No article text was recorded for this version.
pixel-level reconstruction bias
Version 2 of 2232 papers245 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Improving Pixel-based MIM by Reducing Wasted Modeling Capability
- Blog: Semantics-enhanced Cross-modal Masked Image Modeling for Vision-Language Pre-training
- Blog: An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-training
- Blog: BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers
- Blog: Locality and Compositionality in Zero-Shot Learning
- Blog: Improving Pixel-based MIM by Reducing Wasted Modeling Capability
- Blog: Locality and compositionality in zero-shot learning
- Blog: An Empirical Study into Clustering of Unseen Datasets with Self-Supervised Encoders
- Blog: Bootstrapped Masked Autoencoders for Vision BERT Pretraining
- Blog: How robust are pre-trained models to distribution shift?
- Blog: Reconstruction Target Matters in Masked Image Modeling for Cross-Domain Few-Shot Learning
- Blog: Unsupervised Deep Network Pretraining via Human Design
- Blog: SODA: Bottleneck Diffusion Models for Representation Learning
- Blog: Leveraging Hidden Structure in Self-Supervised Learning
- Blog: Understanding disentangling in β-VAE
- Blog: Bootstrap Segmentation Foundation Model under Distribution Shift via Object-Centric Learning
- Blog: Audio-JEPA: Joint-Embedding Predictive Architecture for Audio Representation Learning
- Blog: Context Encoders: Feature Learning by Inpainting
- Blog: EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
- Blog: PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers
- Blog: AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations Rather Than Data
- Blog: Learning Disentangled Representations via Mutual Information Estimation
- Blog: SemanticMIM: Marring Masked Image Modeling with Semantics Compression for General Visual Representation
- Blog: Class-Specific Semantic Reconstruction for Open Set Recognition
- Blog: MAMO: Fine-Grained Vision-Language Representations Learning with Masked Multimodal Modeling
- Blog: Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction
- Blog: OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning
- Blog: Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution Detection
- Blog: Wavelet-Driven Masked Image Modeling: A Path to Efficient Visual Representation
- Blog: Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better
- Blog: Pixology: Probing the Linguistic and Visual Capabilities of Pixel-based Language Models
- Blog: Unmasked Teacher: Towards Training-Efficient Video Foundation Models
- Blog: Reconstruction Target Matters in Masked Image Modeling for Cross-Domain Few-Shot Learning
- Blog: Separating common from salient patterns with Contrastive Representation Learning
- Blog: Next-Embedding Prediction Makes Strong Vision Learners
- Blog: PixMIM: Rethinking Pixel Reconstruction in Masked Image Modeling
- Blog: MILAN: Masked Image Pretraining on Language Assisted Representation
- Blog: Masked Image Modeling with Denoising Contrast
- Blog: Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning
- Blog: Seeing Beyond Words: Self-Supervised Visual Learning for Multimodal Large Language Models
- Blog: The Devil Is in the Frequency: Geminated Gestalt Autoencoder for Self-Supervised Visual Pre-training
- Blog: Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget
- Blog: Masked Image Modeling with Denoising Contrast
- Blog: SdAE: Self-distillated Masked Autoencoder
- Blog: Masked Channel Modeling Enables Vision Transformers to Learn Better Semantics
- Blog: Harnessing Text-to-Image Diffusion Models for Point Cloud Self-Supervised Learning
- Blog: Stare at What You See: Masked Image Modeling without Reconstruction
- Blog: Sample- and Parameter-Efficient Auto-Regressive Image Models
- Blog: DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving
- Blog: PatchGame: Learning to Signal Mid-level Patches in Referential Games
- Blog: Var-JEPA: A Variational Formulation of the Joint-Embedding Predictive Architecture – Bridging Predictive and Generative Self-Supervised Learning
- Blog: Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis
- Blog: Contrastive Self-Supervised Learning for Skeleton Action Recognition
- Blog: Moving Off-the-Grid: Scene-Grounded Video Representations
- Blog: Self-supervised learning of imaging and clinical signatures using a multimodal joint-embedding predictive architecture
- Blog: Unsupervised Outlier Detection via Transformation Invariant Autoencoder
- Blog: Robust outlier detection by de-biasing VAE likelihoods
- Blog: MVP: Multimodality-guided Visual Pre-training
- Blog: Understanding Masked Autoencoders via Hierarchical Latent Variable Models
- Blog: Rethinking the Objectives of Vector-Quantized Tokenizers for Image Synthesis
Showing 60 of 232 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_pixel_level_reconstruction_bias_d24b6e97,
title = {pixel-level reconstruction bias},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/pixel-level-reconstruction-bias/rdr_d24b6e9706a64d6d9f5bff45492e60f3},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 2, frozen text):
@misc{lacuna_pixel_level_reconstruction_bias_d24b6e97_v2,
title = {pixel-level reconstruction bias},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/pixel-level-reconstruction-bias/rdr_d24b6e9706a64d6d9f5bff45492e60f3/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-21},
}