2.4k citations · 2.8k across the 17 of their papers we have counts for
19 papers
LatentCRF: Continuous CRF for Efficient Latent Diffusion
Kanchana Ranasinghe, Sadeep Jayasumana, Andreas Veit +5
Latent Diffusion Models (LDMs) produce high-quality, photo-realistic images, however, the latency incurred by multiple costly inference iterations can restrict their applicability.…
Efficient Document Ranking with Learnable Late Interactions
Ziwei Ji, Himanshu Jain, Andreas Veit +6
Cross-Encoder (CE) and Dual-Encoder (DE) models are two fundamental approaches for query-document relevance in information retrieval. To predict relevance, CE models use joint quer…
Rethinking FID: Towards a Better Evaluation Metric for Image Generation
Sadeep Jayasumana, Srikumar Ramalingam, Andreas Veit +3
As with many machine learning problems, the progress of image generation methods hinges on good evaluation metrics. One of the most popular is the Frechet Inception Distance (FID).…
MarkovGen: Structured Prediction for Efficient Text-to-Image Generation
Sadeep Jayasumana, Daniel Glasner, Srikumar Ramalingam +3
Modern text-to-image generation models produce high-quality images that are both photorealistic and faithful to the text prompts. However, this quality comes at significant computa…
EmbedDistill: A Geometric Knowledge Distillation for Information Retrieval
Seungyeon Kim, Ankit Singh Rawat, Manzil Zaheer +6
Large neural models (such as Transformers) achieve state-of-the-art performance for information retrieval (IR). In this paper, we aim to improve distillation methods that pave the…
When does mixup promote local linearity in learned representations?
Arslan Chaudhry, Aditya Krishna Menon, Andreas Veit +3
Mixup is a regularization technique that artificially produces new samples using convex combinations of original training points. This simple technique has shown strong empirical p…
Disentangling Sampling and Labeling Bias for Learning in Large-Output Spaces
Ankit Singh Rawat, Aditya Krishna Menon, Wittawat Jitkrittum +4
Negative sampling schemes enable efficient training given a large number of classes, by offering a means to approximate a computationally expensive loss function that takes all lab…
Less is more: Selecting informative and diverse subsets with balancing constraints
Srikumar Ramalingam, Daniel Glasner, Kaushal Patel +3
Deep learning has yielded extraordinary results in vision and natural language processing, but this achievement comes at a cost. Most models require enormous resources during train…
Kernelized Classification in Deep Networks
Sadeep Jayasumana, Srikumar Ramalingam, Sanjiv Kumar
We propose a kernelized classification layer for deep networks. Although conventional deep networks introduce an abundance of nonlinearity for representation (feature) learning, th…
Long-tail learning via logit adjustment
Aditya Krishna Menon, Sadeep Jayasumana, Ankit Singh Rawat +3
Real-world classification problems typically exhibit an imbalanced or long-tailed label distribution, wherein many labels are associated with only a few samples. This poses a chall…
Bipartite Conditional Random Fields for Panoptic Segmentation
Sadeep Jayasumana, Kanchana Ranasinghe, Mayuka Jayawardhana +2
We tackle the panoptic segmentation problem with a conditional random field (CRF) model. Panoptic segmentation involves assigning a semantic label and an instance label to each pix…
Prototypical Priors: From Improving Classification to Zero-Shot Learning
Saumya Jetley, Bernardino Romera-Paredes, Sadeep Jayasumana +1
Recent works on zero-shot learning make use of side information such as visual attributes or natural language semantics to define the relations between output visual classes and th…
Higher Order Conditional Random Fields in Deep Neural Networks
Anurag Arnab, Sadeep Jayasumana, Shuai Zheng +1
We address the problem of semantic segmentation using deep learning. Most segmentation systems include a Conditional Random Field (CRF) to produce a structured output that is consi…
Conditional Random Fields as Recurrent Neural Networks
Shuai Zheng, Sadeep Jayasumana, Bernardino Romera-Paredes +5
Pixel-level labelling tasks, such as semantic segmentation, play a central role in image understanding. Recent approaches have attempted to harness the capabilities of deep learnin…
Optimizing Over Radial Kernels on Compact Manifolds
Sadeep Jayasumana, Richard Hartley, Mathieu Salzmann +2
We tackle the problem of optimizing over all possible positive definite radial kernels on Riemannian manifolds for classification. Kernel methods on Riemannian manifolds have recen…
A Framework for Shape Analysis via Hilbert Space Embedding
Sadeep Jayasumana, Mathieu Salzmann, Hongdong Li +1
We propose a framework for 2D shape analysis using positive definite kernels defined on Kendall's shape manifold. Different representations of 2D shapes are known to generate diffe…
Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matrices
Sadeep Jayasumana, Richard Hartley, Mathieu Salzmann +2
Symmetric Positive Definite (SPD) matrices have become popular to encode image information. Accounting for the geometry of the Riemannian manifold of SPD matrices has proven key to…
Kernel Methods on Riemannian Manifolds with Gaussian RBF Kernels
Sadeep Jayasumana, Richard Hartley, Mathieu Salzmann +2
In this paper, we develop an approach to exploiting kernel methods with manifold-valued data. In many computer vision problems, the data can be naturally represented as points on a…
Expanding the Family of Grassmannian Kernels: An Embedding Perspective
Mehrtash T. Harandi, Mathieu Salzmann, Sadeep Jayasumana +2
Modeling videos and image-sets as linear subspaces has proven beneficial for many visual recognition tasks. However, it also incurs challenges arising from the fact that linear sub…