Copertina

Visualizing high-dimensional loss landscapes with Hessian directions

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Böttcher, Lucas, Wheeler, Gregory
Natura:	Preprint
Pubblicazione:	2022
Soggetti:	Machine Learning Computer Vision and Pattern Recognition Computation
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis
di: Gabdullin, Nikita
Pubblicazione: (2024)

Visualizing the loss landscape of Self-supervised Vision Transformer
di: Lee, Youngwan, et al.
Pubblicazione: (2024)

MGVQ: Synergizing Multi-dimensional Sensitivity-Aware and Gradient-Hessian Fusion for Vector Quantization
di: Wang, Zhong, et al.
Pubblicazione: (2026)

Hessian Surgery: Class-Targeted Post-Hoc Rebalancing via Hessian Spike Perturbation
di: Vigna, Hugo, et al.
Pubblicazione: (2026)

The effects of Hessian eigenvalue spectral density type on the applicability of Hessian analysis to generalization capability assessment of neural networks
di: Gabdullin, Nikita
Pubblicazione: (2025)

EPTQ: Enhanced Post-Training Quantization via Hessian-guided Network-wise Optimization
di: Gordon, Ofir, et al.
Pubblicazione: (2023)

Technical Report: Activation Residual Hessian Quantization (ARHQ) for Low-Bit LLM Quantization
di: Wang, YiFeng, et al.
Pubblicazione: (2026)

Object-Centric Cropping for Visual Few-Shot Classification
di: Abdali, Aymane, et al.
Pubblicazione: (2025)

CAMP-HiVe: Cyclic Pair Merging based Efficient DNN Pruning with Hessian-Vector Approximation for Resource-Constrained Systems
di: Uddin, Mohammad Helal, et al.
Pubblicazione: (2025)

Parallel Backpropagation for Shared-Feature Visualization
di: Lappe, Alexander, et al.
Pubblicazione: (2024)

National level satellite-based crop field inventories in smallholder landscapes
di: Rufin, Philippe, et al.
Pubblicazione: (2025)

A margin-based replacement for cross-entropy loss
di: Spratling, Michael W., et al.
Pubblicazione: (2025)

Exploiting the Exact Denoising Posterior Score in Training-Free Guidance of Diffusion Models
di: Bellchambers, Gregory
Pubblicazione: (2025)

Deferred Poisoning: Making the Model More Vulnerable via Hessian Singularization
di: He, Yuhao, et al.
Pubblicazione: (2024)

FogGuard: guarding YOLO against fog using perceptual loss
di: Gharatappeh, Soheil, et al.
Pubblicazione: (2024)

A hierarchical loss and its problems when classifying non-hierarchically
di: Wu, Cinna, et al.
Pubblicazione: (2017)

Inverse problems with diffusion models: MAP estimation via mode-seeking loss
di: Gutha, Sai Bharath Chandra, et al.
Pubblicazione: (2025)

Regularizing cross entropy loss via minimum entropy and K-L divergence
di: Ibraheem, Abdulrahman Oladipupo
Pubblicazione: (2025)

BMIP: Bi-directional Modality Interaction Prompt Learning for VLM
di: Lv, Song-Lin, et al.
Pubblicazione: (2025)

Bayesian generative models can flag performance loss, bias, and out-of-distribution image content
di: López-Pérez, Miguel, et al.
Pubblicazione: (2025)

Reduced storage direct tensor ring decomposition for convolutional neural networks compression
di: Gabor, Mateusz, et al.
Pubblicazione: (2024)

Visual Language Hypothesis
di: Li, Xiu
Pubblicazione: (2025)

Pretrained Visual Uncertainties
di: Kirchhof, Michael, et al.
Pubblicazione: (2024)

Multimodal Reference Visual Grounding
di: Lu, Yangxiao, et al.
Pubblicazione: (2025)

Visualize and Paint GAN Activations
di: Herdt, Rudolf, et al.
Pubblicazione: (2024)

Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processing
di: Shu, Yan, et al.
Pubblicazione: (2024)

Transformer-VQ: Linear-Time Transformers via Vector Quantization
di: Lingle, Lucas D.
Pubblicazione: (2023)

Evaluation of Audio-Visual Alignments in Visually Grounded Speech Models
di: Khorrami, Khazar, et al.
Pubblicazione: (2021)

Lecture Video Visual Objects (LVVO) Dataset: A Benchmark for Visual Object Detection in Educational Videos
di: Biswas, Dipayan, et al.
Pubblicazione: (2025)

Activation-Free Backbones for Image Recognition: Polynomial Alternatives within MetaFormer-Style Vision Models
di: Wang, Jeffrey, et al.
Pubblicazione: (2026)

Adaptive Discriminative Regularization for Visual Classification
di: Zhao, Qingsong, et al.
Pubblicazione: (2022)

VisualRWKV: Exploring Recurrent Neural Networks for Visual Language Models
di: Hou, Haowen, et al.
Pubblicazione: (2024)

LLMs as Visual Explainers: Advancing Image Classification with Evolving Visual Descriptions
di: Han, Songhao, et al.
Pubblicazione: (2023)

Visually Prompted Benchmarks Are Surprisingly Fragile
di: Feng, Haiwen, et al.
Pubblicazione: (2025)

Probing Visual Language Priors in VLMs
di: Luo, Tiange, et al.
Pubblicazione: (2024)

Learning Privacy from Visual Entities
di: Xompero, Alessio, et al.
Pubblicazione: (2025)

CATVis: Context-Aware Thought Visualization
di: Mehmood, Tariq, et al.
Pubblicazione: (2025)

Learning Visual-Semantic Subspace Representations
di: Moreira, Gabriel, et al.
Pubblicazione: (2024)

Questioning the Stability of Visual Question Answering
di: Rosenfeld, Amir, et al.
Pubblicazione: (2025)

Test-Time Visual In-Context Tuning
di: Xie, Jiahao, et al.
Pubblicazione: (2025)