Search Results for author:
Found 27 papers, 9 papers with code
Block and Group Regularized Sparse Modeling for Dictionary Learning
This paper proposes a dictionary learning framework that combines the proposed block/group (BGSC) or reconstructed block/group (R-BGSC) sparse coding schemes with the novel Intra-block Coherence Suppression Dictionary Learning (ICS-DL) algorithm.
High-Level Concepts for Affective Understanding of Images
This paper aims to bridge the affective gap between image content and the emotional response of the viewer it elicits by using High-Level Concepts (HLCs).
Using Satellite Imagery for Good: Detecting Communities in Desert and Mapping Vaccination Activities
Deep convolutional neural networks (CNNs) have outperformed existing object recognition and detection algorithms.
Automatic Image Transformation for Inducing Affect
In this paper we present an automatic image-transformation method that transforms the source image such that it can induce an emotional affect on the viewer, as desired by the user.
Deep Built-Structure Counting in Satellite Imagery Using Attention Based Re-Weighting
In this paper, we attempt to address the challenging problem of counting built-structures in the satellite imagery.
Leveraging Orientation for Weakly Supervised Object Detection with Application to Firearm Localization
The OAOD algorithm is evaluated on the ITUF dataset and compared with current state-of-the-art object detectors, including fully supervised oriented object detectors.
Twin-Net Descriptor: Twin Negative Mining With Quad Loss for Patch-Based Matching
Our results on Brown and HPatches datasets demonstrate Twin-Net's consistently better performance as well as better discriminatory and generalization capability as compared to the state-of-art.
Ranked #1 on
Patch Matching
on HPatches
EpO-Net: Exploiting Geometric Constraints on Dense Trajectories for Motion Saliency
To handle the nonrigid background like a sea, we also propose a robust fusion mechanism between motion and appearance-based features.
MLSL: Multi-Level Self-Supervised Learning for Domain Adaptation with Spatially Independent and Semantically Consistent Labeling
Thus helping latent space learn the representation even when there are very few pixels belonging to the domain category (small object for example) compared to rest of the image.
Destruction from sky: Weakly supervised approach for destruction detection in satellite imagery
Natural and man-made disasters cause huge damage to built infrastructures and results in loss of human lives.
Localizing Firearm Carriers by Identifying Human-Object Pairs
Visual identification of gunmen in a crowd is a challenging problem, that requires resolving the association of a person with an object (firearm).
Weakly Supervised Domain Adaptation for Built-up Region Segmentation in Aerial and Satellite Imagery
We thoroughly study the limitations of existing domain adaptation methods and propose a weakly-supervised adaptation strategy where we assume image-level labels are available for the target domain.
Learning from Scale-Invariant Examples for Domain Adaptation in Semantic Segmentation
Specifically, we show that semantic segmentation model produces output with high entropy when presented with scaled-up patches of target domain, in comparison to when presented original size images.
A Dataset and Benchmark for Malaria Life-Cycle Classification in Thin Blood Smear Images
Malaria microscopy, microscopic examination of stained blood slides to detect parasite Plasmodium, is considered to be a gold-standard for detecting life-threatening disease malaria.
Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection
In this paper, we propose to leverage model predictive uncertainty to strike the right balance between adversarial feature alignment and class-level alignment.
Cross-Region Building Counting in Satellite Imagery using Counting Consistency
We then exploit counting consistency constraints, within-image count consistency, and across-image count consistency, to decrease the domain shift.
Out of distribution detection for skin and malaria images
Deep neural networks have shown promising results in disease detection and classification using medical image data.
Towards Low-Cost and Efficient Malaria Detection
We design a mechanism to transfer these annotations from the high-cost microscope at high magnification to the low-cost microscope, at multiple magnifications.
SSAL: Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection
In this paper, we propose to leverage model’s predictive uncertainty to strike the right balance between adversarial feature alignment and class-level alignment.
FogAdapt: Self-Supervised Domain Adaptation for Semantic Segmentation of Foggy Images
We propose a self-entropy and multi-scale information augmented self-supervised domain adaptation method (FogAdapt) to minimize the domain shift in foggy scenes segmentation.
Ranked #1 on
Domain Adaptation
on SYNTHIA-to-FoggyCityscapes
Mapping Temporary Slums from Satellite Imagery using a Semi-Supervised Approach
A small set of seed samples (32 in our case) are automatically discovered by analyzing the temporal changes, which are manually labeled to train a segmentation and representation learning module.
Distribution Regularized Self-Supervised Learning for Domain Adaptation of Semantic Segmentation
Due to the domain shift, this decision boundary is unaligned in the target domain, resulting in noisy pseudo labels adversely affecting self-supervised domain adaptation.
Towards Improving Calibration in Object Detection Under Domain Shift
To this end, we first propose a new, plug-and-play, train-time calibration loss for object detection (coined as TCD).
Detection and Localization of Firearm Carriers in Complex Scenes for Improved Safety Measures
By combining these components, our approach achieves exceptional results on a newly proposed dataset.
Leveraging Topology for Domain Adaptive Road Segmentation in Satellite and Aerial Imagery
In this work, we propose a topology-aware unsupervised domain adaptation approach for road segmentation in remote sensing imagery.
Cal-DETR: Calibrated Detection Transformer
Third, we develop a logit mixing approach that acts as a regularizer with detection-specific losses and is also complementary to the uncertainty-guided logit modulation technique to further improve the calibration performance.
Domain Adaptive Object Detection via Balancing Between Self-Training and Adversarial Learning
Deep learning based object detectors struggle generalizing to a new target domain bearing significant variations in object and background.
