Search Results for author:
Found 22 papers, 6 papers with code
LRP-QViT: Mixed-Precision Vision Transformer Quantization via Layer-wise Relevance Propagation
To validate and assess our approach, we employ LRP-QViT across ViT, DeiT, and Swin transformer models on various datasets.
Unknown Sample Discovery for Source Free Open Set Domain Adaptation
Source-free OSDA (SF-OSDA) techniques eliminate the need to access source domain samples, but current SF-OSDA methods utilize only the known classes in the target domain for adaptation, and require access to the entire target domain even during inference after adaptation, to make the distinction between known and unknown samples.
Continual Domain Adaptation on Aerial Images under Gradually Degrading Weather
We synthesize two such gradually worsening weather conditions on real images from two existing aerial imagery datasets, generating a total of four benchmark datasets.
Curriculum Guided Domain Adaptation in the Dark
Addressing the rising concerns of privacy and security, domain adaptation in the dark aims to adapt a black-box source trained model to an unlabeled target domain without access to any source data or source model parameters.
DeepRM: Deep Recurrent Matching for 6D Pose Refinement
Optical flow prediction stabilizes the training process, and enforces the learning of features that are relevant to the task of pose estimation.
BAPose: Bottom-Up Pose Estimation with Disentangled Waterfall Representations
We propose BAPose, a novel bottom-up approach that achieves state-of-the-art results for multi-person pose estimation.
Ranked #5 on
Multi-Person Pose Estimation
on MS COCO
Extreme Face Inpainting with Sketch-Guided Conditional GAN
Recovering badly damaged face images is a useful yet challenging task, especially in extreme cases where the masked or damaged region is very large.
Grassmann Iterative Linear Discriminant Analysis with Proxy Matrix Optimization
Linear Discriminant Analysis (LDA) is commonly used for dimensionality reduction in pattern recognition and statistics.
SiamReID: Confuser Aware Siamese Tracker with Re-identification Feature
Siamese deep-network trackers have received significant attention in recent years due to their real-time speed and state-of-the-art performance.
Benchmarking Deep Trackers on Aerial Videos
In recent years, deep learning-based visual object trackers have achieved state-of-the-art performance on several visual object tracking benchmarks.
Automatic Quantification of Facial Asymmetry using Facial Landmarks
Motion is computed and compared between the left and the right parts of each region of interest to estimate the symmetry score.
Visualization of Deep Transfer Learning In SAR Imagery
Synthetic Aperture Radar (SAR) imagery has diverse applications in land and marine surveillance.
ConDA: Continual Unsupervised Domain Adaptation
Our results on three popular DA datasets demonstrate that our method outperforms many existing state-of-the-art DA methods with access to the entire target domain during adaptation.
OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation
We propose OmniPose, a single-pass, end-to-end trainable framework, that achieves state-of-the-art results for multi-person pose estimation.
Ranked #1 on
Pose Estimation
on MS COCO
LABNet: Local Graph Aggregation Network with Class Balanced Loss for Vehicle Re-Identification
Vehicle re-identification is an important computer vision task where the objective is to identify a specific vehicle among a set of vehicles seen at various viewpoints.
UniPose: Unified Human Pose Estimation in Single Images and Videos
Our results on multiple datasets demonstrate that UniPose, with a ResNet backbone and Waterfall module, is a robust and efficient architecture for pose estimation obtaining state-of-the-art results in single person pose detection for both single images and videos.
Ranked #2 on
Pose Estimation
on UPenn Action
Waterfall Atrous Spatial Pooling Architecture for Efficient Semantic Segmentation
We propose a new efficient architecture for semantic segmentation, based on a "Waterfall" Atrous Spatial Pooling architecture, that achieves a considerable accuracy increase while decreasing the number of network parameters and memory footprint.
Ranked #11 on
Semantic Segmentation
on PASCAL VOC 2012 val
Poly-GAN: Multi-Conditioned GAN for Fashion Synthesis
We present Poly-GAN, a novel conditional GAN architecture that is motivated by Fashion Synthesis, an application where garments are automatically placed on images of human models at an arbitrary pose.
Ranked #2 on
Virtual Try-on
on Deep-Fashion
Cascaded Projection: End-to-End Network Compression and Acceleration
We propose a data-driven approach for deep convolutional neural network compression that achieves high accuracy with high throughput and low memory requirements.
Semantically Invariant Text-to-Image Generation
Along with MMVR, we propose two improvements to the text conditioned image generation.
DEFRAG: Deep Euclidean Feature Representations through Adaptation on the Grassmann Manifold
We propose a novel technique for training deep networks with the objective of obtaining feature representations that exist in a Euclidean space and exhibit strong clustering behavior.
Anomaly Detection in Video Using Predictive Convolutional Long Short-Term Memory Networks
Automating the detection of anomalous events within long video sequences is challenging due to the ambiguity of how such events are defined.
