Related papers: Multi-scale Contrastive Adaptor Learning for Segme…

Given a single labeled example, in-context segmentation aims to segment corresponding objects. This setting, known as one-shot segmentation in few-shot learning, explores the segmentation model's generalization ability and has been applied…

Weakly supervised visual recognition using inexact supervision is a critical yet challenging learning problem. It significantly reduces human labeling costs and traditionally relies on multi-instance learning and pseudo-labeling. This paper…

The diversity of retinal imaging devices poses a significant challenge: domain shift, which leads to performance degradation when applying the deep learning models trained on one domain to new testing domains. In this paper, we propose a…

Recent self-supervised contrastive methods have been able to produce impressive transferable visual representations by learning to be invariant to different data augmentations. However, these methods implicitly assume a particular set of…

The existing contrastive learning methods mainly focus on single-grained representation learning, e.g., part-level, object-level or scene-level ones, thus inevitably neglecting the transferability of representations on other granularity…

Foundation models like the Segment Anything Model (SAM) demonstrate impressive zero-shot generalization but frequently degrade under diverse real-world illumination, particularly for instance segmentation. In this work, we address this…

In this work, we present Multi-Level Contrastive Learning for Dense Prediction Task (MCL), an efficient self-supervised method for learning region-level feature representation for dense prediction tasks. Our method is motivated by the three…

To date, most existing self-supervised learning methods are designed and optimized for image classification. These pre-trained models can be sub-optimal for dense prediction tasks due to the discrepancy between image-level prediction and…

Reliable detection of anomalies is crucial when deploying machine learning models in practice, but remains challenging due to the lack of labeled data. To tackle this challenge, contrastive learning approaches are becoming increasingly…

The Segment Anything Model (SAM) is a widely used vision foundation model with diverse applications, including image segmentation, detection, and tracking. Given SAM's wide applications, understanding its robustness against adversarial…

Fully supervised change detection methods have achieved significant advancements in performance, yet they depend severely on acquiring costly pixel-level labels. Considering that the patch-level annotations also contain abundant information…

This paper presents Contrastive Transformer, a contrastive learning scheme using the Transformer innate patches. Contrastive Transformer enables existing contrastive learning techniques, often used for image classification, to benefit dense…

Recent advancements in machine learning (ML), natural language processing (NLP), and foundational models have shown promise for real-life applications in critical, albeit compute-constrainted fields like healthcare. In such areas, combining…

Segment Anything Model (SAM) has gained significant recognition in the field of semantic segmentation due to its versatile capabilities and impressive performance. Despite its success, SAM faces two primary limitations: (1) it relies…

Semi-supervised learning is a sound measure to relieve the strict demand of abundant annotated datasets, especially for challenging multi-organ segmentation . However, most existing SSL methods predict pixels in a single image…

Pre-training a recognition model with contrastive learning on a large dataset of unlabeled data has shown great potential to boost the performance of a downstream task, e.g., image classification. However, in domains such as medical…

The emergence of large foundation models has propelled significant advances in various domains. The Segment Anything Model (SAM), a leading model for image segmentation, exemplifies these advances, outperforming traditional methods.…

Camouflaged Object Detection (COD) aims to segment objects that blend seamlessly into complex backgrounds, with growing interest in exploiting additional visual modalities to enhance robustness through complementary information. However,…

Recent unsupervised approaches to domain adaptation primarily focus on minimizing the gap between the source and the target domains through refining the feature generator, in order to learn a better alignment between the two domains. This…

Accurate prediction of protein-ligand interactions is essential for computer-aided drug discovery. However, existing methods often fail to capture solvent-dependent conformational changes and lack the ability to jointly learn multiple…