Copertina

TPC-ViT: Token Propagation Controller for Efficient Vision Transformer

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Zhu, Wentao
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Multimedia Neural and Evolutionary Computing
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Arabic Handwritten Text for Person Biometric Identification: A Deep Learning Approach
di: Balat, Mazen, et al.
Pubblicazione: (2024)

E2HQV: High-Quality Video Generation from Event Camera via Theory-Inspired Model-Aided Deep Learning
di: Qu, Qiang, et al.
Pubblicazione: (2024)

SSTFormer: Bridging Spiking Neural Network and Memory Support Transformer for Frame-Event based Recognition
di: Wang, Xiao, et al.
Pubblicazione: (2023)

DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs
di: Kim, Donghyun, et al.
Pubblicazione: (2024)

On the Surprising Effectiveness of Attention Transfer for Vision Transformers
di: Li, Alexander C., et al.
Pubblicazione: (2024)

Understanding Transformer-based Vision Models through Inversion
di: Rathjens, Jan, et al.
Pubblicazione: (2024)

EVOS: Efficient Implicit Neural Training via EVOlutionary Selector
di: Zhang, Weixiang, et al.
Pubblicazione: (2024)

Kolmogorov-Arnold Transformer
di: Yang, Xingyi, et al.
Pubblicazione: (2024)

STAS: Spatio-Temporal Adaptive Computation Time for Spiking Transformers
di: Kang, Donghwa, et al.
Pubblicazione: (2025)

DS2TA: Denoising Spiking Transformer with Attenuated Spatiotemporal Attention
di: Xu, Boxun, et al.
Pubblicazione: (2024)

Neural Sentinel: Unified Vision Language Model (VLM) for License Plate Recognition with Human-in-the-Loop Continual Learning
di: Sivakoti, Karthik
Pubblicazione: (2026)

Brain-Inspired Efficient Pruning: Exploiting Criticality in Spiking Neural Networks
di: Chen, Shuo, et al.
Pubblicazione: (2023)

Dynamic Activation with Knowledge Distillation for Energy-Efficient Spiking NN Ensembles
di: Konstantaropoulos, Orestis, et al.
Pubblicazione: (2025)

Fast and Efficient Local Search for Genetic Programming Based Loss Function Learning
di: Raymond, Christian, et al.
Pubblicazione: (2024)

Towards Efficient and Accurate Spiking Neural Networks via Adaptive Bit Allocation
di: Yao, Xingting, et al.
Pubblicazione: (2025)

SMART: Scalable Mesh-free Aerodynamic Simulations from Raw Geometries using a Transformer-based Surrogate Model
di: Hagnberger, Jan, et al.
Pubblicazione: (2026)

Deformable Audio Transformer for Audio Event Detection
di: Zhu, Wentao
Pubblicazione: (2023)

Fitness Landscape Footprint: A Framework to Compare Neural Architecture Search Problems
di: Traoré, Kalifou René, et al.
Pubblicazione: (2021)

When Person Re-Identification Meets Event Camera: A Benchmark Dataset and An Attribute-guided Re-Identification Framework
di: Wang, Xiao, et al.
Pubblicazione: (2025)

SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization
di: Zhang, Jintao, et al.
Pubblicazione: (2024)

TDFormer: A Top-Down Attention-Controlled Spiking Transformer
di: Zhu, Zizheng, et al.
Pubblicazione: (2025)

Making Images from Images: Interleaving Denoising and Transformation
di: Baluja, Shumeet, et al.
Pubblicazione: (2024)

Elastic Spiking Transformers for Efficient Gesture Understanding
di: Ancilotto, Alberto, et al.
Pubblicazione: (2026)

The Platonic Representation Hypothesis
di: Huh, Minyoung, et al.
Pubblicazione: (2024)

Neuromimetic metaplasticity for adaptive continual learning
di: Cho, Suhee, et al.
Pubblicazione: (2024)

CoNO: Complex Neural Operator for Continous Dynamical Physical Systems
di: Tiwari, Karn, et al.
Pubblicazione: (2024)

Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models
di: Kynkäänniemi, Tuomas, et al.
Pubblicazione: (2024)

Benchmarking Spiking Neural Network Learning Methods with Varying Locality
di: Lin, Jiaqi, et al.
Pubblicazione: (2024)

Data augmentation with automated machine learning: approaches and performance comparison with classical data augmentation methods
di: Mumuni, Alhassan, et al.
Pubblicazione: (2024)

HyperGALE: ASD Classification via Hypergraph Gated Attention with Learnable Hyperedges
di: Arora, Mehul, et al.
Pubblicazione: (2024)

Evolutionary Neural Architecture Search for 3D Point Cloud Analysis
di: Yang, Yisheng, et al.
Pubblicazione: (2024)

The devil is in discretization discrepancy. Robustifying Differentiable NAS with Single-Stage Searching Protocol
di: Subbotko, Konstanty, et al.
Pubblicazione: (2024)

Multistep Distillation of Diffusion Models via Moment Matching
di: Salimans, Tim, et al.
Pubblicazione: (2024)

Composite Active Learning: Towards Multi-Domain Active Learning with Theoretical Guarantees
di: Hao, Guang-Yuan, et al.
Pubblicazione: (2024)

Guiding a Diffusion Model with a Bad Version of Itself
di: Karras, Tero, et al.
Pubblicazione: (2024)

Neural network interpretability with layer-wise relevance propagation: novel techniques for neuron selection and visualization
di: Bhati, Deepshikha, et al.
Pubblicazione: (2024)

DUA-D2C: Dynamic Uncertainty Aware Method for Overfitting Remediation in Deep Learning
di: Siddiqui, Md. Saiful Bari, et al.
Pubblicazione: (2024)

Unveiling the Unseen: Identifiable Clusters in Trained Depthwise Convolutional Kernels
di: Babaiee, Zahra, et al.
Pubblicazione: (2024)

Encodings for Prediction-based Neural Architecture Search
di: Akhauri, Yash, et al.
Pubblicazione: (2024)

The Cooperative Network Architecture: Learning Structured Networks as Representation of Sensory Patterns
di: Sager, Pascal J., et al.
Pubblicazione: (2024)