Related papers: SPICE: Semantic Pseudo-labeling for Image Clusteri…

Pixelwise semantic image labeling is an important, yet challenging, task with many applications. Typical approaches to tackle this problem involve either the training of deep networks on vast amounts of images to directly infer the labels…

Auto-Encoder (AE)-based deep subspace clustering (DSC) methods have achieved impressive performance due to the powerful representation extracted using deep neural networks while prioritizing categorical separability. However,…

Although unsupervised person re-identification (Re-ID) has drawn increasing research attention recently, it remains challenging to learn discriminative features without annotations across disjoint camera views. In this paper, we address the…

Image clustering, which involves grouping images into different clusters without labels, is a key task in unsupervised learning. Although previous deep clustering methods have achieved remarkable results, they only explore the intrinsic…

We present LSD-C, a novel method to identify clusters in an unlabeled dataset. Our algorithm first establishes pairwise connections in the feature space between the samples of the minibatch based on a similarity metric. Then it regroups in…

Learning semantic segmentation models under image-level supervision is far more challenging than under fully supervised setting. Without knowing the exact pixel-label correspondence, most weakly-supervised methods rely on external models to…

Clustering is the task of gathering similar data samples into clusters without using any predefined labels. It has been widely studied in machine learning literature, and recent advancements in deep learning have revived interest in this…

In this paper, we introduce a neural network framework for semi-supervised clustering (SSC) with pairwise (must-link or cannot-link) constraints. In contrast to existing approaches, we decompose SSC into two simpler classification…

Unsupervised clustering aims at discovering the semantic categories of data according to some distance measured in the representation space. However, different categories often overlap with each other in the representation space at the…

Segmentation is a critical task in computational pathology, as it identifies areas affected by disease or abnormal growth and is essential for diagnosis and treatment. However, acquiring high-quality pixel-level supervised segmentation data…

Nuclei instance segmentation on histopathology images is of great clinical value for disease analysis. Generally, fully-supervised algorithms for this task require pixel-wise manual annotations, which is especially time-consuming and…

Fine-grained clustering is a practical yet challenging task, whose essence lies in capturing the subtle differences between instances of different classes. Such subtle differences can be easily disrupted by data augmentation or be…

Semi-supervised learning has substantially advanced medical image segmentation since it alleviates the heavy burden of acquiring the costly expert-examined annotations. Especially, the consistency-based approaches have attracted more…

Recently, deep clustering, which is able to perform feature learning that favors clustering tasks via deep neural networks, has achieved remarkable performance in image clustering applications. However, the existing deep clustering…

Manually annotating complex scene point cloud datasets is both costly and error-prone. To reduce the reliance on labeled data, a new model called SnapshotNet is proposed as a self-supervised feature learning approach, which directly works…

Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process. To address this issue, we…

Diffusion-based image generation models can enhance image quality when conditioned on ground truth labels. Here, we conduct a comprehensive experimental study on image-level conditioning for diffusion models using cluster assignments. We…

Unsupervised person re-identification (Re-ID) aims to learn a feature network with cross-camera retrieval capability in unlabelled datasets. Although the pseudo-label based methods have achieved great progress in Re-ID, their performance in…

We propose an effective subspace selection scheme as a post-processing step to improve results obtained by sparse subspace clustering (SSC). Our method starts by the computation of stable subspaces using a novel random sampling scheme. Thus…

Deep clustering has recently emerged as a promising technique for complex data clustering. Despite the considerable progress, previous deep clustering works mostly build or learn the final clustering by only utilizing a single layer of…