Related papers: Diverse Cotraining Makes Strong Semi-Supervised Se…

In this work, we study to release the potential of massive heterogeneous weak computing power to collaboratively train large-scale models on dispersed datasets. In order to improve both efficiency and accuracy in resource-adaptive…

Semi-Supervised Learning (SSL) and Unsupervised Domain Adaptation (UDA) enhance the model performance by exploiting information from labeled and unlabeled data. The clustering assumption has proven advantageous for learning with limited…

Semi-supervised learning has made significant strides in the medical domain since it alleviates the heavy burden of collecting abundant pixel-wise annotated data for semantic segmentation tasks. Existing semi-supervised approaches enhance…

Self-training via pseudo labeling is a conventional, simple, and popular pipeline to leverage unlabeled data. In this work, we first construct a strong baseline of self-training (namely ST) for semi-supervised semantic segmentation via…

We report competitive results on object detection and instance segmentation on the COCO dataset using standard models trained from random initialization. The results are no worse than their ImageNet pre-training counterparts even when using…

Semantic segmentation provides pixel-level scene understanding essential for autonomous driving and fine-grained perception tasks. However, training segmentation models requires costly, labor-intensive annotations on real-world datasets.…

Deep neural networks are behind many of the recent successes in machine learning applications. However, these models can produce overconfident decisions while encountering out-of-distribution (OOD) examples or making a wrong prediction.…

Diffusion models are increasingly used as powerful conditional generators, yet real deployments often involve multiple target distributions arising from different tasks, e.g., diverse prompt domains in text-to-image generation, or multiple…

Co-training, which combines limited in-domain real-world data with abundant surrogate data such as simulation or cross-embodiment robot data, is widely used for training generative robot policies. Despite its empirical success, the…

Partially-supervised learning can be challenging for segmentation due to the lack of supervision for unlabeled structures, and the methods directly applying fully-supervised learning could lead to incompatibility, meaning ground truth is…

Unsupervised learning of visual similarities is of paramount importance to computer vision, particularly due to lacking training data for fine-grained similarities. Deep learning of similarities is often based on relationships between pairs…

Co-part segmentation is an important problem in computer vision for its rich applications. We propose an unsupervised learning approach for co-part segmentation from images. For the training stage, we leverage motion information embedded in…

In this paper, we address the detection of co-occurring salient objects (CoSOD) in an image group using frequency statistics in an unsupervised manner, which further enable us to develop a semi-supervised method. While previous works have…

Semi-supervised semantic segmentation requires the model to effectively propagate the label information from limited annotated images to unlabeled ones. A challenge for such a per-pixel prediction task is the large intra-class variation,…

This paper explores a multimodal co-training framework designed to enhance model generalization in situations where labeled data is limited and distribution shifts occur. We thoroughly examine the theoretical foundations of this framework,…

Cotraining with demonstration data generated both in simulation and on real hardware has emerged as a promising recipe for scaling imitation learning in robotics. This work seeks to elucidate basic principles of this sim-and-real cotraining…

To mimic human vision with the way of recognizing the diverse and open world, foundation vision models are much critical. While recent techniques of self-supervised learning show the promising potentiality of this mission, we argue that…

Pre-training and self-training are two approaches to semi-supervised learning. The comparison between pre-training and self-training has been explored. However, the previous works led to confusing findings: self-training outperforms…

Fully convolutional networks have shown outstanding performance in the salient object detection (SOD) field. The state-of-the-art (SOTA) methods have a tendency to become deeper and more complex, which easily homogenize their learned deep…

Reasoning from diverse observations is a fundamental capability for generalist robot policies to operate in a wide range of environments. Despite recent advancements, many large-scale robotic policies still remain sensitive to key sources…