Related papers: Class-Agnostic Segmentation Loss and Its Applicati…
Inspection of insulators is important to ensure reliable operation of the power system. Deep learning is being increasingly exploited to automate the inspection process by leveraging object detection models to analyse aerial images captured…
Salient Object Detection (SOD) plays a crucial role in many computer vision applications, requiring accurate localization and precise boundary delineation of salient regions. In this work, we present a novel framework that integrates…
Deep-learning has proved in recent years to be a powerful tool for image analysis and is now widely used to segment both 2D and 3D medical images. Deep-learning segmentation frameworks rely not only on the choice of network architecture but…
We introduce CASED, a novel curriculum sampling algorithm that facilitates the optimization of deep learning segmentation or detection models on data sets with extreme class imbalance. We evaluate the CASED learning framework on the task of…
Recent advances in deep learning have pushed the performances of visual saliency models way further than it has ever been. Numerous models in the literature present new ways to design neural networks, to arrange gaze pattern data, or to…
Compared with laborious pixel-wise dense labeling, it is much easier to label data by scribbles, which only costs 1$\sim$2 seconds to label one image. However, using scribble labels to learn salient object detection has not been explored.…
The backbone of traditional CNN classifier is generally considered as a feature extractor, followed by a linear layer which performs the classification. We propose a novel loss function, termed as CAM-loss, to constrain the embedded feature…
Boundary and edge cues are highly beneficial in improving a wide variety of vision tasks such as semantic segmentation, object recognition, stereo, and object proposal generation. Recently, the problem of edge detection has been revisited…
High annotation costs are a major bottleneck for the training of semantic segmentation systems. Therefore, methods working with less annotation effort are of special interest. This paper studies the problem of semi-supervised semantic…
Recent advances in supervised salient object detection has resulted in significant performance on benchmark datasets. Training such models, however, requires expensive pixel-wise annotations of salient objects. Moreover, many existing…
Salient object detection has seen remarkable progress driven by deep learning techniques. However, most of deep learning based salient object detection methods are black-box in nature and lacking in interpretability. This paper proposes the…
We propose Rank & Sort (RS) Loss, a ranking-based loss function to train deep object detection and instance segmentation methods (i.e. visual detectors). RS Loss supervises the classifier, a sub-network of these methods, to rank each…
Current 3D scene segmentation methods are heavily dependent on manually annotated 3D training datasets. Such manual annotations are labor-intensive, and often lack fine-grained details. Importantly, models trained on this data typically…
Object-centric learning aims to decompose an input image into a set of meaningful object files (slots). These latent object representations enable a variety of downstream tasks. Yet, object-centric learning struggles on real-world datasets,…
In class-agnostic object counting, the goal is to estimate the total number of object instances in an image without distinguishing between specific categories. Existing methods often predict this count without considering class-specific…
In this paper, we propose a fast deep learning method for object saliency detection using convolutional neural networks. In our approach, we use a gradient descent method to iteratively modify the input images based on the pixel-wise…
Salient object detection or salient region detection models, diverging from fixation prediction models, have traditionally been dealing with locating and segmenting the most salient object or region in a scene. While the notion of most…
We propose an algorithm for meta-learning that is model-agnostic, in the sense that it is compatible with any model trained with gradient descent and applicable to a variety of different learning problems, including classification,…
The segmentation of skin lesions is a crucial task in clinical decision support systems for the computer aided diagnosis of skin lesions. Although deep learning-based approaches have improved segmentation performance, these models are often…
Recent progress on saliency detection is substantial, benefiting mostly from the explosive development of Convolutional Neural Networks (CNNs). Semantic segmentation and saliency detection algorithms developed lately have been mostly based…