Program
Program Schedule
Timezone: UTC/GMT +2 hours
1:30 PM - 1:40 PM Opening remarks
1:40 PM - 2:10 PM Invited Talk I: Prof. Song Han
2:10 PM - 2:40 PM Invited Talk II: Dr. Prateek Jain
2:40 PM - 2:50 PM Discussion of Results for RCV Challenges
2:50 PM - 3:05 PM Oral Presentation I: Markus Nagel
3:05 PM - 3:20 PM Oral Presentation II: Sophia Abraham
3:20 PM - 4:30 PM Poster Presentation + Coffee Break
4:30 PM - 5:00 PM Invited Talk III: Dr. Sangdoo Yun
5:00 PM - 5:30 PM Invited Talk IV: Dr. Efstratios Gavves
5:30 PM - 5:45 PM Oral Presentation III: Youcef Djenouri
5:45 PM - 5:55 PM Closing Remarks
Meeting links for virtual posters
CoroNetGAN: Controlled Pruning of GANs via Hypernetworks [Meeting Link]
Deterministic Neural Illumination Mapping for Efficient Auto-White Balance Correction [Meeting Link]
Lightweight Vision Transformer with Spatial and Channel Enhanced Self-Attention [Meeting Link]
Enhancing differentiable Architecture search: A study on small number of cell blocks in the search stage, and important branches based cells selection [Meeting Link]
Post Training Mixed Precision Quantization of Neural Networks using First-Order [Meeting Link]
Developing Robust and Lightweight Adversarial Defenders by Enforcing Orthogonality on Attack-Agnostic Denoising Autoencoders [Meeting Link]
Accepted Papers
Workshop Challenge Paper
RCV2023 Challenges: Benchmarking model training and inference for resource-constrained deep learning
Oral
Softmax Bias Correction for Quantized Generative Models [presentation]
NCQS: Nonlinear Convex Quadrature Surrogate Hyperparameter Optimization [presentation]
Shapley Deep Learning: A Consensus for General-Purpose Vision Systems [presentation]
Posters
A Simple and Generic Framework for Feature Distillation via Channel-wise Transformation [poster]
Deterministic Neural Illumination Mapping for Efficient Auto-White Balance Correction [poster]
A Comprehensive Study of Transfer Learning under Constraints [poster]
Ray-Patch: An Efficient Querying for Light Field Transformers [poster]
Cross-model temporal cooperation via saliency maps for efficient frame classification [poster]
YOLOBench: Benchmarking Efficient Object Detectors on Embedded Systems [poster]
Accelerating Deep Neural Networks via Semi-Structured Activation Sparsity [poster]
Revisiting Kernel Temporal Segmentation as an Adaptive Tokenizer for Long-form Video Understanding
When Layers Play the Lottery, all Tickets Win at Initialization [poster]Â
Video Action Recognition with Adaptive Zooming Using Motion Residuals [poster]
HyperSparse Neural Networks: Shifting Exploration to Exploitation through Adaptive Regularization [poster]
Reconstructing Pruned Filters using Cheap Spatial Transformations [poster]
Enhancing differentiable Architecture search: A study on small number of cell blocks in the search stage, and important branches based cells selection [poster]
CoroNetGAN: Controlled Pruning of GANs via Hypernetworks [poster]
Developing Robust and Lightweight Adversarial Defenders by Enforcing Orthogonality on Attack-Agnostic Denoising Autoencoders [poster]
QBitOpt: Fast and Accurate Bitwidth Reallocation during Training [poster]
MGiaD: Multigrid in all dimensions. Efficiency and robustness by weight sharing and coarsening in resolution and channel dimensions [poster]
Accumulation Knowledge Distillation for Conditional GAN Compression [poster]
Characterizing Face Recognition for Resource Efficient Deployment on Edge [poster]
MOFA: A Model Simplification Roadmap for Image Restoration on Mobile Devices [poster]
DetOFA: Efficient Training of Once-for-All Networks for Object Detection using Path Filter [poster]
Post Training Mixed Precision Quantization of Neural Networks using First-Order Information [poster]
ZiCo-BC: A Bias Corrected Zero-Shot NAS for Vision Tasks [poster]
Bi-Encoder Cascades for Efficient Image Search [poster]
Tiny and Efficient Model for the Edge Detection Generalization [poster]
Factorized Dynamic Fully Connected Layers for Neural Networks
DONNAv2 - Lightweight Neural Architecture Search for Vision tasks [poster]
RCD-SGD: Resource-Constrained Distributed SGD in Heterogeneous Environment Via Submodular Partitioning [poster]
Can Unstructured Pruning Reduce the Depth in Deep Neural Networks? [poster]
Surround the Nonlinearity: Inserting Foldable Convolutional Autoencoders to Reduce Activation Footprint [poster]
Cross-Domain Transfer Learning with CoRTe: Consistent and Reliable Transfer from Black-Box to Lightweight Segmentation Model [poster]
Efficient Neural PDE-Solvers using Quantization Aware Training [poster]
Single-Shot Pruning for Pre-trained Models: Rethinking the Importance of Magnitude Pruning [poster]
SCoTTi: Save Computation at Training Time with an adaptive framework [poster]
Entropic Score metric: Decoupling Topology and Size in Training-free NAS [poster]
Fast Object Detection in High-Resolution Videos [poster]
Extending TrOCR for Text Localization-Free OCR of Full-Page Scanned Receipt Images [poster]
Multi-Exit Resource-Efficient Neural Architecture for Image Classification with Optimized Fusion Block [poster]
Lightweight Vision Transformer with Spatial and Channel Enhanced Self-Attention [poster]
Dynamic Neural Network is All You Need: Understanding the Robustness of Dynamic Mechanisms in Neural Networks [poster]
AntiNODE: Evaluating Efficiency Robustness of Neural ODEs [poster]
Shannon Strikes Again! Entropy-based Pruning in Deep Neural Networks for Transfer Learning under Extreme Memory and Computation Budgets [poster]
InstaTune: Instantaneous Neural Architecture Search During Fine-Tuning [poster]
Quantized Generative Models for Solving Inverse Problems [poster]