arXiv Computer Vision
Hierarchical Feature-level Reverse Propagation for Post-Training Neural Networks
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
2d ago
Forward Target Propagation: A Forward-Only Approach to Global Error Credit Assignment via Local Losses
arXiv:2506.11030v2 Announce Type: replace-cross Abstract: Training neural networks has traditionally relied on backpropagation (BP), a gradient-based algorithm that, despite its widespread success, s...
arXiv Machine Learning
Jun 8
Inheritance Between Feedforward and Convolutional Networks via Model Projection
arXiv:2602. 06245v2 Announce Type: replace-cross Abstract: Neural-network techniques are often transferred across architecture families by analogy, but such transfer is valid only when the assumptions required by a technique are preserved.
arXiv AI
Aug 18
RRFC: Recursive Refinement via Feedback Conditioning for Iterative Image-to-Image Generation
arXiv:2608. 15694v1 Announce Type: cross Abstract: Conditional image-to-image generators are single-shot: they map input features to an output in one forward pass and treat it as final, with no opportunity to improve on it.
arXiv Computer Vision
Sep 7
Towards Robust Driving Perception: A Flexible Scale-Driven Family for Self-Supervised Monocular Depth Estimation
The paper introduces FlexDepth, a family of self‑supervised monocular depth estimation models designed for robust driving perception. FlexDepth uses a two‑stage static‑dynamic decoupled training strategy and a Scale‑Driven Decoder that selects components based on scale size, enabling efficient feature fusion and high‑precision depth maps. Experiments on driving benchmarks show state‑of‑the‑art performance across arbitrary scales with minimal computational cost, with the smallest model (Flex‑Nano) achieving 37.6 FPS on mobile devices.
arXiv Machine Learning
Jul 15
From Preimage Search To Source-Grounded Feature Inversion
arXiv:2607. 12526v1 Announce Type: new Abstract: Interpreting a neural network requires understanding what its internal features extract from a particular input.
arXiv Machine Learning
Aug 7
A neural operator view on U-Nets for inverse imaging problems
arXiv:2608. 05839v1 Announce Type: cross Abstract: Deep neural networks have shown great empirical success in the solution of a wide variety of ill-posed inverse problems in imaging.