Related papers: Uncertainty Estimation via Response Scaling for Ps…
Registration networks have shown great application potentials in medical image analysis. However, supervised training methods have a great demand for large and high-quality labeled datasets, which is time-consuming and sometimes impractical…
Weakly supervised instance segmentation with image-level labels, instead of expensive pixel-level masks, remains unexplored. In this paper, we tackle this challenging problem by exploiting class peak responses to enable a classification…
We propose a weakly-supervised framework for the semantic segmentation of circular-scan synthetic-aperture-sonar (CSAS) imagery. The first part of our framework is trained in a supervised manner, on image-level labels, to uncover a set of…
This paper focuses on webly supervised learning (WSL), where datasets are built by crawling samples from the Internet and directly using search queries as web labels. Although WSL benefits from fast and low-cost data collection, noises in…
Image-level weakly supervised semantic segmentation (WSSS) relies on class activation maps (CAMs) for pseudo labels generation. As CAMs only highlight the most discriminative regions of objects, the generated pseudo labels are usually…
Wireless signal recognition (WSR) is crucial in modern and future wireless communication networks since it aims to identify properties of the received signal. Although many deep learning-based WSR models have been developed, they still rely…
Weakly-supervised semantic segmentation is a challenging task as no pixel-wise label information is provided for training. Recent methods have exploited classification networks to localize objects by selecting regions with strong response.…
Audio-Visual Semantic Segmentation (AVSS) aligns audio and video at the pixel level but requires costly per-frame annotations. We introduce Weakly Supervised Audio-Visual Semantic Segmentation (WSAVSS), which uses only video-level labels to…
Deep neural networks are known to be data-driven and label noise can have a marked impact on model performance. Recent studies have shown great robustness to classic image recognition even under a high noisy rate. In medical applications,…
Recent efforts in deploying Deep Neural Networks for object detection in real world applications, such as autonomous driving, assume that all relevant object classes have been observed during training. Quantifying the performance of these…
Accurate segmentation of organelle instances from electron microscopy (EM) images plays an essential role in many neuroscience researches. However, practical scenarios usually suffer from high annotation costs, label scarcity, and large…
Deepfake audio detection has progressed rapidly with strong pre-trained encoders (e.g., WavLM, Wav2Vec2, MMS). However, performance in realistic capture conditions - background noise (domestic/office/transport), room reverberation, and…
To obtain an accurate cosmological inference from upcoming weak lensing surveys such as the one conducted by Euclid, the shear measurement requires calibration using galaxy image simulations. We study the efficiency of different noise…
Automated nodule segmentation is essential for computer-assisted diagnosis in ultrasound images. Nevertheless, most existing methods depend on precise pixel-level annotations by medical professionals, a process that is both costly and…
Current Semi-supervised Learning (SSL) adopts the pseudo-labeling strategy and further filters pseudo-labels based on confidence thresholds. However, this mechanism has notable drawbacks: 1) setting the reasonable threshold is an open…
Generating reliable pseudo masks from image-level labels is challenging in the weakly supervised semantic segmentation (WSSS) task due to the lack of spatial information. Prevalent class activation map (CAM)-based solutions are challenged…
Compared to supervised deep learning, self-supervision provides remote sensing a tool to reduce the amount of exact, human-crafted geospatial annotations. While image-level information for unsupervised pretraining efficiently works for…
Although existing semantic segmentation approaches achieve impressive results, they still struggle to update their models incrementally as new categories are uncovered. Furthermore, pixel-by-pixel annotations are expensive and…
Nodule segmentation from breast ultrasound images is challenging yet essential for the diagnosis. Weakly-supervised segmentation (WSS) can help reduce time-consuming and cumbersome manual annotation. Unlike existing weakly-supervised…
Pseudo-measurements are the dominant source of uncertainty in distribution system state estimation (DSSE), yet their distributional assumptions are treated as fixed inputs by existing uncertainty quantification methods. This paper…