Thalaiyasingam Ajanthan

67 papers A* 14A 4B 1Misc 1Journal 40Unranked 7

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	AsyncMesh: Fully Asynchronous Optimization for Data and Pipeline Parallelism. CoRR Thalaiyasingam Ajanthan, Sameera Ramasinghe, Gil Avraham, Hadi Mohaghegh Dolatabadi, Chamin Hewa Koneputugodage, Violetta Shevchenko, Yan Zuo, Alexander Long
2026	J	`jnl`	NuMuon: Nuclear-Norm-Constrained Muon for Compressible LLM Training. CoRR Hadi Mohaghegh Dolatabadi, Thalaiyasingam Ajanthan, Sameera Ramasinghe, Chamin Hewa Koneputugodage, Shamane Siriwardhana, Violetta Shevchenko, Karol Pajak, James Snewin, Gil Avraham, Alexander Long
2026	J	`jnl`	SENTINEL: Stagewise Integrity Verification for Pipeline Parallel Decentralized Training. CoRR Hadi Mohaghegh Dolatabadi, Thalaiyasingam Ajanthan, Sameera Ramasinghe, Chamin Hewa Koneputugodage, Gil Avraham, Yan Zuo, Violetta Shevchenko, Alexander Long
2025	A*	`conf`	Nesterov Method for Asynchronous Pipeline Parallel Optimization. ICML Thalaiyasingam Ajanthan, Sameera Ramasinghe, Yan Zuo, Gil Avraham, Alexander Long
2025	J	`jnl`	Nesterov Method for Asynchronous Pipeline Parallel Optimization. CoRR Thalaiyasingam Ajanthan, Sameera Ramasinghe, Yan Zuo, Gil Avraham, Alexander Long
2025	J	`jnl`	Protocol Models: Scaling Decentralized Training with Communication-Efficient Model Parallelism. CoRR Sameera Ramasinghe, Thalaiyasingam Ajanthan, Gil Avraham, Yan Zuo, Alexander Long
2025	B	`conf`	Scaling Prompt Instructed Zero Shot Composed Image Retrieval with Image-Only Data. IJCNN Yiqun Duan, Sameera Ramasinghe, Stephen Gould, Thalaiyasingam Ajanthan
2025	J	`jnl`	Scaling Prompt Instructed Zero Shot Composed Image Retrieval with Image-Only Data. CoRR Yiqun Duan, Sameera Ramasinghe, Stephen Gould, Thalaiyasingam Ajanthan
2025	J	`jnl`	Sharper Convergence Rates for Nonconvex Optimisation via Reduction Mappings. CoRR Evan Markou, Thalaiyasingam Ajanthan, Stephen Gould
2024	A*	`conf`	Accept the Modality Gap: An Exploration in the Hyperbolic Space. CVPR Sameera Ramasinghe, Violetta Shevchenko, Gil Avraham, Thalaiyasingam Ajanthan
2024	A*	`conf`	Guiding Neural Collapse: Optimising Towards the Nearest Simplex Equiangular Tight Frame. NeurIPS Evan Markou, Thalaiyasingam Ajanthan, Stephen Gould
2024	J	`jnl`	Guiding Neural Collapse: Optimising Towards the Nearest Simplex Equiangular Tight Frame. CoRR Evan Markou, Thalaiyasingam Ajanthan, Stephen Gould
2024	J	`jnl`	Learning Visual Hierarchies with Hyperbolic Embeddings. CoRR Ziwei Wang, Sameera Ramasinghe, Chenchen Xu, Julien Monteil, Loris Bazzani, Thalaiyasingam Ajanthan
2024	A	`conf`	Self-Supervision Improves Diffusion Models for Tabular Data Imputation. CIKM Yixin Liu, Thalaiyasingam Ajanthan, Hisham Husain, Vu Nguyen
2024	J	`jnl`	Self-Supervision Improves Diffusion Models for Tabular Data Imputation. CoRR Yixin Liu, Thalaiyasingam Ajanthan, Hisham Husain, Vu Nguyen
2023	J	`jnl`	Adaptive Cross Batch Normalization for Metric Learning. CoRR Thalaiyasingam Ajanthan, Matt Ma, Anton van den Hengel, Stephen Gould
2023	J	`jnl`	Bidirectionally self-normalizing neural networks. Neural Networks Yao Lu, Stephen Gould, Thalaiyasingam Ajanthan
2023	A*	`conf`	Semi-Supervised Semantic Segmentation under Label Noise via Diverse Learning Groups. ICCV Peixia Li, Pulak Purkait, Thalaiyasingam Ajanthan, Majid Abdolshah, Ravi Garg, Hisham Husain, Chenchen Xu, Stephen Gould, Wanli Ouyang, Anton van den Hengel
2022	A	`conf`	Few-shot Weakly-Supervised Object Detection via Directional Statistics. WACV Amirreza Shaban, Amir Rahimi, Thalaiyasingam Ajanthan, Byron Boots, Richard Hartley
2022	A*	`conf`	Improved Gradient-Based Adversarial Attacks for Quantized Networks. AAAI Kartik Gupta, Thalaiyasingam Ajanthan
2022	A*	`conf`	Retrieval Augmented Classification for Long-Tail Visual Recognition. CVPR Alexander Long, Wei Yin, Thalaiyasingam Ajanthan, Vu Nguyen, Pulak Purkait, Ravi Garg, Alan Blair, Chunhua Shen, Anton van den Hengel
2022	J	`jnl`	Retrieval Augmented Classification for Long-Tail Visual Recognition. CoRR Alexander Long, Wei Yin, Thalaiyasingam Ajanthan, Vu Nguyen, Pulak Purkait, Ravi Garg, Alan Blair, Chunhua Shen, Anton van den Hengel
2022	—	`conf`	Training 1-Bit Networks on a Sphere: A Geometric Approach. ICANN (3) Luis Guerra, Thalaiyasingam Ajanthan, Gil Avraham, Yan Zou, Tom Drummond
2022	J	`jnl`	Understanding and Improving the Role of Projection Head in Self-Supervised Learning. CoRR Kartik Gupta, Thalaiyasingam Ajanthan, Anton van den Hengel, Stephen Gould
2021	Misc	`conf`	A Chaos Theory Approach to Understand Neural Network Optimization. DICTA Michele Sasdelli, Thalaiyasingam Ajanthan, Tat-Jun Chin, Gustavo Carneiro
2021	A*	`conf`	Calibration of Neural Networks using Splines. ICLR Kartik Gupta, Amir Rahimi, Thalaiyasingam Ajanthan, Thomas Mensink, Cristian Sminchisescu, Richard Hartley
2021	J	`jnl`	Few-shot Weakly-Supervised Object Detection via Directional Statistics. CoRR Amirreza Shaban, Amir Rahimi, Thalaiyasingam Ajanthan, Byron Boots, Richard I. Hartley
2021	A	`conf`	Mirror Descent View for Neural Network Quantization. AISTATS Thalaiyasingam Ajanthan, Kartik Gupta, Philip H. S. Torr, Richard Hartley, Puneet K. Dokania
2021	J	`jnl`	RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNs. CoRR Zhiwei Xu, Thalaiyasingam Ajanthan, Vibhav Vineet, Richard I. Hartley
2021	A*	`conf`	Understanding the effects of data parallelism and sparsity on neural network training. ICLR Namhoon Lee, Thalaiyasingam Ajanthan, Philip H. S. Torr, Martin Jaggi
2020	A*	`conf`	A Signal Propagation Perspective for Pruning Neural Networks at Initialization. ICLR Namhoon Lee, Thalaiyasingam Ajanthan, Stephen Gould, Philip H. S. Torr
2020	J	`jnl`	Bidirectional Self-Normalizing Neural Networks. CoRR Yao Lu, Stephen Gould, Thalaiyasingam Ajanthan
2020	J	`jnl`	Calibration of Neural Networks using Splines. CoRR Kartik Gupta, Amir Rahimi, Thalaiyasingam Ajanthan, Thomas Mensink, Cristian Sminchisescu, Richard Hartley
2020	J	`jnl`	DGPose: Deep Generative Models for Human Body Analysis. Int. J. Comput. Vis. Rodrigo Andrade de Bem, Arnab Ghosh, Thalaiyasingam Ajanthan, Ondrej Miksik, Adnane Boukhayma, N. Siddharth, Philip H. S. Torr
2020	J	`jnl`	Deep Learning Superpixel Semantic Segmentation with Transparent Initialization and Sparse Encoder. CoRR Zhiwei Xu, Thalaiyasingam Ajanthan, Richard I. Hartley
2020	—	`conf`	Fast and Differentiable Message Passing on Pairwise Markov Random Fields. ACCV (3) Zhiwei Xu, Thalaiyasingam Ajanthan, Richard I. Hartley
2020	J	`jnl`	Improved Gradient based Adversarial Attacks for Quantized Networks. CoRR Kartik Gupta, Thalaiyasingam Ajanthan
2020	J	`jnl`	In Defense of Graph Inference Algorithms for Weakly Supervised Object Localization. CoRR Amir Rahimi, Amirreza Shaban, Thalaiyasingam Ajanthan, Richard Hartley, Byron Boots
2020	—	`conf`	Pairwise Similarity Knowledge Transfer for Weakly Supervised Object Localization. ECCV (24) Amir Rahimi, Amirreza Shaban, Thalaiyasingam Ajanthan, Richard I. Hartley, Byron Boots
2020	J	`jnl`	Post-hoc Calibration of Neural Networks. CoRR Amir Rahimi, Kartik Gupta, Thalaiyasingam Ajanthan, Thomas Mensink, Cristian Sminchisescu, Richard Hartley
2020	—	`conf`	RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNs. 3DV Zhiwei Xu, Thalaiyasingam Ajanthan, Vibhav Vineet, Richard I. Hartley
2020	J	`jnl`	RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNs. CoRR Zhiwei Xu, Thalaiyasingam Ajanthan, Vibhav Vineet, Richard I. Hartley
2019	A	`conf`	A Conditional Deep Generative Model of People in Natural Images. WACV Rodrigo Andrade de Bem, Arnab Ghosh, Adnane Boukhayma, Thalaiyasingam Ajanthan, N. Siddharth, Philip H. S. Torr
2019	J	`jnl`	A Signal Propagation Perspective for Pruning Neural Networks at Initialization. CoRR Namhoon Lee, Thalaiyasingam Ajanthan, Stephen Gould, Philip H. S. Torr
2019	J	`jnl`	Continual Learning with Tiny Episodic Memories. CoRR Arslan Chaudhry, Marcus Rohrbach, Mohamed Elhoseiny, Thalaiyasingam Ajanthan, Puneet Kumar Dokania, Philip H. S. Torr, Marc'Aurelio Ranzato
2019	J	`jnl`	Efficient Relaxations for Dense CRFs with Sparse Higher-Order Potentials. SIAM J. Imaging Sci. Thomas Joy, Alban Desmaison, Thalaiyasingam Ajanthan, Rudy Bunel, Mathieu Salzmann, Pushmeet Kohli, Philip H. S. Torr, M. Pawan Kumar
2019	J	`jnl`	Fast and Differentiable Message Passing for Stereo Vision. CoRR Zhiwei Xu, Thalaiyasingam Ajanthan, Richard Hartley
2019	A*	`conf`	Learning to Adapt for Stereo. CVPR Alessio Tonioni, Oscar Rahnama, Thomas Joy, Luigi Di Stefano, Thalaiyasingam Ajanthan, Philip H. S. Torr
2019	J	`jnl`	Learning to Adapt for Stereo. CoRR Alessio Tonioni, Oscar Rahnama, Thomas Joy, Luigi Di Stefano, Thalaiyasingam Ajanthan, Philip H. S. Torr
2019	J	`jnl`	Memory Efficient Max Flow for Multi-Label Submodular MRFs. IEEE Trans. Pattern Anal. Mach. Intell. Thalaiyasingam Ajanthan, Richard Hartley, Mathieu Salzmann
2019	J	`jnl`	Mirror Descent View for Neural Network Quantization. CoRR Thalaiyasingam Ajanthan, Kartik Gupta, Philip H. S. Torr, Richard Hartley, Puneet K. Dokania
2019	A*	`conf`	Proximal Mean-Field for Neural Network Quantization. ICCV Thalaiyasingam Ajanthan, Puneet K. Dokania, Richard Hartley, Philip H. S. Torr
2019	—	`conf`	Snip: single-Shot Network Pruning based on Connection sensitivity. ICLR (Poster) Namhoon Lee, Thalaiyasingam Ajanthan, Philip H. S. Torr
2018	—	`conf`	A Semi-supervised Deep Generative Model for Human Body Analysis. ECCV Workshops (2) Rodrigo Andrade de Bem, Arnab Ghosh, Thalaiyasingam Ajanthan, Ondrej Miksik, N. Siddharth, Philip H. S. Torr
2018	J	`jnl`	DGPose: Disentangled Semi-supervised Deep Generative Models for Human Body Analysis. CoRR Rodrigo Andrade de Bem, Arnab Ghosh, Thalaiyasingam Ajanthan, Ondrej Miksik, N. Siddharth, Philip H. S. Torr
2018	J	`jnl`	Efficient Relaxations for Dense CRFs with Sparse Higher Order Potentials. CoRR Thomas Joy, Alban Desmaison, Thalaiyasingam Ajanthan, Rudy Bunel, Mathieu Salzmann, Pushmeet Kohli, Philip H. S. Torr, M. Pawan Kumar
2018	J	`jnl`	Generalized Range Moves. CoRR Richard I. Hartley, Thalaiyasingam Ajanthan
2018	J	`jnl`	Proximal Mean-field for Neural Network Quantization. CoRR Thalaiyasingam Ajanthan, Puneet Kumar Dokania, Richard I. Hartley, Philip H. S. Torr
2018	—	`conf`	Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence. ECCV (11) Arslan Chaudhry, Puneet Kumar Dokania, Thalaiyasingam Ajanthan, Philip H. S. Torr
2018	J	`jnl`	Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence. CoRR Arslan Chaudhry, Puneet Kumar Dokania, Thalaiyasingam Ajanthan, Philip H. S. Torr
2018	J	`jnl`	SNIP: Single-shot Network Pruning based on Connection Sensitivity. CoRR Namhoon Lee, Thalaiyasingam Ajanthan, Philip H. S. Torr
2017	A*	`conf`	Efficient Linear Programming for Dense CRFs. CVPR Thalaiyasingam Ajanthan, Alban Desmaison, Rudy Bunel, Mathieu Salzmann, Philip H. S. Torr, M. Pawan Kumar
2017	J	`jnl`	Memory Efficient Max Flow for Multi-label Submodular MRFs. CoRR Thalaiyasingam Ajanthan, Richard I. Hartley, Mathieu Salzmann
2016	J	`jnl`	Efficient Linear Programming for Dense CRFs. CoRR Thalaiyasingam Ajanthan, Alban Desmaison, Rudy Bunel, Mathieu Salzmann, Philip H. S. Torr, M. Pawan Kumar
2016	A*	`conf`	Memory Efficient Max Flow for Multi-label Submodular MRFs. CVPR Thalaiyasingam Ajanthan, Richard I. Hartley, Mathieu Salzmann
2015	A*	`conf`	Iteratively reweighted graph cut for multi-label MRFs with non-convex priors. CVPR Thalaiyasingam Ajanthan, Richard I. Hartley, Mathieu Salzmann, Hongdong Li
2014	J	`jnl`	Iteratively Reweighted Graph Cut for Multi-label MRFs with Non-convex Priors. CoRR Thalaiyasingam Ajanthan, Richard I. Hartley, Mathieu Salzmann, Hongdong Li