Related papers: Prototype-Guided Pseudo-Labeling with Neighborhood…

Source-Free Domain Adaptation (SFDA) tackles the problem of adapting a pre-trained source model to an unlabeled target domain without accessing any source data, which is quite suitable for the field of data security. Although recent…

Pre-trained vision-language models (VLMs), exemplified by CLIP, demonstrate remarkable adaptability across zero-shot classification tasks without additional training. However, their performance diminishes in the presence of domain shifts.…

Recent advancements in pre-trained vision-language models like CLIP have enabled the task of open-vocabulary segmentation. CLIP demonstrates impressive zero-shot capabilities in various downstream tasks that require holistic image…

3D object detection is essential for autonomous driving and robotic perception, yet its reliance on large-scale manually annotated data limits scalability and adaptability. To reduce annotation dependency, unsupervised and…

State-of-the-art techniques in weakly-supervised semantic segmentation (WSSS) using image-level labels exhibit severe performance degradation on driving scene datasets such as Cityscapes. To address this challenge, we develop a new WSSS…

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…

Multimodal fusion breaks through the boundaries between diverse modalities and has already achieved notable performances. However, in many specialized fields, it is struggling to obtain sufficient alignment data for training, which…

Recently, contrastive learning has largely advanced the progress of unsupervised visual representation learning. Pre-trained on ImageNet, some self-supervised algorithms reported higher transfer learning performance compared to…

Domain adaptation of visual detectors is a critical challenge, yet existing methods have overlooked pixel appearance transformations, focusing instead on bootstrapping and/or domain confusion losses. We propose a Semantic Pixel-Level…

Semi-supervised multi-label learning (SSMLL) aims to address the challenge of limited labeled data in multi-label learning (MLL) by leveraging unlabeled data to improve the model's performance. While pseudo-labeling has become a dominant…

Recent advances in Source-Free Unsupervised Video Domain Adaptation (SFUVDA) leverage vision-language models to enhance pseudo-label generation. However, challenges such as noisy pseudo-labels and over-confident predictions limit their…

Recent breakthroughs in semi-supervised semantic segmentation have been developed through contrastive learning. In prevalent pixel-wise contrastive learning solutions, the model maps pixels to deterministic representations and regularizes…

Consistency regularization on label predictions becomes a fundamental technique in semi-supervised learning, but it still requires a large number of training iterations for high performance. In this study, we analyze that the consistency…

Contrastive Vision-Language Pre-training, known as CLIP, has provided a new paradigm for learning visual representations by using large-scale contrastive image-text pairs. It shows impressive performance on zero-shot knowledge transfer to…

The emergence of large pre-trained vision-language models (VLMs) represents a paradigm shift in machine learning, with unprecedented results in a broad span of visual recognition tasks. CLIP, one of the most popular VLMs, has exhibited…

The unsupervised 3D object detection is to accurately detect objects in unstructured environments with no explicit supervisory signals. This task, given sparse LiDAR point clouds, often results in compromised performance for detecting…

Zero-shot anomaly detection (ZSAD) aims to detect anomalies without any target domain training samples, relying solely on external auxiliary data. Existing CLIP-based methods attempt to activate the model's ZSAD potential via handcrafted or…

This work presents a tuning-free semantic segmentation framework based on classifying SAM masks by CLIP, which is universally applicable to various types of supervision. Initially, we utilize CLIP's zero-shot classification ability to…

Person re-identification (re-ID) is of great importance to video surveillance systems by estimating the similarity between a pair of cross-camera person shorts. Current methods for estimating such similarity require a large number of…

The high capacity of deep learning models to learn complex patterns poses a significant challenge when confronted with label noise. The inability to differentiate clean and noisy labels ultimately results in poor generalization. We approach…