Related papers: CoDTS: Enhancing Sparsely Supervised Collaborative…
Given multiple datasets with different label spaces, the goal of this work is to train a single object detector predicting over the union of all the label spaces. The practical benefits of such an object detector are obvious and significant…
Partial multi-label learning and complementary multi-label learning are two popular weakly supervised multi-label classification paradigms that aim to alleviate the high annotation costs of collecting precisely annotated multi-label data.…
Weakly-Supervised Semantic Segmentation (WSSS) aims to train segmentation models by weak labels, which is receiving significant attention due to its low annotation cost. Existing approaches focus on generating pseudo labels for supervision…
Semi-supervised learning has emerged as a widely adopted technique in the field of medical image segmentation. The existing works either focuses on the construction of consistency constraints or the generation of pseudo labels to provide…
Active learning approaches in computer vision generally involve querying strong labels for data. However, previous works have shown that weak supervision can be effective in training models for vision tasks while greatly reducing annotation…
We present a novel confidence refinement scheme that enhances pseudo labels in semi-supervised semantic segmentation. Unlike existing methods, which filter pixels with low-confidence predictions in isolation, our approach leverages the…
Large-scale single-stream pre-training has shown dramatic performance in image-text retrieval. Regrettably, it faces low inference efficiency due to heavy attention layers. Recently, two-stream methods like CLIP and ALIGN with high…
In this work we address multi-target domain adaptation (MTDA) in semantic segmentation, which consists in adapting a single model from an annotated source dataset to multiple unannotated target datasets that differ in their underlying data…
Annotated images are required for both supervised model training and evaluation in image classification. Manually annotating images is arduous and expensive, especially for multi-labeled images. A recent trend for conducting such laboursome…
Weakly Supervised Semantic Segmentation (WSSS), which relies only on image-level labels, has attracted significant attention for its cost-effectiveness and scalability. Existing methods mainly enhance inter-class distinctions and employ…
Semi-supervised text classification (SSTC) has gained increasing attention due to its ability to leverage unlabeled data. However, existing approaches based on pseudo-labeling suffer from the issues of pseudo-label bias and error…
In fine-grained road scene understanding, semantic segmentation plays a crucial role in enabling vehicles to perceive and comprehend their surroundings. By assigning a specific class label to each pixel in an image, it allows for precise…
The pioneering method for unsupervised meta-learning, CACTUs, is a clustering-based approach with pseudo-labeling. This approach is model-agnostic and can be combined with supervised algorithms to learn from unlabeled data. However, it…
This manuscript presents a series of my selected contributions to the topic of label-efficient learning in computer vision and remote sensing. The central focus of this research is to develop and adapt methods that can learn effectively…
Offline model-based optimization aims to find a design that maximizes a property of interest using only an offline dataset, with applications in robot, protein, and molecule design, among others. A prevalent approach is gradient ascent,…
Effective weed control plays a crucial role in optimizing crop yield and enhancing agricultural product quality. However, the reliance on herbicide application not only poses a critical threat to the environment but also promotes the…
When labeled data is insufficient, semi-supervised learning with the pseudo-labeling technique can significantly improve the performance of automatic speech recognition. However, pseudo-labels are often noisy, containing numerous incorrect…
Scribble-based weakly-supervised semantic segmentation using sparse scribble supervision is gaining traction as it reduces annotation costs when compared to fully annotated alternatives. Existing methods primarily generate pseudo-labels by…
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…
Weakly supervised object detection has recently received much attention, since it only requires image-level labels instead of the bounding-box labels consumed in strongly supervised learning. Nevertheless, the save in labeling expense is…