure images and text with a contrastive loss is effective, but ignores fine-grained alignment due to a dual-stream architecture that aligns image and text representations only on a global…
State-of-the-art deep learning approaches for skin lesion recognition often require pretraining on larger and more varied datasets, to overcome the generalization limitations derived from the reduced size of the skin lesion imaging…
Recently, the cross-modal pretraining model has been employed to produce meaningful pseudo-labels to supervise the training of an image clustering model. However, numerous erroneous alignments in a cross-modal pre-training model could…
Magnetic Resonance Imaging (MRI) represents an important diagnostic modality; however, its inherently slow acquisition process poses challenges in obtaining fully-sampled $k$-space data under motion. In the absence of fully-sampled…
Self-supervised learning makes significant progress in pre-training large models, but struggles with small models. Mainstream solutions to this problem rely mainly on knowledge distillation, which involves a two-stage procedure: first…
Modern deep models are often pretrained on large-scale data with missing labels using composite objectives, where the relative weights of multiple loss terms act as hyperparameters. Tuning these weights with random search or Bayesian…
Pre-training a large transformer model on a massive amount of unlabeled data and fine-tuning it on labeled datasets for diverse downstream tasks has proven to be a successful strategy, for a variety of vision and natural language processing…
Handling uncertainty is critical for ensuring reliable decision-making in intelligent systems. Modern neural networks are known to be poorly calibrated, resulting in predicted confidence scores that are difficult to use. This article…
Recently, lots of deep networks are proposed to improve the quality of predicted super-resolution (SR) images, due to its widespread use in several image-based fields. However, with these networks being constructed deeper and deeper, they…
Effective data selection is essential for pretraining large language models (LLMs), enhancing efficiency and improving generalization to downstream tasks. However, existing approaches often require leveraging external pretrained models,…
Alignment between image and text has shown promising improvements on patch-level pre-trained document image models. However, investigating more effective or finer-grained alignment techniques during pre-training requires a large amount of…
In multi-robot systems, achieving coordinated missions remains a significant challenge due to the coupled nature of coordination behaviors and the lack of global information for individual robots. To mitigate these challenges, this paper…
Pretrained language models have achieved remarkable success in natural language understanding. However, fine-tuning pretrained models on limited training data tends to overfit and thus diminish performance. This paper presents Bi-Drop, a…
The paradigm of large-scale pre-training followed by downstream fine-tuning has been widely employed in various object detection algorithms. In this paper, we reveal discrepancies in data, model, and task between the pre-training and…
Semi-Supervised Learning (SSL) has been proved to be an effective way to leverage both labeled and unlabeled data at the same time. Recent semi-supervised approaches focus on deep neural networks and have achieved promising results on…
In recent years, deep neural networks (DNNs) have been found very successful for multi-label classification (MLC) of remote sensing (RS) images. Self-supervised pre-training combined with fine-tuning on a randomly selected small training…
Can a small amount of verified goal information steer the expensive self-supervised pretraining of foundation models? Standard pretraining optimizes a fixed proxy objective (e.g., next-token prediction), which can misallocate compute away…