3.6k citations · 4.8k across the 50 of their papers we have counts for
11 papers · 1 filter
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations
Sanath Narayan, Hisham Cholakkal, Munawar Hayat +3
This work proposes a weakly-supervised temporal action localization framework, called D2-Net, which strives to temporally localize actions using video-level supervision. Our main c…
Synthesizing the Unseen for Zero-shot Object Detection
Nasir Hayat, Munawar Hayat, Shafin Rahman +3
The existing zero-shot detection approaches project visual features to the semantic domain for seen objects, hoping to map unseen objects to their corresponding semantics during in…
Meta-learning the Learning Trends Shared Across Tasks
Jathushan Rajasegaran, Salman Khan, Munawar Hayat +2
Meta-learning stands for 'learning to learn' such that generalization to new tasks is achieved. Among these methods, Gradient-based meta-learning algorithms are a specific sub-clas…
AIM 2020 Challenge on Real Image Super-Resolution: Methods and Results
Pengxu Wei, Hannan Lu, Radu Timofte +68
This paper introduces the real image Super-Resolution (SR) challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020. This ch…
Stylized Adversarial Defense
Muzammal Naseer, Salman Khan, Munawar Hayat +2
Deep Convolution Neural Networks (CNNs) can easily be fooled by subtle, imperceptible changes to the input images. To address this vulnerability, adversarial training creates pertu…
A Self-supervised Approach for Adversarial Robustness
Muzammal Naseer, Salman Khan, Munawar Hayat +2
Adversarial examples can cause catastrophic mistakes in Deep Neural Network (DNNs) based vision systems e.g., for classification, segmentation and object detection. The vulnerabili…
Self-supervised Knowledge Distillation for Few-shot Learning
Jathushan Rajasegaran, Salman Khan, Munawar Hayat +2
Real-world contains an overwhelmingly large number of object classes, learning all of which at once is infeasible. Few shot learning is a promising learning paradigm due to its abi…
iTAML: An Incremental Task-Agnostic Meta-learning Approach
Jathushan Rajasegaran, Salman Khan, Munawar Hayat +2
Humans can continuously learn new knowledge as their experience grows. In contrast, previous learning in deep neural networks can quickly fade out when they are trained on a new ta…
CycleISP: Real Image Restoration via Improved Data Synthesis
Syed Waqas Zamir, Aditya Arora, Salman Khan +4
The availability of large-scale datasets has helped unleash the true potential of deep convolutional neural networks (CNNs). However, for the single-image denoising problem, captur…
Learning Enriched Features for Real Image Restoration and Enhancement
Syed Waqas Zamir, Aditya Arora, Salman Khan +4
With the goal of recovering high-quality image content from its degraded version, image restoration enjoys numerous applications, such as in surveillance, computational photography…
Towards Robust and Reproducible Active Learning Using Neural Networks
Prateek Munjal, Nasir Hayat, Munawar Hayat +2
Active learning (AL) is a promising ML paradigm that has the potential to parse through large unlabeled data and help reduce annotation cost in domains where labeling data can be p…