Related papers: deep PACO: Combining statistical models with deep …
Large sky surveys are increasingly relying on image subtraction pipelines for real-time (and archival) transient detection. In this process one has to contend with varying PSF, small brightness variations in many sources, as well as…
Contrastive pretraining can substantially increase model generalisation and downstream performance. However, the quality of the learned representations is highly dependent on the data augmentation strategy applied to generate positive…
Many real-world applications involve data from multiple modalities and thus exhibit the view heterogeneity. For example, user modeling on social media might leverage both the topology of the underlying social network and the content of the…
Self-supervised representation learning based on Contrastive Learning (CL) has been the subject of much attention in recent years. This is due to the excellent results obtained on a variety of subsequent tasks (in particular…
Stereo estimation has made many advancements in recent years with the introduction of deep-learning. However the traditional supervised approach to deep-learning requires the creation of accurate and plentiful ground-truth data, which is…
Instance contrast for unsupervised representation learning has achieved great success in recent years. In this work, we explore the idea of instance contrastive learning in unsupervised domain adaptation (UDA) and propose a novel Category…
Photon-counting CT (PCCT) offers improved diagnostic performance through better spatial and energy resolution, but developing high-quality image reconstruction methods that can deal with these large datasets is challenging. Model-based…
We report on the methods used in our recent DeepEnsembleCoco submission to the PASCAL VOC 2012 challenge, which achieves state-of-the-art performance on the object detection task. Our method is a variant of the R-CNN model proposed…
Current and future high contrast imaging instruments aim to detect exoplanets at closer orbital separations, lower masses, and/or older ages than their predecessors. However, continually evolving speckles in the coronagraphic science image…
Substellar companions such as exoplanets and brown dwarfs exhibit changes in brightness arising from top-of-atmosphere inhomogeneities, providing insights into their atmospheric structure and dynamics. This variability can be measured in…
We present a new self-supervised paradigm on point cloud sequence understanding. Inspired by the discriminative and generative self-supervised methods, we design two tasks, namely point cloud sequence based Contrastive Prediction and…
The search for exoplanets is pushing adaptive optics systems on ground-based telescopes to their limits. One of the major limitations at small angular separations, exactly where exoplanets are predicted to be, is the servo-lag of the…
Homography estimation between multiple aerial images can provide relative pose estimation for collaborative autonomous exploration and monitoring. The usage on a robotic system requires a fast and robust homography estimation algorithm. In…
Recent advancements in diffusion models have enabled the generation of realistic deepfakes from textual prompts in natural language. While these models have numerous benefits across various sectors, they have also raised concerns about the…
Deep-predictive-coding networks (DPCNs) are hierarchical, generative models. They rely on feed-forward and feed-back connections to modulate latent feature representations of stimuli in a dynamic and context-sensitive manner. A crucial…
Recent progress in contrastive learning has revolutionized unsupervised representation learning. Concretely, multiple views (augmentations) from the same image are encouraged to map to the similar embeddings, while views from different…
Many signal processing algorithms break the target signal into overlapping segments (also called windows, or patches), process them separately, and then stitch them back into place to produce a unified output. At the overlaps, the final…
This work develops a novel end-to-end deep unsupervised learning method based on convolutional neural network (CNN) with pseudo-classes for remote sensing scene representation. First, we introduce center points as the centers of the pseudo…
For modern large-scale structure survey techniques it has become standard practice to test data analysis pipelines on large suites of mock simulations, a task which is currently prohibitively expensive for full N-body simulations. Instead…
The challenges of high contrast imaging (HCI) for detecting exoplanets for both ground and space applications can be met with extreme adaptive optics (ExAO), a high-order adaptive optics system that performs wavefront sensing (WFS) and…