1.1k citations · 2.1k across the 32 of their papers we have counts for
20 papers · 1 filter
Scaling Prompt Instructed Zero Shot Composed Image Retrieval with Image-Only Data
Yiqun Duan, Sameera Ramasinghe, Stephen Gould +1
Composed Image Retrieval (CIR) is the task of retrieving images matching a reference image augmented with a text, where the text describes changes to the reference image in natural…
Learning Visual Hierarchies in Hyperbolic Space for Image Retrieval
Ziwei Wang, Sameera Ramasinghe, Chenchen Xu +3
Structuring latent representations in a hierarchical manner enables models to learn patterns at multiple levels of abstraction. However, most prevalent image understanding models f…
Adaptive Cross Batch Normalization for Metric Learning
Thalaiyasingam Ajanthan, Matt Ma, Anton van den Hengel +1
Metric learning is a fundamental problem in computer vision whereby a model is trained to learn a semantically useful embedding space via ranking losses. Traditionally, the effecti…
Retrieval Augmented Classification for Long-Tail Visual Recognition
Alexander Long, Wei Yin, Thalaiyasingam Ajanthan +6
We introduce Retrieval Augmented Classification (RAC), a generic approach to augmenting standard image classification pipelines with an explicit retrieval module. RAC consists of a…
Few-shot Weakly-Supervised Object Detection via Directional Statistics
Amirreza Shaban, Amir Rahimi, Thalaiyasingam Ajanthan +2
Detecting novel objects from few examples has become an emerging topic in computer vision recently. However, these methods need fully annotated training images to learn new object…
RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNs
Zhiwei Xu, Thalaiyasingam Ajanthan, Vibhav Vineet +1
Although 3D Convolutional Neural Networks are essential for most learning based applications involving dense 3D data, their applicability is limited due to excessive memory and com…
Refining Semantic Segmentation with Superpixel by Transparent Initialization and Sparse Encoder
Zhiwei Xu, Thalaiyasingam Ajanthan, Richard Hartley
Although deep learning greatly improves the performance of semantic segmentation, its success mainly lies in object central areas without accurate edges. As superpixels are a popul…
RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNs
Zhiwei Xu, Thalaiyasingam Ajanthan, Vibhav Vineet +1
Although 3D Convolutional Neural Networks (CNNs) are essential for most learning based applications involving dense 3D data, their applicability is limited due to excessive memory…
Improved Gradient based Adversarial Attacks for Quantized Networks
Kartik Gupta, Thalaiyasingam Ajanthan
Neural network quantization has become increasingly popular due to efficient memory consumption and faster computation resulting from bitwise operations on the quantized networks.…
Pairwise Similarity Knowledge Transfer for Weakly Supervised Object Localization
Amir Rahimi, Amirreza Shaban, Thalaiyasingam Ajanthan +2
Weakly Supervised Object Localization (WSOL) methods only require image level labels as opposed to expensive bounding box annotations required by fully supervised algorithms. We st…
Fast and Differentiable Message Passing on Pairwise Markov Random Fields
Zhiwei Xu, Thalaiyasingam Ajanthan, Richard Hartley
Despite the availability of many Markov Random Field (MRF) optimization algorithms, their widespread usage is currently limited due to imperfect MRF modelling arising from hand-cra…
Learning to Adapt for Stereo
Alessio Tonioni, Oscar Rahnama, Thomas Joy +3
Real world applications of stereo depth estimation require models that are robust to dynamic variations in the environment. Even though deep learning based stereo methods are succe…
Proximal Mean-field for Neural Network Quantization
Thalaiyasingam Ajanthan, Puneet K. Dokania, Richard Hartley +1
Compressing large Neural Networks (NN) by quantizing the parameters, while maintaining the performance is highly desirable due to reduced memory and time complexity. In this work,…
Generalized Range Moves
Richard Hartley, Thalaiyasingam Ajanthan
We consider move-making algorithms for energy minimization of multi-label Markov Random Fields (MRFs). Since this is not a tractable problem in general, a commonly used heuristic i…
SNIP: Single-shot Network Pruning based on Connection Sensitivity
Namhoon Lee, Thalaiyasingam Ajanthan, Philip H. S. Torr
Pruning large neural networks while maintaining their performance is often desirable due to the reduced space and time complexity. In existing methods, pruning is done within an it…
Efficient Relaxations for Dense CRFs with Sparse Higher Order Potentials
Thomas Joy, Alban Desmaison, Thalaiyasingam Ajanthan +5
Dense conditional random fields (CRFs) have become a popular framework for modelling several problems in computer vision such as stereo correspondence and multi-class semantic segm…
DGPose: Deep Generative Models for Human Body Analysis
Rodrigo de Bem, Arnab Ghosh, Thalaiyasingam Ajanthan +4
Deep generative modelling for human body analysis is an emerging problem with many interesting applications. However, the latent space learned by such approaches is typically not i…
Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
Arslan Chaudhry, Puneet K. Dokania, Thalaiyasingam Ajanthan +1
Incremental learning (IL) has received a lot of attention recently, however, the literature lacks a precise problem definition, proper evaluation settings, and metrics tailored spe…
Efficient Linear Programming for Dense CRFs
Thalaiyasingam Ajanthan, Alban Desmaison, Rudy Bunel +3
The fully connected conditional random field (CRF) with Gaussian pairwise potentials has proven popular and effective for multi-class semantic segmentation. While the energy of a d…
Iteratively Reweighted Graph Cut for Multi-label MRFs with Non-convex Priors
Thalaiyasingam Ajanthan, Richard Hartley, Mathieu Salzmann +1
While widely acknowledged as highly effective in computer vision, multi-label MRFs with non-convex priors are difficult to optimize. To tackle this, we introduce an algorithm that…