The Shape of Events: Edge-Based Inductive Biases via Cross-Domain Distillation
cs.CV
Submitted: 2026-09-24
Updated: 2026-09-24
Code: https://github.com/snskysk/event2rgb-distillation
Terminology
Sources
- ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
- Event-based Vision: A Survey
- Benchmarking Neural Network Robustness to Common Corruptions and Perturbations
- Distilling the Knowledge in a Neural Network
- N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Cameras
- ImageNet Large Scale Visual Recognition Challenge
- PRED18: Dataset and Further Experiments with DAVIS Event Camera in Predator-Prey Robot Chasing
- EventCLIP: Adapting CLIP for Event-based Object Recognition
- Adaptive Event Stream Slicing for Open-Vocabulary Event-Based Object Detection via Vision-Language Knowledge Distillation
- Towards Video Anomaly Detection from Event Streams: A Baseline and Benchmark Datasets
- Deep Residual Learning for Image Recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- A ConvNet for the 2020s
- Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs
- Understanding intermediate layers using linear classifier probes
- Learning Robust Global Representations by Penalizing Local Predictive Power
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Decoupled Weight Decay Regularization
- SGDR: Stochastic Gradient Descent with Warm Restarts
- mixup: Beyond Empirical Risk Minimization
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models