Select Page

Dr. Salman H. Khan

Assistant Professor @ MBZUAI

phd

Computer Vision Department

Dr. Salman Khan is an Assistant Professor at MBZUAI. He actively works on Deep Neural Networks, Visual Understanding, Low-shot learning, Adversarial learning and Continual life-long learning problems in the Computer Vision domain.

 

Research Synopsis

I am intrigued by the compelling performance of deep neural networks (DNNs) on visual learning tasks. DNNs have revolutionized the pattern recognition and computer vision disciplines with their scalability to large-scale datasets and a diverse set of problems. However, these systems still suffer from several limitations that question their applicability to real-world applications. My research focuses on understanding the limitations of DNNs for computer vision problems and aims to devise novel ways to circumvent these bottlenecks. E.g., deep learning models find it challenging to learn representations on imbalanced datasets, their performance severely degrades against adversarial perturbations, their conventional forms cannot operate in life-long (continual) learning settings, and they typically require large amounts of training data which makes it interesting to investigate how quick adaptation to new tasks is possible with only a few data-samples (zero- and few-shot learning).
Z

Deep learning

Z

Computer Vision

Z

Structured learning

Z

Pattern Recognition

Z

Image Processing

Recent Activity

 

Research

 

  • Three papers (including one Oral) are accepted to CVPR’21. Congratulations to Waqas, Joseph and Rizve! [March’21]
  • Our paper on Conditional Generative Modelling accepted to ICLR’21 [Jan’21]
  • Paper on object counting accepted to IEEE TPAMI [Sep’20]
  • Two papers accepted to ECCV’20. Congratulations to Waqas and Guolei! [Jul’20]
  • A paper on ZSD accepted to IJCV, Springer. [Jul’20]
  • Paper on Spectral-GAN accepted to IROS’20. [Jun’20]
  • A paper accepted in TPAMI on adversarial defense. [Mar’20]
  • Five papers accepted at CVPR’20 (2 orals). Congratulations to Muzammal, Jathushan, Yaxing, Waqas and Haris. [Mar’20]
  • A paper accepted in ACM Computing Surveys. [Mar’20]
  • Our paper won the best student paper award at ICPRAM’20. Congratulations to Sameera. [Feb’20]
  • Paper accepted in IJCV. Congratulations to Sameera! [Dec’19]
  • Our papers on fine-grained recognition and zero-shot detection are accepted in AAAI’20, New York. [Nov’19]
  • Two papers accepted in NeurIPS’19, Vancouver. Congratulations to Jathushan and Muzammal! [Sep’19]
  • A Large-scale Instance Segmentation Dataset for Aerial Images (iSAID) is available for download. [Aug’19]
  • Four papers accepted in upcoming ICCV’19 (including 1 oral). Congratulations to Aamir, Shafin and Sudong! [Jul’19]
  • Selected for the ‘Outstanding Reviewer Award’ at CVPR’19 [May’19]
  • We have claimed 2nd position in CVPR-NTIRE 2019 Image Enhancement Challenge [Apr’19]
  • Two papers (1 oral, 1 poster) accepted in CVPR’19! [Feb’19]

Teaching:

 

  • I am a course co-ordinator for Machine Learning course (ML701) at MBZUAI (Spring 2021).
  • I will be teaching ML701 in the Fall semester. 

Publications:

 

Book

  • S. H. Khan, H. Rahmani, S. A. Shah, M. Bennamoun
    “A Guide to Convolutional Neural Networks for Computer Vision,”
    Synthesis Lectures on Computer Vision, Morgan & Claypool Publishers, Vol. 8, No. 1 , Pages 1-207, 2018.
    [BibTeX] [Link] [Flyer]

2021

  • S. W. Zamir, A. Arora, S. H. Khan, M. Hayat, F. S. Khan, M. H. Yang, and L. Shao,
    “Multi-Stage Progressive Image Restoration,”
    IEEE Conference on Computer Vision and Pattern Recognition, (CVPR), 2021.
    [BibTeX] [PDF] [Supplementary Material] [Code]

  • K. J. Joseph, S. H. Khan, F. S. Khan and V. N Balasubramanian,
    “Towards Open World Object Detection,”
    IEEE Conference on Computer Vision and Pattern Recognition, (CVPR), 2021. (Oral)
    [BibTeX] [PDF] [Code]

  • M. N. Rizve, S. H. Khan, F. S. Khan, and M. Shah,
    “Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning,”
    IEEE Conference on Computer Vision and Pattern Recognition, (CVPR), 2021.
    [BibTeX] [PDF]

  • S. Ramasinghe, K. Ranasinghe, S. Khan, N. Barnes and S. Gould
    “Conditional Generative Modeling via Learning the Latent Space,”
    9th International Conference on Learning Representations, (ICLR), 2021.
    [BibTeX] [PDF] [Codes]

2020

  • H. Cholakkal, G. Sun, S. H. Khan, F. S. Khan, L. Shao and L. V. Gool,
    “Towards Partial Supervision for Generic Object Counting in Natural Scenes,”
    IEEE Transactions on Pattern Analysis and Machine Intelligence, (TPAMI), IEEE, 2020. (Journal)
    [BibTeX] [PDF] [Codes]

  • S. W. Zamir, A. Arora, S. H. Khan, M. Hayat, F. Khan, M. H. Yang and L. Shao,
    “Learning Enriched Features for Real Image Restoration and Enhancement,”
    16th European Conference on Computer Vision, (ECCV), Glasgow, Scotland, 2020.
    [BibTeX] [PDF] [Code]

  • G. Sun, S. H. Khan, W. Li, H. Cholakkal, F. Khan, L. V. Gool,
    “Fixing Localization Errors to Improve Image Classification,”
    16th European Conference on Computer Vision, (ECCV), Glasgow, Scotland, 2020.
    [BibTeX] [PDF] [Code]

  • S. Ramasinghe, S. H. Khan, N. Barnes and S. Gould,
    “Spectral-GANs for High-Resolution 3D Point-cloud Generation,”
    IEEE/RSJ International Conference on Intelligent Robots and Systems, (IROS), Las Vegas, US, 2020.
    [BibTeX] [PDF] [Code]

  • A. Mustafa, S. H. Khan, M. Hayat, R. Goecke, J. Shen and L. Shao,
    “Deeply Supervised Discriminative Learning for Adversarial Defense,”
    IEEE Transactions on Pattern Analysis and Machine Intelligence, (TPAMI), IEEE, 2020. (Journal)
    [BibTeX] [PDF] [Code]

  • S. Rahman, S. H. Khan, N. Barnes and F. S. Khan,
    “Any-Shot Object Detection,”
    Asian Conference on Computer Vision, (ACCV), Kyoto, Japan, 2020.
    [BibTeX] [PDF]

  • N. Hayat, M. Hayat, S. Rahman, S. H. Khan, S. W. Zamir and F. S. Khan,
    “Synthesizing the Unseen for Zero-shot Object Detection,”
    Asian Conference on Computer Vision, (ACCV), Kyoto, Japan, 2020.
    [BibTeX] [PDF] [Code]

  • S. Rahman, S. H. Khan and F. Porikli,
    “Zero-Shot Object Detection: Joint Recognition and Localization of Novel Concepts,”
    International Journal of Computer Vision, (IJCV), 2020. (Journal)
    [BibTeX] [PDF] [Project Page] [Code]

  • S. W. Zamir, A. Arora, S. H. Khan, M. Hayat, F. S. Khan, M. H. Yang, and L. Shao,
    “CycleISP: Real Image Restoration via Improved Data Synthesis,”
    IEEE Conference on Computer Vision and Pattern Recognition, (CVPR), Seattle, Washington, US, 2020. [Oral]
    [BibTeX] [PDF] [Supplementary Material] [Code]

  • M. Naseer, S. H. Khan, M. Hayat, F. S. Khan, and F. Porikli,
    “A Self-supervised Approach for Adversarial Robustness,”
    IEEE Conference on Computer Vision and Pattern Recognition, (CVPR), Seattle, Washington, US, 2020. [Oral]
    [BibTeX] [PDF] [Supplementary Material] [Code]

  • J. Rajasegaran, S. H. Khan, M. Hayat, F. S. Khan, and M. Shah,
    “iTAML: An Incremental Task-Agnostic Meta-learning Approach,”
    IEEE Conference on Computer Vision and Pattern Recognition, (CVPR), Seattle, Washington, US, 2020.
    [BibTeX] [PDF] [Supplementary Material] [Code] [Presentation]

  • M. H. Khan, J. McDonagh, S. H. Khan, M. Shahabuddin, A. Arora, F. S. Khan, L. Shao and G. Tzimiropoulos,
    “AnimalWeb: A Large-Scale Hierarchical Dataset of Annotated Animal Faces,”
    IEEE Conference on Computer Vision and Pattern Recognition, (CVPR), Seattle, Washington, US, 2020.
    [BibTeX] [PDF] [Arxiv] [Dataset]

  • Y. Wang, S. H. Khan, A. Gonzalez-Garcia, J. van de Weijer and F. S. Khan,
    “Semi-supervised Learning for Few-shot Image-to-Image Translation,”
    IEEE Conference on Computer Vision and Pattern Recognition, (CVPR), Seattle, Washington, US, 2020.
    [BibTeX] [PDF] [Supplementary Material] [Code]

  • S. Ramasinghe, S. H. Khan, N. Barnes and S. Gould,
    “Representation Learning on Unit Ball with 3D Roto-Translational Equivariance,”
    International Journal of Computer Vision, (IJCV), 2020. (Journal)
    [BibTeX] [PDF]

  • S. Anwar, S. H. Khan and N. Barnes,
    “A Deep Journey into Super-resolution: A Survey.,”
    ACM Computing Surveys, (CSUR), 2020. (Journal)
    [BibTeX] [PDF] [Arxiv]

  • S. Rahman, S. H. Khan, and N. Barnes,
    “Improved Visual-Semantic Alignment for Zero-Shot Object Detection,”
    34th AAAI Conference on Artificial Intelligence, (AAAI), New York, US, 2020.
    [BibTeX] [PDF] [Project Page] [Arxiv] [Code]

  • G. Sun, H. Cholakkal, S. H. Khan, F. S. Khan and L. Shao,
    “Fine-grained Recognition: Accounting for Subtle Differences between Similar Classes,”
    34th AAAI Conference on Artificial Intelligence, (AAAI), New York, US, 2020.
    [BibTeX] [PDF]

  • Q. Lai, S. H. Khan, Y. Nie, H. Sun, J. Shen, L. Shao,
    “Understanding More about Human and Machine Attention in Deep Neural Networks,”
    IEEE Transactions on Multimedia, (TMM), 2020. (Journal)
    [BibTeX] [PDF]

  • S. Ramasinghe, S. H. Khan, N. Barnes and S. Gould,
    “Blended Convolution and Synthesis for Efficient Discrimination of 3D Shapes,”
    IEEE Winter Conference on Computer Vision, (WACV), 2020.
    [BibTeX] [PDF]

  • M. M. Farazi, S. H. Khan and N. Barnes
    “Question-Agnostic Attention for Visual Question Answering,”
    25th International Conference on Pattern Recognition, (ICPR), Milan Italy, 2020.
    [BibTeX] [PDF]

2019

  • J. Rajasegaran, M. Hayat, S. H. Khan, F. S. Khan and L. Shao,
    “Random Path Selection for Incremental Learning,”
    Advances in Neural Information Processing Systems, (NeurIPS), Vancouver, Canada, 2019.
    [BibTeX] [Arxiv] [Code]

  • M. Naseer, S. H. Khan, H. Khan, F. S. Khan and F. Porikli,
    “Cross-Domain Transferability of Adversarial Perturbations,”
    Advances in Neural Information Processing Systems, (NeurIPS), Vancouver, Canada, 2019.
    [BibTeX] [Arxiv] [Code]

  • M. Hayat, S. H. Khan, S. W. Zamir, J. Shen and L. Shao,
    “Gaussian Affinity for Max-margin Class Imbalanced Learning,”
    International Conference on Computer Vision, (ICCV), Seoul, South Korea, 2019.
    [BibTeX] [PDF]

  • S. Cai, Y. Guo, S. H. Khan, J. Hu and G. Wen,
    “Ground-to-Aerial Image Geo-Localization With a Hard Exemplar Reweighting Triplet Loss,”
    International Conference on Computer Vision, (ICCV), Seoul, South Korea, 2019.
    [BibTeX] [PDF] [Supplementary Material]

  • S. Rahman, S. H. Khan, and N. Barnes,
    “Transductive Learning for Zero-Shot Object Detection,”
    International Conference on Computer Vision, (ICCV), Seoul, South Korea, 2019. [Oral]
    [BibTeX] [PDF] [Supplementary Material] [Code-coming soon]

  • A. Mustafa, S. H. Khan, M. Hayat, R. Goecke, J. Shen and L. Shao,
    “Adversarial Defense by Restricting the Hidden Space of Deep Neural Networks,”
    International Conference on Computer Vision, (ICCV), Seoul, South Korea, 2019.
    [BibTeX] [PDF] [Arxiv] [Codes]

  • A. Mustafa, S. H. Khan, M. Hayat, J. Shen and L. Shao,
    “Image Super-Resolution as a Defense Against Adversarial Attacks,”
    IEEE Transactions on Image Processing (TIP), 2019. (Journal)
    [BibTeX] [PDF] [Codes]

  • G. Ding, S. Khan, and Z. Tang,
    “Dispersion based Clustering for Unsupervised Person Re-identification,”
    30th British Machine Vision Conference, (BMVC), Cardiff UK, 2019.
    [BibTeX] [PDF]

  • S. Rahman, S. Khan, and N. Barnes,
    “Deep0Tag: Deep Multiple Instance Learning for Zero-shot Image Tagging,”
    IEEE Transactions on Multimedia, (TMM), 2019. (Journal)
    [BibTeX] [PDF]

  • S. H. Khan, M. Hayat, S. W. Zamir, J. Shen and L. Shao,
    “Striking the Right Balance with Uncertainty,”
    IEEE Conference on Computer Vision and Pattern Recognition, (CVPR), Long Beach, US, 2019. [Oral]
    [BibTeX] [PDF]

  • S. H. Khan, Y. Guo, M. Hayat and N. Barnes
    “Unsupervised Primitive Discovery for Improved 3D Generative Modeling,”
    IEEE Conference on Computer Vision and Pattern Recognition, (CVPR), Long Beach, US, 2019.
    [BibTeX] [PDF]

  • S. W. Zamir, A. Arora, A. Gupta, S. H. Khan, G. Sun, F. S. Khan, F. Zhu, L. Shao, G. S. Xia, and X. Bai
    “iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images,”
    Workshop on Detecting Objects in Aerial Images, IEEE Conference on Computer Vision and Pattern Recognition, (CVPRw), Long Beach, US, 2019.
    [BibTeX] [PDF] [Dataset Page]

  • G. Ding, S. Zhang, S. H. Khan, Z. Tang, J. Zhang and F. Porikli,
    “Feature Affinity based Pseudo Labeling for Semi-supervised Person Re-identification,”
    IEEE Transactions on Multimedia, (TMM), 2019. (Journal)
    [BibTeX] [PDF]

  • M. Naseer, S. H. Khan and F. Porikli,
    “Local Gradients Smoothing: Defense against localized adversarial attacks,”
    IEEE Winter Conference on Applications of Computer Vision, (WACV), Hawaii, US, 2019.
    [BibTeX] [PDF]

  • G. Ding, S. H. Khan, Z. Tang and F. Porikli,
    “Feature Mask Network for Person Re-identification,”
    Pattern Recognition Letters, (PRL), Elsevier, 2019. (Journal)
    [BibTeX] [PDF]

  • M. Naseer, S. H. Khan and F. Porikli,
    “Indoor Scene Understanding in 2.5/3D for Autonomous Agents: A Survey,”
    IEEE Access, 2019. (Journal)
    [BibTeX] [PDF]

2018

  • S. H. Khan, M. Hayat and F. Porikli,
    “Regularization of Deep Neural Networks with Spectral Dropout,”
    Neural Networks (NN), Elsevier, 2018. (Journal)
    [BibTeX] [PDF]

  • S. Rahman, S. H. Khan and F. Porikli,
    “A Unified approach for Conventional Zero-shot, Generalized Zero-shot and Few-shot Learning,”
    IEEE Transactions on Image Processing (TIP), 2018. (Journal)
    [BibTeX] [PDF]

  • S. Rahman, S. H. Khan and F. Porikli,
    “Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts,”
    Asian Conference on Computer Vision, (ACCV), Perth, Australia, 2018.
    [Project Page] [BibTeX] [PDF] [Code]

  • S. Rahman and S. H. Khan,
    “Deep Multiple Instance Learning for Zero-shot Image Tagging,”
    Asian Conference on Computer Vision, (ACCV), Perth, Australia, 2018.
    [BibTeX] [PDF]

  • M. M. Farazi and S. H. Khan,
    “Reciprocal Attention Fusion for Visual Question Answering,”
    29th British Machine Vision Conference, (BMVC), Newcastle UK, 2018.
    [BibTeX] [PDF]

  • S. Ramasinghe, C. D. Athuraliya and S. H. Khan,
    “A Context-aware Capsule Network for Multi-label Classification,”
    Brain-Driven Computer Vision Workshop, European Conference on Computer Vision, (ECCVw), Munich Germany, 2018.
    [BibTeX] [PDF]

  • S. H. Khan, M. Hayat, and N. Barnes,
    “Adversarial Training of Variational Auto-encoders for High Fidelity Image Generation,”
    IEEE Winter Conference on Applications of Computer Vision (WACV), Nevada USA, 2018.
    [BibTeX] [PDF]

  • M. A. Armin, N. Barnes, S. Khan, M. Liu, F. Grimpen and O. Salvado,
    “Unsupervised learning of endoscopy video frames’ correspondences from global and local transformation,”
    Workshop on Computer Assisted Robotic Endoscopy, 21st International Conference on Medical Image Computing \& Computer Assisted Intervention (MICCAIw), Granada, Spain, 2018.
    [BibTeX] [PDF]

  • G. Ding, S. Zhang, S. Khan and Z. Tang,
    “Center based Pseudo-Labeling for semi-supervised Person Re-identification,”
    Multimodal Biometrics Learning Workshop, IEEE International Conference on Multimedia and Expo (ICMEw), San Diego, USA, 2018.
    [BibTeX] [PDF]

2017

  • S. H. Khan, M. Hayat, M. Bennamoun, F. Sohel and R. Togneri,
    “Cost Sensitive Learning of Deep Feature Representations from Imbalanced Data,”
    IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2017. (Journal)
    [BibTeX] [PDF] [Supp. Material]

  • S. H. Khan, X. He, F. Porikli and M. Bennamoun
    “Forest Change Detection in Incomplete Satellite Images with Deep Neural Networks,”
    IEEE Transactions on Geoscience and Remote Sensing (TGRS), 2017. (Journal)
    [BibTeX] [PDF]

  • M. Hayat, S. H. Khan and M. Bennamoun
    “Empowering Simple Binary Classifiers for Image Set based Face Recognition,”
    International Journal of Computer Vision (IJCV), 2017. (Journal)
    [BibTeX] [PDF]

  • S. H. Khan, M. Hayat, and F. Porikli,
    “Scene Categorization with Spectral Features,”
    IEEE International Conference on Computer Vision (ICCV), 2017.
    [BibTeX] [PDF]

  • S. H. Khan, X. He, F. Porikli, M. Bennamoun, F. Sohel and R. Togneri,
    “Learning deep structured network for weakly supervised change detection,”
    International Joint Conference on Artificial Intelligence (IJCAI), 2017.
    [BibTeX] [PDF]

  • M. Hayat, S. H. Khan, N. Werghi and R. Goecke,
    “Joint Registration and Representation Learning for Unconstrained Face Identification,”
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
    [BibTeX] [PDF]

2016

  • S. H. Khan, M. Bennamoun, F. Sohel and R. Togneri,
    “Automatic shadow detection and removal from a single image,”
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 38, no. 3, pp. 431-446, 2016. (Journal)
    [BibTeX] [PDF]

  • S. H. Khan, M. Bennamoun, F. Sohel, R. Togneri and I. Naseem,
    “Integrating geometrical context for semantic labeling of indoor scenes using rgbd images,”
    International Journal of Computer Vision (IJCV), vol. 117, no. 1, pp. 1-20, 2016. (Journal)
    [BibTeX] [PDF]

  • M. Hayat, S. H. Khan, M. Bennamoun and S. An,
    “A Spatial Layout and Scale Invariant Feature Representation for Indoor Scene Classification,”
    IEEE Transactions on Image Processing (TIP), 2016. (Journal)
    [BibTeX] [PDF]

  • S. H. Khan, M. Hayat, M. Bennamoun, R. Togneri and F. A. Sohel,
    “A Discriminative Representation of Convolutional Features for Indoor Scene Recognition,”
    IEEE Transactions on Image Processing (TIP), vol. 25, no. 7, pp. 3372-3383, 2016. (Journal)
    [BibTeX] [PDF] [OCIS Dataset]

2015

  • S. H. Khan and M. A. Akbar,
    “Multi-Factor Authentication on Cloud,”
    IEEE International Conference on Digital Image Computing: Techniques and Applications (DICTA), pp. 1-7, 2015.
    [BibTeX] [PDF]

  • S. An, M. Hayat, S. H. Khan, M. Bennamoun, F. Boussaid and F. Sohel,
    “Contractive Rectifier Networks for Nonlinear Maximum Margin Classification,”
    IEEE International Conference on Computer Vision (ICCV), pp. 2515-2523, 2015.
    [BibTeX] [PDF]

  • S. H. Khan, X. He, M. Bennamoun, F. Sohel and R. Togneri,
    “Separating objects and clutter in indoor scenes,”
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4603-4611, 2015.
    [BibTeX] [PDF] [Supp. Material] [Poster] [Presentation] [Extended Abstract]

  • S. H. Khan, M. Bennamoun, F. Sohel and R. Togneri,
    “Geometry Driven Semantic Labeling of Indoor Scenes,”
    Scene Understanding Workshop (SUNw) held with (CVPR), 2015.
    [BibTeX] [Extended Abstract]

2014 and Older

  • S. H. Khan, M. Bennamoun, F. Sohel and R. Togneri,
    “Geometry Driven Semantic Labeling of Indoor Scenes,”
    European Conference on Computer Vision, Switzerland, (ECCV), pp. Part-I, 2014.
    [BibTeX] [Plane Detection Code] [PDF]

  • S. H. Khan, M. Bennamoun, F. Sohel and R. Togneri,
    “Automatic Feature Learning for Robust Shadow Detection,”
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1939-1946, 2014.
    [BibTeX] [PDF]

  • S. H. Khan, Z. Khan and F. Shafait,
    “Can Signature Biometrics Address Both Identification and Verification Problems?,”
    12th International Conference on Document Analysis and Recognition (ICDAR), pp. 981-985, 2013.
    [BibTeX] [PDF]

Code and Data:

Datasets and Protocols

  • AnimalWeb – A Large-Scale Hierarchical Dataset of Annotated Animal Faces: We introduce a largescale, hierarchical annotated dataset of animal faces, featuring 21.9K faces captured ‘in-the-wild’ conditions. These faces belong to 334 diverse species, while covering 21 different animal orders across biological taxonomy. Each face is consistently annotated with 9 landmarks on key facial features. It is structured and scalable by design; its development underwent four systematic stages involving rigorous, manual annotation effort of over 6K man-hours. We benchmark the proposed dataset for face alignment using the existing art under two new problem settings. Results showcase its challenging nature, unique attributes and present definite prospects for novel, adaptive, and generalized face-oriented CV algorithms. We further benchmark the dataset across related tasks, namely face detection and fine-grained recognition, to demonstrate multi-task applications and opportunities for improvement. For more details, please see our paper and dataset page.
  • iSAID – A Large-scale Dataset for InstanceSegmentation in Aerial Images: Existing Earth Vision datasets are either suitable for semantic segmentation or object detection. iSAID is the first benchmark dataset for instance segmentation in aerial images. This large-scale and densely annotated dataset contains 655,451 object instances for 15 categories across 2,806 high-resolution images. The distinctive characteristics of iSAID are the following: (a) large number of images with high spatial resolution, (b) fifteen important and commonly occurring categories, (c) large number of instances per category, (d) large count of labelled instances per image, which might help in learning contextual information, (e) huge object scale variation, containing small, medium and large objects, often within the same image, (f) Imbalanced and uneven distribution of objects with varying orientation within images, depicting real-life aerial conditions, (g) several small size objects, with ambiguous appearance, can only be resolved with contextual reasoning, (h) precise instance-level annotations carried out by professional annotators, cross-checked and validated by expert annotators complying with well-defined guidelines. For more detail, please refer to our paper and the dataset page.
  • ImageNet Zero-Shot Object Detection Protocol: The train/val/test splits for zero-shot object detection based on ILSVRC object detection dataset are avilable here. The intructions on how to use the proposed splits are available here. The motivation and details for the proposed train and test protocol can be found in the associated publication and project page.
  • MS-COCO Zero-Shot Object Detection Protocol: The train/val/test splits for zero-shot object detection based on MS-COCO object detection dataset are avilable here. The intructions on how to use the proposed splits are available here. The motivation and details for the proposed train and test protocol can be found in the associated publication and project page.
  • Object Categories in Indoor Scenes: This database contains a total of 15,324 images spanning more than 1300 frequently occurring indoor object categories. The database can potentially be used for fine-grained scene categorization, high-level scene understanding and attribute-based reasoning. The dataset is available for download here. More details about the dataset can be found in the associated publication.

Codes

  • Multi-Stage Progressive Image Restoration [Paper] [Code Link] (CVPR’21)
  • Towards Open World Object Detection [Paper] [Code Link] (CVPR’21)
  • Orthogonal Projection Loss [Paper] [Code Link] (Arxiv’21)
  • On Generating Transferable Targeted Perturbations [Paper] [Code Link] (Arxiv’21)
  • Self-supervised Knowledge Distillation for Few-shot Learning [Paper] [Code Link] (Arxiv’20)
  • Synthesizing the Unseen for Zero-shot Object Detection [Paper] [Code Link] (ACCV’20)
  • Towards Partial Supervision for Generic Object Counting in Natural Scenes [Paper] [Code Link] (TPAMI’20)
  • Fixing Localization Errors to Improve Image Classification [PDF] [Code Link] (ECCV’20)
  • Spectral-GANs for High-Resolution 3D Point-cloud Generation [PDF] [Code Link] (IROS’20)
  • MIRNet: Learning Enriched Features for Real Image Restoration and Enhancement [Paper] [Code Link] (ECCV’20)
  • CycleISP: Real Image Restoration via Improved Data Synthesis [Paper] [Code Link] (CVPR’20)
  • A Self-supervised Approach for Adversarial Robustness [Paper] [Code Link] (CVPR’20)
  • iTAML: An Incremental Task-Agnostic Meta-learning Approach [Paper] [Code Link] (CVPR’20)
  • Semi-supervised Learning for Few-shot Image-to-Image Translation [Paper] [Code Link] (CVPR’20)
  • Cross-Domain Transferability of Adversarial Perturbations [Paper] [Code Link] (NeurIPS’19)
  • Random Path Selection for Incremental Learning [Paper] [Code Link] (NeurIPS’19)
  • Towards better Validity: Dispersion based Clustering for Unsupervised Person Re-identification [Paper] [Code Link] (BMVC’19)
  • Adversarial Defense by Restricting the Hidden Space of Deep Neural Networks [Paper] [Code Link] (ICCV’19)
  • Image Super-Resolution as a Defense Against Adversarial Attacks [Paper] [Code Link] (IEEE TIP’19)
  • Polarity Loss for Zero-shot Detection [Paper] [Code Link] (AAAI’20)
  • Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts [Paper] [Code Link] (ACCV’18)
  • Empowering Simple Binary Classifiers for Image Set based Face Recognition [Paper] [Code Link] (IJCV’17)
  • Plane Detection Code for Geometry Driven Semantic Labeling of Indoor Scenes [Paper] (ECCV’14)

Contact