Related papers: Franca: Nested Matryoshka Clustering for Scalable …

Multi-view clustering can partition data samples into their categories by learning a consensus representation in an unsupervised way and has received more and more attention in recent years. However, there is an untrusted fusion problem.…

Accurately representing the complex linkages and inherent uncertainties included in huge datasets is still a major difficulty in the field of data clustering. We address these issues with our proposed Unified Neutrosophic Clustering…

We introduce FLARE, a family of vision language models (VLMs) with a fully vision-language alignment and integration paradigm. Unlike existing approaches that rely on single MLP projectors for modality alignment and defer cross-modal…

Vertical Federated Learning (VFL) enables collaborative analysis across parties holding complementary feature views of the same samples, yet existing approaches are largely restricted to distributed variants of $k$-means, requiring…

Given a large unlabeled set of images, how to efficiently and effectively group them into clusters based on extracted visual representations remains a challenging problem. To address this problem, we propose a convolutional neural network…

Self-supervised visual foundation models produce powerful embeddings that achieve remarkable performance on a wide range of downstream tasks. However, unlike vision-language models such as CLIP, self-supervised visual features are not…

Common approaches rely on fixed-length embedding vectors from language models as sentence embeddings for downstream tasks such as semantic textual similarity (STS). Such methods are limited in their flexibility due to unknown computational…

Clustering functional data is a challenging task due to intrinsic infinite-dimensionality and the need for stable, data-adaptive partitioning. In this work, we propose a clustering framework based on Random Projections, which simultaneously…

Convolutional neural networks (CNNs) have been widely used in efficient image super-resolution. However, for CNN-based methods, performance gains often require deeper networks and larger feature maps, which increase complexity and inference…

Pathology foundation models (FMs) have driven significant progress in computational pathology. However, these high-performing models can easily exceed a billion parameters and produce high-dimensional embeddings, thus limiting their…

Can pretrained models generalize to new datasets without any retraining? We deploy pretrained image models on datasets they were not trained for, and investigate whether their embeddings form meaningful clusters. Our suite of benchmarking…

Visual-Language Alignment (VLA) has gained a lot of attention since CLIP's groundbreaking work. Although CLIP performs well, the typical direct latent feature alignment lacks clarity in its representation and similarity scores. On the other…

Feature visualization has gained substantial popularity, particularly after the influential work by Olah et al. in 2017, which established it as a crucial tool for explainability. However, its widespread adoption has been limited due to a…

Multi-view clustering has attracted broad attention due to its capacity to utilize consistent and complementary information among views. Although tremendous progress has been made recently, most existing methods undergo high complexity,…

Unsupervised representation learning with contrastive learning achieved great success. This line of methods duplicate each training batch to construct contrastive pairs, making each training batch and its augmented version forwarded…

Machine learning has become a central research area, with increasing attention devoted to explainable clustering, also known as conceptual clustering, which is a knowledge-driven unsupervised learning paradigm that partitions data into…

Object Referring Analysis (ORA), commonly known as referring expression comprehension, requires the identification and localization of specific objects in an image based on natural descriptions. Unlike generic object detection, ORA requires…

Vision-language models (VLMs) have demonstrated remarkable zero-shot performance across various classification tasks. Nonetheless, their reliance on hand-crafted text prompts for each task hinders efficient adaptation to new tasks. While…

Large Vision-Language Models (LVLMs) typically encode an image into a fixed number of visual tokens (e.g., 576) and process these tokens with a language model. Despite their strong performance, LVLMs face challenges in adapting to varying…

Audio-Visual Speech Recognition (AVSR) leverages audio and visual modalities to improve robustness in noisy environments. Recent advances in Large Language Models (LLMs) show strong performance in speech recognition, including AVSR.…