Related papers: ImagebindDC: Compressing Multi-modal Data with Ima…

Dataset condensation (DC) enables the creation of compact, privacy-preserving synthetic datasets that can match the utility of real patient records, supporting democratised access to highly regulated clinical data for developing downstream…

Classification using multimodal data arises in many machine learning applications. It is crucial not only to model cross-modal relationship effectively but also to ensure robustness against loss of part of data or modalities. In this paper,…

Modern convolutional neural networks (CNNs)-based face detectors have achieved tremendous strides due to large annotated datasets. However, misaligned results with high detection confidence but low localization accuracy restrict the further…

Unsupervised disentangled representation learning is a long-standing problem in computer vision. This work proposes a novel framework for performing image clustering from deep embeddings by combining instance-level contrastive learning with…

Upon deployment to edge devices, it is often desirable for a model to further learn from streaming data to improve accuracy. However, extracting representative features from such data is challenging because it is typically unlabeled,…

In this paper, we propose a novel, effective and simpler end-to-end image clustering auto-encoder algorithm: ICAE. The algorithm uses PEDCC (Predefined Evenly-Distributed Class Centroids) as the clustering centers, which ensures the…

Previous industrial anomaly detection methods often struggle to handle the extensive diversity in training sets, particularly when they contain stylistically diverse and feature-rich samples, which we categorize as feature-rich anomaly…

Structured pruning and quantization are promising approaches for reducing the inference time and memory footprint of neural networks. However, most existing methods require the original training dataset to fine-tune the model. This not only…

Multimodal learning often outperforms its unimodal counterparts by exploiting unimodal contributions and cross-modal interactions. However, focusing only on integrating multimodal features into a unified comprehensive representation…

Recently, unsupervised image-to-image translation methods based on contrastive learning have achieved state-of-the-art results in many tasks. However, in the previous works, the negatives are sampled from the input image itself, which…

Scene understanding using multi-modal data is necessary in many applications, e.g., autonomous navigation. To achieve this in a variety of situations, existing models must be able to adapt to shifting data distributions without arduous data…

Multimodal contrastive learning is a methodology for linking different data modalities; the canonical example is linking image and text data. The methodology is typically framed as the identification of a set of encoders, one for each…

Multi-view clustering has attracted much attention thanks to the capacity of multi-source information integration. Although numerous advanced methods have been proposed in past decades, most of them generally overlook the significance of…

Image translation is one of the crucial approaches for mitigating information deficiencies in the infrared and visible modalities, while also facilitating the enhancement of modality-specific datasets. However, existing methods for infrared…

Modern deep models are trained on large real-world datasets, where data quality varies and redundancy is common. Data-centric approaches such as dataset pruning have shown promise in improving training efficiency and model performance.…

Diffusion probabilistic models (DPMs) have become a popular approach to conditional generation, due to their promising results and support for cross-modal synthesis. A key desideratum in conditional synthesis is to achieve high…

We introduce a multi-modal diffusion model tailored for the bi-directional conditional generation of video and audio. We propose a joint contrastive training loss to improve the synchronization between visual and auditory occurrences. We…

Generative models are increasingly used to augment medical imaging datasets for fairer AI. Yet a key assumption often goes unexamined: that generators themselves produce equally high-quality images across demographic groups. Models trained…

Federated Learning (FL) is a method for training machine learning models using distributed data sources. It ensures privacy by allowing clients to collaboratively learn a shared global model while storing their data locally. However, a…

The use of high-dimensional features has become a normal practice in many computer vision applications. The large dimension of these features is a limiting factor upon the number of data points which may be effectively stored and processed,…