No article text was recorded for this version.
cross-task generalization (dense prediction adaptation)
Version 1 of 1974 papers975 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection
- Blog: ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation
- Blog: Cross-Layer Attentive Feature Upsampling for Low-latency Semantic Segmentation
- Blog: Convolutional Neural Networks With Alternately Updated Clique
- Blog: MedKAN: An Advanced Kolmogorov-Arnold Network for Medical Image Classification
- Blog: Correlation-aware Adversarial Domain Adaptation and Generalization
- Blog: Deep High-Resolution Representation Learning for Human Pose Estimation
- Blog: Spatio-Temporal Representation Factorization for Video-based Person Re-Identification
- Blog: Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective
- Blog: Explicitly Modeling the Discriminability for Instance-Aware Visual Object Tracking
- Blog: Progressive Conditioned Scale-Shift Recalibration of Self-Attention for Online Test-time Adaptation
- Blog: EntAugment: Entropy-Driven Adaptive Data Augmentation Framework for Image Classification
- Blog: Faithful Label-free Knowledge Distillation
- Blog: Model-Agnostic Hierarchical Attention for 3D Object Detection
- Blog: Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence
- Blog: Semi-Supervised Training of Structured Output Neural Networks with an Adversarial Loss
- Blog: LocalBins: Improving Depth Estimation by Learning Local Distributions
- Blog: Self-Supervised Noisy Label Learning for Source-Free Unsupervised Domain Adaptation
- Blog: Multi-channel Deep Supervision for Crowd Counting
- Blog: Towards Self-similarity Consistency and Feature Discrimination for Unsupervised Domain Adaptation
- Blog: GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model
- Blog: Step Out and Seek Around: On Warm-Start Training with Incremental Data
- Blog: Unsupervised Visual Domain Adaptation: A Deep Max-Margin Gaussian Process Approach
- Blog: CoAtNet: Marrying Convolution and Attention for All Data Sizes
- Blog: Role-Wise Data Augmentation for Knowledge Distillation
- Blog: Local Relation Networks for Image Recognition
- Blog: VCC-INFUSE: Towards Accurate and Efficient Selection of Unlabeled Examples in Semi-supervised Learning
- Blog: Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction
- Blog: A Good Student is Cooperative and Reliable: CNN-Transformer Collaborative Learning for Semantic Segmentation
- Blog: Bridging the Gap between Classification and Localization for Weakly Supervised Object Localization
- Blog: Universal Semi-Supervised Semantic Segmentation
- Blog: Super-Resolution for Monocular Depth Estimation With Multi-Scale Sub-Pixel Convolutions and a Smoothness Constraint
- Blog: Towards Self-Adaptive Pseudo-Label Filtering for Semi-Supervised Learning
- Blog: Graph-based Asynchronous Event Processing for Rapid Object Recognition
- Blog: Context-aware Dynamic Block
- Blog: Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspective
- Blog: Receptive Field Broadening and Boosting for Salient Object Detection
- Blog: Semi-supervised Vision Transformers at Scale
- Blog: Dynamic Spatial Propagation Network for Depth Completion
- Blog: Unadversarial Examples: Designing Objects for Robust Vision
- Blog: SegBlocks: Block-Based Dynamic Resolution Networks for Real-Time Segmentation
- Blog: Video-to-Task Learning via Motion-Guided Attention for Few-Shot Action Recognition
- Blog: Distill on the Go: Online knowledge distillation in self-supervised learning
- Blog: CvT: Introducing Convolutions to Vision Transformers
- Blog: Feature boosting with efficient attention for scene parsing
- Blog: Domain Generalization via Inference-time Label-Preserving Target Projections
- Blog: Un-Mixing Test-Time Normalization Statistics: Combatting Label Temporal Correlation
- Blog: Receptive Field Block Net for Accurate and Fast Object Detection
- Blog: Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization
- Blog: CellMix: A General Instance Relationship based Method for Data Augmentation Towards Pathology Image Analysis
- Blog: Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform
- Blog: Amortized Learning of Dynamic Feature Scaling for Image Segmentation
- Blog: KITE: A Kernel-based Improved Transferability Estimation Method
- Blog: Deeper Insights into ViTs Robustness towards Common Corruptions
- Blog: Style-Pro: Style-Guided Prompt Learning for Generalizable Vision-Language Models
- Blog: AMD: Automatic Multi-step Distillation of Large-scale Vision Models
- Blog: AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition
- Blog: Semi-Supervised Heterogeneous Domain Adaptation: Theory and Algorithms
- Blog: DRIVE: Dual-Robustness via Information Variability and Entropic Consistency in Source-Free Unsupervised Domain Adaptation
- Blog: SCFI-ESeg: Enhancing Semantic Segmentation with Spatial and Content Feature Integration
Showing 60 of 974 papers.
History & citation
Current · Permanent link
- Adapting Efficient Vision Models for Dense Prediction merged into this direction (55% overlap)
- Spatial and Structural Priors for Dense Visual Tasks merged into this direction (59% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_cross_task_generalization_dense_predicti_fbec0661,
title = {cross-task generalization (dense prediction adaptation)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cross-task-generalization-dense-prediction-adaptation/rdr_fbec0661944244d7b639b7708c1b9c3a},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_cross_task_generalization_dense_predicti_fbec0661_v1,
title = {cross-task generalization (dense prediction adaptation)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cross-task-generalization-dense-prediction-adaptation/rdr_fbec0661944244d7b639b7708c1b9c3a/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}