Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Konstantinos N. PlataniotisSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works18 from public data
- DataDAM: Efficient Dataset Distillation with Attention Matching121
This paper learns synthetic images by matching the spatial attention maps of real and synthetic data generated by different layers within a family of randomly initialized neural networks, achieving state-of-the-art performance while reducing training costs.
- Computational pathology: A survey review and the way forward116
A comprehensive review of more than 800 papers to address the challenges faced in problem design all-the-way to the application and implementation viewpoints of CPath and sketch remaining challenges and provide directions for future technical developments and clinical integration of CPath.
- Emphasizing Discriminative Features for Dataset Distillation in Complex Scenarios23
EDF (emphasizes the discriminative features), a dataset distillation method that enhances key discriminative regions in synthetic images using Grad-CAM activation maps using Grad-CAM activation maps.
- SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference17
This work introduces SparseVILA, a novel method of query-aware token retrieval to dynamically accelerate the underlying LLM, by pruning tokens in the context stage while attending to a sparse subset of visual tokens during the generation phase.
- The Need for Speed: Pruning Transformers with One Recipe17
OPTIN presents one of the first one-shot efficient frameworks for compressing transformer architectures that generalizes well across different class domains, in particular: natural language and image-related tasks, without re-training.
- DD-Ranking: Rethinking the Evaluation of Dataset Distillation14
DD-Ranking, a unified evaluation framework, along with new general evaluation metrics to uncover the true performance improvements achieved by different methods are proposed, which provide a more comprehensive and fair evaluation standard for future research advancements.
- CFDP: Common Frequency Domain Pruning12
This work aims to shed light on the interoperability of intermediate model outputs and their significance beyond the spatial domain, and aims to extrapolate common frequency characteristics defined over the feature maps to rank the individual channels of a layer based on their level of importance in learning the representation.
- Dynamic Vision Mamba8
The proposed method, Dynamic Vision Mamba (DyVM), effectively reduces FLOPs with minor performance drops and generalizes well across different Mamba vision model architectures and different vision tasks.
- Data-to-Model Distillation: Data-Efficient Learning Framework8
A novel framework called Data-to-Model Distillation (D2M) is proposed to distill the real dataset's knowledge into the learnable parameters of a pre-trained generative model by aligning rich representations extracted from real and generated images.
- ATOM: Attention Mixer for Efficient Dataset Distillation8
The ATtentiOn Mixer (ATOM) module is proposed to efficiently distill large datasets using a mixture of channel and spatial-wise attention in the feature matching process, demonstrating superior performance across various computer vision datasets, including CIFAR10/100 and Tiny-Imagenet.
- End-to-End Supervised Multilabel Contrastive Learning8
A new end-to-end training framework -- dubbed KMCL (Kernel-based Mutlilabel Contrastive Learning) -- to address the shortcomings of both model- and data-centric designs and models the uncertainty of the feature encoder while maintaining a low computational footprint.
- 8
- ProbMCL: Simple Probabilistic Contrastive Learning for Multi-Label Visual Classification7
This paper proposes Probabilistic Multi-label Contrastive Learning (ProbMCL), a novel framework to address challenges in multi-label image classification tasks that outperforms the existing state-of-the-art methods while achieving a low computational footprint on both datasets.
- Prioritize Alignment in Dataset Distillation5
This work proposes Prioritize Alignment in Dataset Distillation (PAD), which aligns information from the following two perspectives and achieves remarkable improvements on various benchmarks, achieving state-of-the-art performance.
- CONetV2: Efficient Auto-Channel Size Optimization for CNNs5
This work introduces an efficient searching algorithm, with simulated annealing inspired stochasticity, and demonstrates its effectiveness in finding optimal architectures that outperform baselines by a large margin by examining the micro-search space of channel size.
- 3
- 3
- 2
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.