Composing two optical flows to supervise a third yields an architecture-agnostic geometric training constraint that consistently improves optical flow across supervised, unsupervised, and transfer settings.
In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
A sequential-to-global SSL method based on DINO pretrains iterative foveal-inspired vision transformers to achieve competitive ImageNet-1K performance with constant compute regardless of input resolution.
MEPA adds token-routed MoE and residual self-supervised feature alignment to VAR models, reporting better FID on ImageNet 256x256 with half the training epochs and fewer parameters than dense baselines.
Neural networks trained via supervised contrastive learning yield feature attributions that are more faithful, less complex, and more continuous than those from cross-entropy trained networks.
T-DuMpRa fuses classifier outputs with cosine-matched multi-prototypes from a teacher model via conservative gating, yielding 0.21-2.69% gains on skin lesion datasets across five backbones.
citing papers explorer
-
Triangular Consistency as a Universal Constraint for Learning Optical Flow
Composing two optical flows to supervise a third yields an architecture-agnostic geometric training constraint that consistently improves optical flow across supervised, unsupervised, and transfer settings.
-
Self-supervised pretraining for an iterative image size agnostic vision transformer
A sequential-to-global SSL method based on DINO pretrains iterative foveal-inspired vision transformers to achieve competitive ImageNet-1K performance with constant compute regardless of input resolution.
-
MEPA: Multi-Scale Representation Alignment for Visual Autoregressive Modeling with Mixture of Experts
MEPA adds token-routed MoE and residual self-supervised feature alignment to VAR models, reporting better FID on ImageNet 256x256 with half the training epochs and fewer parameters than dense baselines.
-
On the Properties of Feature Attribution for Supervised Contrastive Learning
Neural networks trained via supervised contrastive learning yield feature attributions that are more faithful, less complex, and more continuous than those from cross-entropy trained networks.
-
T-DuMpRa: Teacher-guided Dual-path Multi-prototype Retrieval Augmented framework for fine-grained medical image classification
T-DuMpRa fuses classifier outputs with cosine-matched multi-prototypes from a teacher model via conservative gating, yielding 0.21-2.69% gains on skin lesion datasets across five backbones.