Salman Khan

Any-Shot Object Detection

Previous work on novel object detection considers zero or few-shot setti...
03/16/2020 ∙ by Shafin Rahman, et al. ∙ 43 ∙ share

read it
Fine-grained Recognition: Accounting for Subtle Differences between Similar Classes

The main requisite for fine-grained recognition task is to focus on subt...
12/14/2019 ∙ by Guolei Sun, et al. ∙ 37 ∙ share

read it
A Deep Journey into Super-resolution: A survey

Deep convolutional networks based super-resolution is a fast-growing fie...
04/16/2019 ∙ by Saeed Anwar, et al. ∙ 28 ∙ share

read it
Spectral-GANs for High-Resolution 3D Point-cloud Generation

Point-clouds are a popular choice for vision and graphics tasks due to t...
12/04/2019 ∙ by Sameera Ramasinghe, et al. ∙ 19 ∙ share

read it
Human vs Machine Attention in Neural Networks: A Comparative Study

Recent years have witnessed a surge in the popularity of attention mecha...
06/20/2019 ∙ by Qiuxia Lai, et al. ∙ 18 ∙ share

read it
CycleISP: Real Image Restoration via Improved Data Synthesis

The availability of large-scale datasets has helped unleash the true pot...
03/17/2020 ∙ by Syed Waqas Zamir, et al. ∙ 14 ∙ share

read it
Learning Enriched Features for Real Image Restoration and Enhancement

With the goal of recovering high-quality image content from its degraded...
03/15/2020 ∙ by Syed Waqas Zamir, et al. ∙ 11 ∙ share

read it
Incremental Object Detection via Meta-Learning

In a real-world setting, object instances from new classes may be contin...
03/17/2020 ∙ by K J Joseph, et al. ∙ 11 ∙ share

read it
Towards Partial Supervision for Generic Object Counting in Natural Scenes

Generic object counting in natural scenes is a challenging computer visi...
12/13/2019 ∙ by Hisham Cholakkal, et al. ∙ 9 ∙ share

read it
Local Gradients Smoothing: Defense against localized adversarial attacks

Deep neural networks (DNNs) have shown vulnerability to adversarial atta...
07/03/2018 ∙ by Muzammal Naseer, et al. ∙ 8 ∙ share

read it
AnimalWeb: A Large-Scale Hierarchical Dataset of Annotated Animal Faces

Being heavily reliant on animals, it is our ethical obligation to improv...
09/11/2019 ∙ by Muhammad Haris Khan, et al. ∙ 7 ∙ share

read it
Semi-supervised Learning for Few-shot Image-to-Image Translation

In the last few years, unpaired image-to-image translation has witnessed...
03/30/2020 ∙ by Yaxing Wang, et al. ∙ 5 ∙ share

read it
iTAML: An Incremental Task-Agnostic Meta-learning Approach

Humans can continuously learn new knowledge as their experience grows. I...
03/25/2020 ∙ by Jathushan Rajasegaran, et al. ∙ 4 ∙ share

read it
Towards better Validity: Dispersion based Clustering for Unsupervised Person Re-identification

Person re-identification aims to establish the correct identity correspo...
06/04/2019 ∙ by Guodong Ding, et al. ∙ 3 ∙ share

read it
Regularization of Deep Neural Networks with Spectral Dropout

The big breakthrough on the ImageNet challenge in 2012 was partially due...
11/23/2017 ∙ by Salman Khan, et al. ∙ 0 ∙ share

read it
Let Features Decide for Themselves: Feature Mask Network for Person Re-identification

Person re-identification aims at establishing the identity of a pedestri...
11/20/2017 ∙ by Guodong Ding, et al. ∙ 0 ∙ share

read it
Deep Multiple Instance Learning for Zero-shot Image Tagging

In-line with the success of deep learning on traditional recognition pro...
03/16/2018 ∙ by Shafin Rahman, et al. ∙ 0 ∙ share

read it
Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts

Current Zero-Shot Learning (ZSL) approaches are restricted to recognitio...
03/16/2018 ∙ by Shafin Rahman, et al. ∙ 0 ∙ share

read it
Feature Affinity based Pseudo Labeling for Semi-supervised Person Re-identification

Person re-identification aims to match a person's identity across multip...
05/16/2018 ∙ by Guodong Ding, et al. ∙ 0 ∙ share

read it
Reciprocal Attention Fusion for Visual Question Answering

Existing attention mechanisms either attend to local image grid or objec...
05/11/2018 ∙ by Moshiur R Farazi, et al. ∙ 0 ∙ share

read it
Visual Affordance and Function Understanding: A Survey

Nowadays, robots are dominating the manufacturing, entertainment and hea...
07/18/2018 ∙ by Mohammed Hassanin, et al. ∙ 0 ∙ share

read it
A Context-aware Capsule Network for Multi-label Classification

Recently proposed Capsule Network is a brain inspired architecture that ...
10/15/2018 ∙ by Sameera Ramasinghe, et al. ∙ 0 ∙ share

read it
Polarity Loss for Zero-shot Object Detection

Zero-shot object detection is an emerging research topic that aims to re...
11/22/2018 ∙ by Shafin Rahman, et al. ∙ 0 ∙ share

read it
Volumetric Convolution: Automatic Representation Learning in Unit Ball

Convolution is an efficient technique to obtain abstract feature represe...
01/03/2019 ∙ by Sameera Ramasinghe, et al. ∙ 0 ∙ share

read it
Max-margin Class Imbalanced Learning with Gaussian Affinity

Real-world object classes appear in imbalanced ratios. This poses a sign...
01/23/2019 ∙ by Munawar Hayat, et al. ∙ 0 ∙ share

read it
Striking the Right Balance with Uncertainty

Learning unbiased models on imbalanced datasets is a significant challen...
01/22/2019 ∙ by Salman Khan, et al. ∙ 0 ∙ share

read it
Adversarial Defense by Restricting the Hidden Space of Deep Neural Networks

Deep neural networks are vulnerable to adversarial attacks, which can fo...
04/01/2019 ∙ by Aamir Mustafa, et al. ∙ 0 ∙ share

read it
Learning Digital Camera Pipeline for Extreme Low-Light Imaging

In low-light conditions, a conventional camera imaging pipeline produces...
04/11/2019 ∙ by Syed Waqas Zamir, et al. ∙ 0 ∙ share

read it
iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images

Existing Earth Vision datasets are either suitable for semantic segmenta...
05/30/2019 ∙ by Syed Waqas Zamir, et al. ∙ 0 ∙ share

read it
Random Path Selection for Incremental Learning

Incremental life-long learning is a main challenge towards the long-stan...
06/03/2019 ∙ by Jathushan Rajasegaran, et al. ∙ 0 ∙ share

read it
Blended Convolution and Synthesis for Efficient Discrimination of 3D Shapes

Existing networks directly learn feature representations on 3D point clo...
08/24/2019 ∙ by Sameera Ramasinghe, et al. ∙ 0 ∙ share

read it
Representation Learning on Unit Ball with 3D Roto-Translational Equivariance

Convolution is an integral operation that defines how the shape of one f...
11/30/2019 ∙ by Sameera Ramasinghe, et al. ∙ 0 ∙ share

read it

Salman Khan

Featured Co-authors