Search Results for author:
Found 15 papers, 11 papers with code
Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control
We introduce Cosmos-Transfer, a conditional world generation model that can generate world simulations based on multiple spatial control inputs of various modalities such as segmentation, depth, and edge.
Faster Neighborhood Attention: Reducing the O(n^2) Cost of Self Attention at the Threadblock Level
Known for reducing the quadratic time complexity of self attention to a linear complexity, neighborhood attention can now enjoy a reduced and constant memory footprint, and record-breaking half precision runtime.
FarSight: A Physics-Driven Whole-Body Biometric System at Large Distance and Altitude
Whole-body biometric recognition is an important area of research due to its vast applications in law enforcement, border security, and surveillance.
StyleNAT: Giving Each Head a New Perspective
Image generation has been a long sought-after but challenging task, and performing the generation task in an efficient manner is similarly difficult.
Ranked #2 on
Image Generation
on FFHQ 256 x 256
OneFormer: One Transformer to Rule Universal Image Segmentation
However, such panoptic architectures do not truly unify image segmentation because they need to be trained individually on the semantic, instance, or panoptic segmentation to achieve the best performance.
Ranked #1 on
Instance Segmentation
on ADE20K val
Dilated Neighborhood Attention Transformer
These models typically employ localized attention mechanisms, such as the sliding-window Neighborhood Attention (NA) or Swin Transformer's Shifted Window Self Attention.
Ranked #7 on
Instance Segmentation
on Cityscapes val
AdaFocusV3: On Unified Spatial-temporal Dynamic Video Recognition
Recent research has revealed that reducing the temporal and spatial redundancy are both effective approaches towards efficient video recognition, e. g., allocating the majority of computation to a task-relevant subset of frames or the most valuable image regions of each frame.
Distilling Facial Knowledge With Teacher-Tasks: Semantic-Segmentation-Features For Pose-Invariant Face-Recognition
This paper demonstrates a novel approach to improve face-recognition pose-invariance using semantic-segmentation features.
DiSparse: Disentangled Sparsification for Multitask Model Compression
We analyzed the pruning masks generated with DiSparse and observed strikingly similar sparse network architecture identified by each task even before the training starts.
Neighborhood Attention Transformer
We present Neighborhood Attention (NA), the first efficient and scalable sliding-window attention mechanism for vision.
Ranked #126 on
Semantic Segmentation
on ADE20K
Adversarial Attacks on Speech Recognition Systems for Mission-Critical Applications: A Survey
Indeed, Adversarial Artificial Intelligence (AI) which refers to a set of techniques that attempt to fool machine learning models with deceptive data, is a growing threat in the AI and machine learning research community, in particular for machine-critical applications.
ConvMLP: Hierarchical Convolutional MLPs for Vision
MLP-based architectures, which consist of a sequence of consecutive multi-layer perceptron blocks, have recently been found to reach comparable results to convolutional and transformer-based methods.
Ranked #9 on
Image Classification
on Flowers-102
(using extra training data)
Escaping the Big Data Paradigm with Compact Transformers
Our models are flexible in terms of model size, and can have as little as 0. 28M parameters while achieving competitive results.
Ranked #1 on
Image Classification
on Flowers-102
(using extra training data)
Fine-Grained Image Classification
Superpixel Image Classification
Text Mining using Nonnegative Matrix Factorization and Latent Semantic Analysis
Together, these feature vectors create a new feature space much more suitable for clustering.
DISCERN: Diversity-based Selection of Centroids for k-Estimation and Rapid Non-stochastic Clustering
One of the applications of center-based clustering algorithms such as K-Means is partitioning data points into K clusters.
