Related papers: Unicom: Universal and Compact Representation Learn…

Aligning machine representations with human understanding is key to improving interpretability of machine learning (ML) models. When classifying a new image, humans often explain their decisions by decomposing the image into concepts and…

Training visual embeddings with labeled data supervision has been the de facto setup for representation learning in computer vision. Inspired by recent success of adopting masked image modeling (MIM) in self-supervised representation…

Recent progress in diffusion models significantly advances various image generation tasks. However, the current mainstream approach remains focused on building task-specific models, which have limited efficiency when supporting a wide range…

Since the publication of CLIP, the approach of using InfoNCE loss for contrastive pre-training has become widely popular for bridging two or more modalities. Despite its wide adoption, CLIP's original design choices of L2 normalization and…

Recently, large-scale Contrastive Language-Image Pre-training (CLIP) has attracted unprecedented attention for its impressive zero-shot recognition ability and excellent transferability to downstream tasks. However, CLIP is quite…

Image fusion aims to integrate complementary information from multiple source images to produce a more informative and visually consistent representation, benefiting both human perception and downstream vision tasks. Despite recent…

The usage of convolutional neural networks (CNNs) for unsupervised image segmentation was investigated in this study. In the proposed approach, label prediction and network parameter learning are alternately iterated to meet the following…

With the rapid development of generative models, detecting generated fake images to prevent their malicious use has become a critical issue recently. Existing methods frame this challenge as a naive binary image classification task.…

Medical image understanding plays a crucial role in enabling automated diagnosis and data-driven clinical decision support. However, its progress is impeded by two primary challenges: the limited availability of high-quality annotated…

Semi-supervised learning in medical image segmentation leverages unlabeled data to reduce annotation burdens through consistency learning. However, current methods struggle with class imbalance and high uncertainty from pathology…

Multi-label recognition is a fundamental, and yet is a challenging task in computer vision. Recently, deep learning models have achieved great progress towards learning discriminative features from input images. However, conventional…

The rapid advancement of generative models has significantly enhanced the quality of AI-generated images, raising concerns about misinformation and the erosion of public trust. Detecting AI-generated images has thus become a critical…

The recent growth of large foundation models that can easily generate pseudo-labels for huge quantity of unlabeled data makes unsupervised Zero-Shot Cross-Domain Image Retrieval (UZS-CDIR) less relevant. In this paper, we therefore turn our…

Medical image analysis using supervised deep learning methods remains problematic because of the reliance of deep learning methods on large amounts of labelled training data. Although medical imaging data repositories continue to expand…

We propose a novel framework for image clustering that incorporates joint representation learning and clustering. Our method consists of two heads that share the same backbone network - a "representation learning" head and a "clustering"…

Decoding visual representations from brain signals has attracted significant attention in both neuroscience and artificial intelligence. However, the degree to which brain signals truly encode visual information remains unclear. Current…

This paper proposes a novel generic one-class feature learning method based on intra-class splitting. In one-class classification, feature learning is challenging, because only samples of one class are available during training. Hence,…

Contrastive learning is among the most successful methods for visual representation learning, and its performance can be further improved by jointly performing clustering on the learned representations. However, existing methods for joint…

Large-scale pre-trained Vision-Language Models (VLMs), such as CLIP, establish the correlation between texts and images, achieving remarkable success on various downstream tasks with fine-tuning. In existing fine-tuning methods, the…

Few-shot learning often involves metric learning-based classifiers, which predict the image label by comparing the distance between the extracted feature vector and class representations. However, applying global pooling in the backend of…