Related papers: AsyInst: Asymmetric Affinity with DepthGrad and Co…
Anomaly detection is a fundamental problem in domains such as healthcare, manufacturing, and cybersecurity. This thesis proposes new unsupervised methods for anomaly detection in both structured and streaming data settings. In the first…
Deep learning approaches to the segmentation of magnetic resonance images have shown significant promise in automating the quantitative analysis of brain images. However, a continuing challenge has been its sensitivity to the variability of…
Deep learning techniques have achieved great success in remote sensing image change detection. Most of them are supervised techniques, which usually require large amounts of training data and are limited to a particular application.…
In recent years, deep face recognition methods have demonstrated impressive results on in-the-wild datasets. However, these methods have shown a significant decline in performance when applied to real-world low-resolution benchmarks like…
How to improve discriminative feature learning is central in classification. Existing works address this problem by explicitly increasing inter-class separability and intra-class similarity, whether by constructing positive and negative…
Multi-modal medical image segmentation plays an essential role in clinical diagnosis. It remains challenging as the input modalities are often not well-aligned spatially. Existing learning-based methods mainly consider sharing trainable…
In this paper we address the problem of unsupervised localization of objects in single images. Compared to previous state-of-the-art method our method is fully unsupervised in the sense that there is no prior instance level or category…
Current instance segmentation methods rely heavily on pixel-level annotated images. The huge cost to obtain such fully-annotated images restricts the dataset scale and limits the performance. In this paper, we formally address…
One of the key problems in computer vision is adaptation: models are too rigid to follow the variability of the inputs. The canonical computation that explains adaptation in sensory neuroscience is divisive normalization, and it has…
A class of optimization problems characterized by a weighted finite-sum objective function subject to box constraints is considered. We propose a novel stochastic optimization method, named AS-BOX (\text{A}ddi\-ti\-onal \text{S}ampling for…
This paper addresses weakly supervised amodal instance segmentation, where the goal is to segment both visible and occluded (amodal) object parts, while training provides only ground-truth visible (modal) segmentations. Following prior…
Interactive graph-based segmentation methods partition an image into foreground and background regions with the aid of user inputs. However, existing approaches often suffer from high computational costs, sensitivity to user interactions,…
We present a semi-supervised learning approach to the temporal action segmentation task. The goal of the task is to temporally detect and segment actions in long, untrimmed procedural videos, where only a small set of videos are densely…
Most digital camera pipelines use color constancy methods to reduce the influence of illumination and camera sensor on the colors of scene objects. The highest accuracy of color correction is obtained with learning-based color constancy…
We present a new instance segmentation approach tailored to biological images, where instances may correspond to individual cells, organisms or plant parts. Unlike instance segmentation for user photographs or road scenes, in biological…
A primary challenge in semi-supervised learning (SSL) for segmentation is the confirmation bias from noisy pseudo-labels, which destabilizes training and degrades performance. We propose Inconsistency Masks (IM), a framework that reframes…
Reliable detection of anomalies is crucial when deploying machine learning models in practice, but remains challenging due to the lack of labeled data. To tackle this challenge, contrastive learning approaches are becoming increasingly…
Probabilistic convolutional neural networks, which predict distributions of predictions instead of point estimates, led to recent advances in many areas of computer vision, from image reconstruction to semantic segmentation. Besides state…
Loss functions are error metrics that quantify the difference between a prediction and its corresponding ground truth. Fundamentally, they define a functional landscape for traversal by gradient descent. Although numerous loss functions…
The deployment of traditional deep learning models in high-risk security tasks in an unlabeled, data-non-exploitable video intelligence environment faces significant challenges. In this paper, we propose a lightweight anomaly detection…