arXiv Machine Learning
JEDI: JEPA-to-Edge Distillation for Efficient Cropland Segmentation from Satellite Imagery
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Computer Vision
Aug 28
Cross-Architecture Knowledge Distillation from a Vision Foundation Model to a Lightweight Visual State Space Model for Tea Leaf Disease Classification
The paper presents a method for cross‑architecture knowledge distillation from a fine‑tuned DINOv2 Vision Transformer teacher to a lightweight bidirectional Visual State Space Model (LVSSM) student for tea leaf disease classification. By addressing training‑stability issues with a progressive convolutional stem and gated selective‑scan block, the 4.45 M‑parameter student achieves a mean test accuracy of 95.41%—a 3.09‑point improvement over the teacher’s 92.32%—while using only one‑fifth of the teacher’s parameters. Ablation studies show that simple logit‑level distillation outperforms intermediate feature alignment, and the gains are specific to students that start below the teacher’s performance.
arXiv AI
Jun 29
Gated Relational Alignment via Confidence-based Distillation for Efficient VLMs
arXiv:2601. 22709v5 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) achieve strong multimodal performance but are costly to deploy, and post-training quantization often causes significant accuracy loss.
arXiv Computer Vision
Oct 2
PixelDense: Dense Prediction as Representation Alignment for Pixel Diffusion
PixelDense introduces a dual‑stream representation alignment for pixel diffusion, separating semantic and geometric teachers (DINOv2, SAM2, Depth Anything v2, Metric3D v2) into distinct projection spaces with an orthogonality penalty. The method improves dense‑prediction benchmarks, boosting PixelGen‑XXL’s GenEval score from 0.7927 to 0.8093, achieving significant gains in panoptic quality and depth accuracy, and accelerating training from random initialization. It also enhances SDEdit editing by preserving background structure and increasing PSNR.
arXiv Computer Vision
Oct 16
Data-Efficient ConvNeXt Pretraining for High-Resolution Sentinel-1 GRD SAR Representation Learning
The paper introduces SparK-SAR, a sparse convolutional masked pretraining framework that leverages ConvNeXt for high‑resolution Sentinel‑1 GRD SAR data. It presents three key contributions: a domain‑adapted ConvNeXt‑RS encoder with a reduced stem stride, a lightweight ConvNeXt‑512 decoder that cuts VRAM usage while matching UNet accuracy, and an analysis of FP16 instability and layer‑wise learning‑rate decay benefits. Experiments on four Copernicus‑Bench S1GRD tasks show that the 27.8 M‑parameter ConvNeXt‑RS encoder outperforms a larger ViT baseline on most tasks and demonstrates strong data efficiency, with classification saturating at 10–25 % of the SSL4EO‑S12 corpus.
arXiv Machine Learning
Jul 22
KALE: Kernel Alignment with Loss Equilibration for Stable CLIP-DINOv2 Alignment at Web Scale
arXiv:2607. 18885v1 Announce Type: new Abstract: Kernel-based alignment of CLIP toward a vision centric teacher such as DINOv2 (KUEA) improves CLIP's visual representations while preserving text-encoder compatibility, using a fixed trade-off weight tuned on curated ImageNet-1K.
Hugging Face Trending Papers
Aug 11
Grid-Preserving Knowledge Distillation: Transferring Convolutional Inductive Bias to Vision Transformers under Data Scarcity
Vision Transformers underperform convolutional networks when training data is scarce, and distilling convolutional inductive biases from a CNN teacher is an effective remedy that leaves the deployed model unchanged. General-purpose feature distillation, however, transfers little in this setting.