Copertina

No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Simoncini, Walter, Gidaris, Spyros, Bursuc, Andrei, Asano, Yuki M.
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition Computation and Language Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments
di: Gidaris, Spyros, et al.
Pubblicazione: (2023)

Boosting Visual Instruction Tuning with Self-Supervised Guidance
di: Sirko-Galouchenko, Sophia, et al.
Pubblicazione: (2026)

OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networks
di: Sirko-Galouchenko, Sophia, et al.
Pubblicazione: (2024)

Multi-Token Prediction Needs Registers
di: Gerontopoulos, Anastasios, et al.
Pubblicazione: (2025)

Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning
di: Venkataramanan, Shashanka, et al.
Pubblicazione: (2025)

DIP: Unsupervised Dense In-Context Post-training of Visual Representations
di: Sirko-Galouchenko, Sophia, et al.
Pubblicazione: (2025)

Deep Augmentation: Dropout as Augmentation for Self-Supervised Learning
di: Brüel-Gabrielsson, Rickard, et al.
Pubblicazione: (2023)

The Common Stability Mechanism behind most Self-Supervised Learning Approaches
di: Jha, Abhishek, et al.
Pubblicazione: (2024)

Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation
di: Vobecky, Antonin, et al.
Pubblicazione: (2022)

POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images
di: Vobecky, Antonin, et al.
Pubblicazione: (2024)

Coevolving Representations in Joint Image-Feature Diffusion
di: Kouzelis, Theodoros, et al.
Pubblicazione: (2026)

Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction
di: Karypidis, Efstathios, et al.
Pubblicazione: (2026)

SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers
di: Kakogeorgiou, Ioannis, et al.
Pubblicazione: (2023)

Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs
di: Shukor, Mustafa, et al.
Pubblicazione: (2024)

Learning to Generate Training Datasets for Robust Semantic Segmentation
di: Hariat, Marwane, et al.
Pubblicazione: (2023)

Self-Masking Networks for Unsupervised Adaptation
di: Warmerdam, Alfonso Taboada, et al.
Pubblicazione: (2024)

Improving Visual Grounding by Encouraging Consistent Gradient-based Explanations
di: Yang, Ziyan, et al.
Pubblicazione: (2022)

Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Survey
di: Siméoni, Oriane, et al.
Pubblicazione: (2023)

Can Generative Models Improve Self-Supervised Representation Learning?
di: Ayromlou, Sana, et al.
Pubblicazione: (2024)

Three Pillars improving Vision Foundation Model Distillation for Lidar
di: Puy, Gilles, et al.
Pubblicazione: (2023)

Improving Resnet-9 Generalization Trained on Small Datasets
di: Awad, Omar Mohamed, et al.
Pubblicazione: (2023)

T-MARS: Improving Visual Representations by Circumventing Text Feature Learning
di: Maini, Pratyush, et al.
Pubblicazione: (2023)

Controlled Training Data Generation with Diffusion Models
di: Yeo, Teresa, et al.
Pubblicazione: (2024)

ProFeAT: Projected Feature Adversarial Training for Self-Supervised Learning of Robust Representations
di: Addepalli, Sravanti, et al.
Pubblicazione: (2024)

Self-Supervised Visual Preference Alignment
di: Zhu, Ke, et al.
Pubblicazione: (2024)

LatentExplainer: Explaining Latent Representations in Deep Generative Models with Multimodal Large Language Models
di: Zhu, Mengdan, et al.
Pubblicazione: (2024)

Significance-Gain Pair Encoding for LLMs: A Statistical Alternative to Frequency-Based Subword Merging
di: Nouri, Azam
Pubblicazione: (2026)

C2-Evo: Co-Evolving Multimodal Data and Model for Self-Improving Reasoning
di: Chen, Xiuwei, et al.
Pubblicazione: (2025)

Frozen Transformers in Language Models Are Effective Visual Encoder Layers
di: Pang, Ziqi, et al.
Pubblicazione: (2023)

FLOSS: Free Lunch in Open-vocabulary Semantic Segmentation
di: Benigmim, Yasser, et al.
Pubblicazione: (2025)

Domain Adaptation with a Single Vision-Language Embedding
di: Fahes, Mohammad, et al.
Pubblicazione: (2024)

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents
di: Xiao, Han, et al.
Pubblicazione: (2025)

COAP: Memory-Efficient Training with Correlation-Aware Gradient Projection
di: Xiao, Jinqi, et al.
Pubblicazione: (2024)

Self-Distillation of Hidden Layers for Self-Supervised Representation Learning
di: Lowe, Scott C., et al.
Pubblicazione: (2026)

Gradient descent with generalized Newton's method
di: Bu, Zhiqi, et al.
Pubblicazione: (2024)

Federated Learning with a Single Shared Image
di: Soni, Sunny, et al.
Pubblicazione: (2024)

Unsupervised Parameter Efficient Source-free Post-pretraining
di: Jha, Abhishek, et al.
Pubblicazione: (2025)

CROC: Evaluating and Training T2I Metrics with Pseudo- and Human-Labeled Contrastive Robustness Checks
di: Leiter, Christoph, et al.
Pubblicazione: (2025)

Classifier-guided Gradient Modulation for Enhanced Multimodal Learning
di: Guo, Zirun, et al.
Pubblicazione: (2024)

Semantic Prompt Learning for Weakly-Supervised Semantic Segmentation
di: Lin, Ci-Siang, et al.
Pubblicazione: (2024)