L3: Accelerator-Friendly Lossless Image Format for High-Resolution, High-Throughput DNN Training

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	ECCV (17. : 2022 : Tel Aviv; Online) Computer vision – ECCV 2022 ; Part 11
1. Verfasser:	Bae, Jonghyun (VerfasserIn)
Weitere Verfasser:	Baek, Woohyeon (VerfasserIn), Ham, Tae Jun (VerfasserIn), Lee, Jae W. (VerfasserIn)
Pages:	2022
Format:	UnknownFormat
Sprache:	eng
Veröffentlicht:	2022
Schlagworte:
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Bestellen

Titel	Jahr	Verfasser
Knowledge Condensation Distillation	2022	Li, Chenxin
Patch Similarity Aware Data-Free Quantization for Vision Transformers	2022	Li, Zhikai
Symmetry Regularization and Saturating Nonlinearity for Robust Quantization	2022	Park, Sein
ℓ∞-Robustness and Beyond: Unleashing Efficient Adversarial Training	2022	Dolatabadi, Hadi M.
Deep Ensemble Learning by Diverse Knowledge Distillation for Fine-Grained Object Classification	2022	Okamoto, Naoki
A Simple Approach and Benchmark for 21,000-Category Object Detection	2022	Lin, Yutong
Reducing Information Loss for Spiking Neural Networks	2022	Guo, Yufei
Learning with Recoverable Forgetting	2022	Ye, Jingwen
Streaming Multiscale Deep Equilibrium Models	2022	Ertenli, Can Ufuk
Learning to Weight Samples for Dynamic Early-Exiting Networks	2022	Han, Yizeng
Towards Accurate Binary Neural Networks via Modeling Contextual Dependencies	2022	Xing, Xingrun
Network Binarization via Contrastive Learning	2022	Shang, Yuzhang
SPViT: Enabling Faster Vision Transformers via Latency-Aware Soft Token Pruning	2022	Kong, Zhenglun
Non-uniform Step Size Quantization for Accurate Post-training Quantization	2022	Oh, Sangyun
SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning	2022	You, Haoran
Efficient One Pass Self-distillation with Zipf’s Label Smoothing	2022	Liang, Jiajun
Deep Partial Updating: Towards Communication Efficient Updating for On-Device Inference	2022	Qu, Zhongnan
L3: Accelerator-Friendly Lossless Image Format for High-Resolution, High-Throughput DNN Training	2022	Bae, Jonghyun
Mixed-Precision Neural Network Quantization via Learned Layer-Wise Importance	2022	Tang, Chen
Equivariance and Invariance Inductive Bias for Learning from Insufficient Data	2022	Wad, Tan

Alle Artikel auflisten