Predicts food ingredient amounts from images.
problem Predicting relative amounts of ingredients from food images.
method Proposes two deep learning models for sparse and dense predictions, with semi-automatic data pre-processing.
result Encouraging experimental results on a recipe dataset.
New meta-learning method outperforms human-designed architectures in dense image prediction tasks.
problem Designing efficient neural network architectures for dense image prediction.
method Recursive search space construction for multi-scale visual information.
result Meta-learning method achieves state-of-the-art performance on scene parsing, person-part segmentation, and semantic image segmentation.
New method speeds up image denoising models without sacrificing performance.
problem Efficiently training models for image denoising tasks.
method Introduces superkernel techniques for fast training of dense prediction models.
result Demonstrates effectiveness on SIDD+ benchmark with 6-8 RTX2080 GPU hours.
The key idea of current deep learning methods for dense prediction is to apply a model on a regular patch centered on each pixel to make pixel-wise predictions. These methods are limited in the sense that the patches are determined by network architecture instead of learned from data. In this work, we propose the dense…
ARMA nets expand receptive fields for dense prediction tasks.
problem Global information in dense prediction problems is challenging for traditional convolutional layers.
method ARMA layers with adjustable autoregressive coefficients replace traditional convolutions.
result ARMA networks improve dense prediction tasks including video prediction and semantic segmentation.
Deep learning animates objects from input images and videos.
problem Animating arbitrary objects from input images and videos.
method A deep learning framework with three modules: Keypoint Detector, Dense Motion prediction network, and Motion Transfer Network.
result Our method outperforms state-of-the-art image animation and video generation methods.
Enhanced image denoising with MWRDCNN using residual dense blocks.
problem Image denoising with improved performance and robustness.
method Multi-wavelet residual dense convolutional neural network (MWRDCNN) with residual dense blocks (RDBs).
result Significantly improved performance in image denoising compared to existing techniques.
Generic Hitchin representations generate dense subgroups.
problem Understanding dense subgroups in SL_n(R) representations.
method Using a theorem by Rapinchuk, Benyash-Krivetz, and Chernousov.
result Generic Hitchin representations are strongly dense.
Deep learning improves automatic image segmentation.
problem Automatic object localization and boundary delineation in images and medical scans.
method Proposed and evaluated novel dilated dense encoder-decoder architectures for salient object segmentation and lesion localization in medical images.
result Proposed architectures outperform state-of-the-art models in accuracy and efficiency.
Predicting human fixations from images has recently seen large improvements by leveraging deep representations which were pretrained for object recognition. However, as we show in this paper, these networks are highly overparameterized for the task of fixation prediction. We first present a simple yet principled greedy…
A new deep learning method for tissue-cleared image registration.
problem Efficient registration of high-resolution tissue-cleared images.
method Densely connected convolutional architecture for deformable image registration, unsupervised training.
result Comparable and superior registration performance to state-of-the-art methods, especially at higher resolutions.
One of the key challenges of visual perception is to extract abstract models of 3D objects and object categories from visual measurements, which are affected by complex nuisance factors such as viewpoint, occlusion, motion, and deformations. Starting from the recent idea of viewpoint factorization, we propose a new app…
New representations of hyperbolic 3-manifold groups into larger groups.
problem Finding representations of hyperbolic 3-manifold groups into larger matrix groups.
method Holonomy representations from projective deformations of hyperbolic structures.
result First examples of strongly dense representations into SL(4,R) and SU(3,1). From human crowds to cells in tissue, the detection and efficient tracking of multiple objects in dense configurations is an important and unsolved problem. In the past, limitations of image analysis have restricted studies of dense groups to tracking a single or subset of marked individuals, or to coarse-grained group…
Deep learning predicts human survival from cardiac MRI motion data.
problem Predicting human survival from cardiac MRI motion data.
method Fully convolutional network for dense motion modeling, autoencoder for latent code learning, Cox partial likelihood loss for right-censored data.
result Predictive accuracy (C-index) significantly higher (p < .0001) for deep learning model (C=0.73) than human benchmark (C=0.59).
Generic metrics make geodesic nets dense.
problem Density of geodesic nets under generic metrics.
method Proving density for Baire-generic metrics.
result Union of geodesic nets images is dense.
End-to-end image super-resolution using Attention-based DenseNet with residual deconvolution.
problem Challenging task of improving low-resolution images.
method Proposes a novel ADRD model with weighted dense blocks and spatial attention modules.
result Demonstrates promising performance on publicly available datasets.
In this paper we construct a complete injective holomorphic immersion C→C2 whose image is dense in C2. The analogous result is obtained for any closed complex submanifold X⊂Cn for n>1 in place of C⊂C2. We also show that, if X intersect…
ViCE uses superpixels to enhance self-supervised learning for better dense visual embeddings.
problem Lack of high-resolution feature maps from self-supervised models.
method Superpixels for dense representation learning, contrasting over regions.
result Improves unsupervised semantic segmentation on benchmarks like Cityscapes and COCO.
Method matches noisy remote sensing images robustly.
problem Matching noisy remote sensing images.
method Combining attention mechanism with feature enhancement.
result More efficient and accurate matches achieved.
Sparse Vision MoE matches dense networks in image recognition while using less compute.
problem Scaling vision models efficiently in computer vision.
method Vision MoE (V-MoE) - a sparse version of Vision Transformer.
result V-MoE matches state-of-the-art dense networks in image recognition with half the compute.
OLALA automates document layout annotation by selecting ambiguous regions for labeling.
problem Efficiently annotating complex document layouts with limited resources.
method Object-Level Active Learning framework that selects ambiguous regions for labeling and uses semi-automatic correction.
result OLALA significantly boosts model performance and improves annotation efficiency.
Using a Bayesian approach, we consider the problem of recovering sparse signals under additive sparse and dense noise. Typically, sparse noise models outliers, impulse bursts or data loss. To handle sparse noise, existing methods simultaneously estimate the sparse signal of interest and the sparse noise of no interest.…
The paper finds dense subgroups in certain Lie groups.
problem Finding dense subgroups in Lie groups.
method Constructing dense surface subgroups in specific Lie groups.
result Uniform lattices contain infinitely many dense Hitchin representations.
Maximal representations in symplectic lattices proven for most cases.
problem Understanding maximal representations in symplectic lattices.
method Analyzing mapping class group orbits and continuous deformations of maximal diagonal representations.
result Proof of maximal representations in most lattices of Sp(2n,R).
A new method uses Gaussian Processes for feature-based nonrigid image registration.
problem Estimating dense displacement fields for nonrigid image registration.
method Using Gaussian Processes to estimate both dense displacement field and uncertainty map.
result GP-based interpolation performs similarly to state-of-the-art B-spline interpolation.
Deep learning improves MRI image quality from down-sampled data.
problem Improving MRI image quality from accelerated, down-sampled k-space data.
method Deep Residual Dense U-Net architecture with Residual Dense Block and new loss function.
result The proposed method achieves better performance in reconstructing high-quality images from down-sampled k-space data.
Compact Gaussian model approximates deep ensemble predictions.
problem Efficiently approximating deep ensemble models for image prediction.
method Sparse-structured multivariate Gaussian with Cholesky parameterization trained to match pre-trained ensemble outputs.
result Compact representation captures uncertainty and structured correlations explicitly.
The paper explores mapping class group quotients by Dehn twists and their representations.
problem Finite quotients and representations of mapping class groups by powers of Dehn twists.
method Construction of finite quotients using representations with Zariski dense images into semisimple Lie groups, and Long and Moody's method.
result The Fibonacci TQFT representation is a specialization of the Jones representation in genus 2.
LangDA improves domain adaptation for semantic segmentation by learning context-aware scene descriptions.
problem Improving domain adaptation for semantic segmentation with dense prediction tasks.
method LangDA learns contextual relationships between objects via VLM-generated scene descriptions and aligns image features with text representation.
result LangDA sets new state-of-the-art across three DASS benchmarks, outperforming existing methods.
A deep model learns to infer fluorescence labels from unlabeled microscopy images.
problem Challenges in obtaining high quality images of cellular structures due to complex environments and label staining limitations.
method Developed a novel deep model using global pixel transformer layers and dense blocks, incorporating multi-scale input strategy.
result Significantly outperforms state-of-the-art methods in fluorescence image prediction tasks.
Neural network accuracy improves with denser training samples.
problem Improving neural network accuracy on unseen test samples.
method Bounding empirical training error smoothed across activation regions and using it to discard high-risk test samples.
result Discarding high-risk test samples based on error bounds improves prediction accuracy by up to 20%.
Paper proposes dense average network for improved power load forecasting.
problem Improving power load forecasting accuracy to save millions for the power industry.
method Introduces dense average connection and constructs dense average network for power load forecasting.
result Proposed model outperforms existing methods on public datasets.
A geometric account explains why 'The Dress' is ambiguous, predicting observable signatures in image processing.
problem Understanding and predicting ambiguity in image processing, particularly in intrinsic image decomposition.
method Geometric analysis of intrinsic image decomposition, focusing on the discontinuous switch in prior-mode sections.
result Predicted signatures in albedo Jacobian and Fernet curvature can be observed in various models and datasets.
ECN framework improves training on noisy structured labels.
problem Structured errors in fine-grained annotations lead to biased models.
method Error-Correcting Networks (ECN) framework.
result ECN improves fine-grained annotation prediction.
New solver MPLP++ outperforms existing solvers for dense graph models.
problem Efficiently solving dense, discrete Graphical Models with pairwise potentials.
method Dual Block-Coordinate Ascent with MPLP++ modification.
result MPLP++ significantly outperforms existing solvers, including TRWS.
DVNet efficiently segments large neurovascular datasets using skip connections.
problem Challenges in segmenting large neurovascular datasets from high-throughput microscopy data.
method A fully-convolutional, deep, and densely-connected encoder-decoder network with skip connections.
result DVNet achieves superior performance in semantic segmentation of neurovascular datasets.
This note introduces and studies an open set of PSL(2,C) characters of a nonabelian free group, on which the action of the outer automorphism group is properly discontinuous, and which is strictly larger than the set of discrete, faithful convex-cocompact (i.e. Schottky) characters. This implies, in particular, that th…
Method infers depth from sparse points and camera motion.
problem Depth inference from limited sparse data.
method Constructs a planar scaffolding and uses predictive cross-modal criterion.
result State-of-the-art performance on depth completion benchmark.
Deep convolutional neural networks have become a key element in the recent breakthrough of salient object detection. However, existing CNN-based methods are based on either patch-wise (region-wise) training and inference or fully convolutional networks. Methods in the former category are generally time-consuming due to…
Framework improves CT image segmentation robustness with domain-specific cues.
problem Challenges in CT image segmentation by deep learning models.
method Combines domain-specific preprocessing and augmentation with CNN architectures.
result Framework stabilizes prediction performance on varying CT volumes.
Complex projective manifolds without rational curves are quotients of Abelian varieties.
problem Characterizing complex projective manifolds without rational curves.
method Using conjectures about rational and entire curves on Calabi-Yau varieties.
result Non-hyperbolic complex projective manifolds contain the image of an Abelian variety.
We define submersions f between manifolds M and N modelled on locally convex spaces. If the range N is finite-dimensional or a Banach manifold, then these coincide with the naive notion of a submersion. We study pre-images of submanifolds under submersions and pre-images under mappings whose differentials have dense im…
Safe control for vehicles using learned perception from images.
problem Controlling autonomous vehicles with partial state information from images.
method Learned perception map and safe set design for a closed loop system.
result Generalization properties of the perception-control loop are favorable.
We present a method for training multi-label, massively multi-class image classification models, that is faster and more accurate than supervision via a sigmoid cross-entropy loss (logistic regression). Our method consists in embedding high-dimensional sparse labels onto a lower-dimensional dense sphere of unit-normed …
We show that for an odd prime r > 3 and an integer g > 1, in the projective representation given by the SO(3) Witten-Chern-Simons theory at an rth root of unity, the image of the mapping class group of a surface of genus g is dense.
We solve 6-DoF localisation and 3D reconstruction using deep state-space models.
problem 6-DoF localisation and dense 3D reconstruction in spatial environments.
method Approximate Bayesian inference in a deep state-space model combining learning and domain knowledge.
result Near state-of-the-art performance on UAV flight data.
Extends DAMs to Gaussian distributions for efficient pattern storage and retrieval.
problem Limited storage capacity and retrieval methods for non-vector pattern representations.
method Introduces a log-sum-exp energy function over Gaussian distributions, using optimal transport maps for retrieval dynamics.
result Proves exponential storage capacity and provides quantitative retrieval guarantees.