Copertina

You Don't Need Domain-Specific Data Augmentations When Scaling Self-Supervised Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Moutakanni, Théo, Oquab, Maxime, Szafraniec, Marc, Vakalopoulou, Maria, Bojanowski, Piotr
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach
di: Vo, Huy V., et al.
Pubblicazione: (2024)

Vision Transformers Need Registers
di: Darcet, Timothée, et al.
Pubblicazione: (2023)

Advancing human-centric AI for robust X-ray analysis through holistic self-supervised learning
di: Moutakanni, Théo, et al.
Pubblicazione: (2024)

DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment
di: Jose, Cijo, et al.
Pubblicazione: (2024)

Cluster and Predict Latent Patches for Improved Masked Image Modeling
di: Darcet, Timothée, et al.
Pubblicazione: (2025)

Efficient Universal Perception Encoder
di: Zhu, Chenchen, et al.
Pubblicazione: (2026)

DINOv2: Learning Robust Visual Features without Supervision
di: Oquab, Maxime, et al.
Pubblicazione: (2023)

Towards domain-invariant Self-Supervised Learning with Batch Styles Standardization
di: Scalbert, Marin, et al.
Pubblicazione: (2023)

NeIn: Telling What You Don't Want
di: Bui, Nhat-Tan, et al.
Pubblicazione: (2024)

Back to the Features: DINO as a Foundation for Video World Models
di: Baldassarre, Federico, et al.
Pubblicazione: (2025)

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models
di: Zhao, Kairan, et al.
Pubblicazione: (2026)

DINOv3
di: Siméoni, Oriane, et al.
Pubblicazione: (2025)

Vision Transformers Don't Need Trained Registers
di: Jiang, Nick, et al.
Pubblicazione: (2025)

Visually Dehallucinative Instruction Generation: Know What You Don't Know
di: Cha, Sungguk, et al.
Pubblicazione: (2024)

Don't Judge Before You CLIP: A Unified Approach for Perceptual Tasks
di: Zalcher, Amit, et al.
Pubblicazione: (2025)

Get What You Want, Not What You Don't: Image Content Suppression for Text-to-Image Diffusion Models
di: Li, Senmao, et al.
Pubblicazione: (2024)

Now You See It, Now You Don't - Instant Concept Erasure for Safe Text-to-Image and Video Generation
di: Biswas, Shristi Das, et al.
Pubblicazione: (2025)

Now You See Me, Now You Don't: A Unified Framework for Expression Consistent Anonymization in Talking Head Videos
di: Egin, Anil, et al.
Pubblicazione: (2026)

If At First You Don't Succeed: Test Time Re-ranking for Zero-shot, Cross-domain Retrieval
di: Hudson, Finlay G. C., et al.
Pubblicazione: (2023)

Rethinking Deep Clustering Paradigms: Self-Supervision Is All You Need
di: Shaheena, Amal, et al.
Pubblicazione: (2025)

You Only Need Half: Boosting Data Augmentation by Using Partial Content
di: Hu, Juntao, et al.
Pubblicazione: (2024)

Information Maximization for Long-Tailed Semi-Supervised Domain Generalization
di: Fillioux, Leo, et al.
Pubblicazione: (2026)

Better (pseudo-)labels for semi-supervised instance segmentation
di: Porcher, François, et al.
Pubblicazione: (2024)

Efficient Building Roof Type Classification: A Domain-Specific Self-Supervised Approach
di: Mutreja, Guneet, et al.
Pubblicazione: (2025)

The Geometry of Noise: Why Diffusion Models Don't Need Noise Conditioning
di: Sahraee-Ardakan, Mojtaba, et al.
Pubblicazione: (2026)

Pixels Don't Lie (But Your Detector Might): Bootstrapping MLLM-as-a-Judge for Trustworthy Deepfake Detection and Reasoning Supervision
di: Kuckreja, Kartik, et al.
Pubblicazione: (2026)

World Models That Know When They Don't Know - Controllable Video Generation with Calibrated Uncertainty
di: Mei, Zhiting, et al.
Pubblicazione: (2025)

Bridging Domain Gap of Point Cloud Representations via Self-Supervised Geometric Augmentation
di: Yu, Li, et al.
Pubblicazione: (2024)

Don't Reach for the Stars: Rethinking Topology for Resilient Federated Learning
di: Konstantin, Mirko, et al.
Pubblicazione: (2025)

Large Self-Supervised Models Bridge the Gap in Domain Adaptive Object Detection
di: Lavoie, Marc-Antoine, et al.
Pubblicazione: (2025)

Fairness and Robustness of CLIP-Based Models for Chest X-rays
di: Sourget, Théo, et al.
Pubblicazione: (2025)

AdvDINO: Domain-Adversarial Self-Supervised Representation Learning for Spatial Proteomics
di: Su, Stella, et al.
Pubblicazione: (2025)

Show, Don't Tell: Morphing Latent Reasoning into Image Generation
di: Chen, Harold Haodong, et al.
Pubblicazione: (2026)

Don't Pause! Every prediction matters in a streaming video
di: Chatterjee, Dibyadip, et al.
Pubblicazione: (2026)

Don't Look into the Dark: Latent Codes for Pluralistic Image Inpainting
di: Chen, Haiwei, et al.
Pubblicazione: (2024)

When Text and Images Don't Mix: Bias-Correcting Language-Image Similarity Scores for Anomaly Detection
di: Goodge, Adam, et al.
Pubblicazione: (2024)

When Better Teachers Don't Make Better Students: Revisiting Knowledge Distillation for CLIP Models in VQA
di: Tuchinda, Pume, et al.
Pubblicazione: (2025)

Transferable-guided Attention Is All You Need for Video Domain Adaptation
di: Sacilotti, André, et al.
Pubblicazione: (2024)

Don't let the information slip away
di: Li, Taozhe, et al.
Pubblicazione: (2026)

Controllable Latent Space Augmentation for Digital Pathology
di: Boutaj, Sofiène, et al.
Pubblicazione: (2025)