相关论文: SegPrompt: Using Segmentation Map as a Better Prom…

This paper presents a new method for pre-training neural networks that can decrease the total training time for a neural network while maintaining the final performance, which motivates its use on deep neural networks. By partitioning the…

Autonomous vehicles and robots require a full scene understanding of the environment to interact with it. Such a perception typically incorporates pixel-wise knowledge of the depths and semantic labels for each image from a video sensor.…

Multimodal perception systems for robotics and embodied AI often assume reliable RGB-D sensing, but in practice, depth is frequently missing, noisy, or corrupted. We thus present GeomPrompt, a lightweight cross-modal adaptation module that…

Neural networks pre-trained on a self-supervision scheme have become the standard when operating in data rich environments with scarce annotations. As such, fine-tuning a model to a downstream task in a parameter-efficient but effective…

Few-shot learning is a challenging problem since only a few examples are provided to recognize a new class. Several recent studies exploit additional semantic information, e.g. text embeddings of class names, to address the issue of rare…

A fundamental problem in supervised learning is to find a good set of features or distance measures. If the new set of features is of lower dimensionality and can be obtained by a simple transformation of the original data, they can make…

In recent years, deep neural networks have achieved high ac-curacy in the field of image recognition. By inspired from human learning method, we propose a semantic segmentation method using cooperative learning which shares the information…

The problem of autonomous indoor mapping is addressed. The goal is to minimize the time to achieve a predefined percentage of exposure with some desired level of certainty. The use of a pre-trained generative deep neural network, acting as…

Pseudo depth maps are depth map predicitions which are used as ground truth during training. In this paper we leverage pseudo depth maps in order to segment objects of classes that have never been seen during training. This renders our…

Deep kernel map networks have shown excellent performances in various classification problems including image annotation. Their general recipe consists in aggregating several layers of singular value decompositions (SVDs) -- that map data…

Multivariate time series data, collected across various fields such as manufacturing and wearable technology, exhibit states at multiple levels of granularity, from coarse-grained system behaviors to fine-grained, detailed events.…

Automated segmentation of cancer on medical images can aid targeted diagnostic and therapeutic procedures. However, its adoption is limited by the high cost of expert annotations required for training and inter-observer variability in…

Automated medical image segmentation is becoming increasingly crucial to modern clinical practice, driven by the growing demand for precise diagnosis, the push towards personalized treatment plans, and the advancements in machine learning…

Promptable foundation models, particularly Segment Anything Model (SAM), have emerged as a promising alternative to the traditional task-specific supervised learning for image segmentation. However, many evaluation studies have found that…

Large-scale supervised classification algorithms, especially those based on deep convolutional neural networks (DCNNs), require vast amounts of training data to achieve state-of-the-art performance. Decreasing this data requirement would…

Automated surface-anomaly detection using machine learning has become an interesting and promising area of research, with a very high and direct impact on the application domain of visual inspection. Deep-learning methods have become the…

Recent co-part segmentation methods mostly operate in a supervised learning setting, which requires a large amount of annotated data for training. To overcome this limitation, we propose a self-supervised deep learning method for co-part…

Multi-scale deep CNNs have been used successfully for problems mapping each pixel to a label, such as depth estimation and semantic segmentation. It has also been shown that such architectures are reusable and can be used for multiple…

Deep learning has successfully been leveraged for medical image segmentation. It employs convolutional neural networks (CNN) to learn distinctive image features from a defined pixel-wise objective function. However, this approach can lead…

The proliferation of extensive neural network architectures, particularly deep learning models, presents a challenge in terms of resource-intensive training. GPU memory constraints have become a notable bottleneck in training such sizable…