arXiv AI
Jul 16
Barnamala: Parameter-Efficient Handwritten Devanagari Recognition at Benchmark Saturation
arXiv:2607. 13689v1 Announce Type: cross Abstract: We built a compact convolutional network (1.
Barnamala: Parameter-Efficient Handwritten Devanagari Recognition at Benchmark Saturation
We built a compact convolutional network (1. 11 M parameters) for 46-class DHCD Devanagari recognition and reached 99.
Related stories
arXiv Machine Learning
Sep 16
Measuring Annotation Efficiency for Handwritten Devanagari Recognition: Sample-Complexity Curves for Four Pretraining Regimes
arXiv:2609.16859v1 Announce Type: cross Abstract: To train handwritten text recognition systems we need word images and their corresponding transcriptions, and these transcriptions are produced manua...
Hugging Face Trending Papers
Sep 15
Measuring Annotation Efficiency for Handwritten Devanagari Recognition: Sample-Complexity Curves for Four Pretraining Regimes
To train handwritten text recognition systems we need word images and their corresponding transcriptions, and these transcriptions are produced manually. For a script that can be read by only a small...
arXiv Machine Learning
Jun 2
A Closer Look at In-Distribution vs. Out-of-Distribution Accuracy for Open-Set Test-time Adaptation
arXiv:2606. 01973v1 Announce Type: new Abstract: Open-set test-time adaptation (TTA) updates models on new data in the presence of input shifts and unknown output classes.
arXiv AI
Aug 7
Toward Deployable Bangla Sign Language Recognition with Expert-Validated Data and a Lightweight Attention-Based Model
arXiv:2608. 06252v1 Announce Type: cross Abstract: Deaf and hard-of-hearing people in Bangladesh communicate mainly through Bangla Sign Language (BdSL).
arXiv AI
Jul 23
Decodable but Not Detectable: A Leakage Fingerprint for Near-OOD Benchmarks
arXiv:2607. 19393v1 Announce Type: cross Abstract: While auditing a perturbation-based OOD detector on a document benchmark, we recorded an AUROC of 0.
arXiv Machine Learning
Jul 14
Student Capacity Moderates Knowledge Distillation Effectiveness: A Systematic Study Across ResNet Teacher-Student Pairs on CIFAR-10
arXiv:2605. 31191v2 Announce Type: replace Abstract: We investigate how teacher-student capacity relationships modulate knowledge distillation (KD) effectiveness in ResNet-based image classification on CIFAR-10.
arXiv Computer Vision
Sep 2
Fi-ImageNet-1k: An OOD Benchmark From the Inside of the ImageNet-1k Validation Set
arXiv:2609.01027v1 Announce Type: new Abstract: Out-of-distribution (OOD) detection predicts whether a test image belongs to none of the predefined classes. To evaluate this task, benchmarks need ima...
arXiv Computer Vision
Oct 5
ViTok: Improving Dense Semantics in AM-RADIO-Style Multi-Teacher Distillation with PHI-S and Masked Image Modelling
The paper presents ViTok, a multi‑teacher distillation approach that combines SigLIP2 and DINOv3‑L to jointly preserve global recognition and dense semantics. By introducing split adaptor heads, asymmetric losses, teacher reweighting, masked image modeling, and PHI‑S feature balancing, the authors achieve higher ImageNet‑1K kNN accuracy and restore ADE20K segmentation performance to match the teacher. The study also reports negative findings, such as limited benefits from scaling to ImageNet22K and interference from additional teachers.
arXiv AI
Aug 20
OmniHandwritingOCR: A Diagnostic Benchmark for Evaluating Multimodal LLMs in Handwritten OCR Scenarios
OmniHandwritingOCR is a diagnostic benchmark designed to evaluate multimodal large language models (MLLMs) and OCR systems on handwritten text and mathematical expression recognition. It comprises 77.57K labeled images across six subtasks and twelve subsets, including a difficulty‑stratified multi‑line formula corpus that tests robustness to increasing structural complexity. The benchmark reveals that current systems perform poorly on complex multi‑line formulas, exhibit variable rankings across languages and formula settings, and sometimes hallucinate corrections that are not visually supported.
arXiv AI
Sep 7
Phase Transition Frequency as a Training Time Predictor of Test Accuracy in ResNets
The study investigates whether the number of discrete class‑separability jumps (phase transitions) observed during ResNet fine‑tuning can predict final test accuracy. Across 75 experiments on four benchmarks (CIFAR‑10, CIFAR‑100, TinyImageNet, CIFAR‑10‑C) and three ResNet variants, a strong negative correlation is found on standard i.i.d. datasets (r = −0.84 on CIFAR‑10, r = −0.87 on CIFAR‑100), while the correlation weakens under distributional stress. Additional analyses show that the transition count retains predictive power after controlling for architecture depth and outperforms other training‑curve signals on in‑distribution benchmarks, though it is dominated by other signals on stressed datasets.
arXiv Computer Vision
Sep 28
CSCWD: Cross-Scale Channel-wise Knowledge Distillation for Lightweight Tiny Object Detection on Edge Devices
The paper introduces Cross-Scale Channel-wise Knowledge Distillation (CSCWD), a training-time framework that transfers high‑resolution spatial representations from a YOLO11m‑P2 teacher to a lightweight YOLO11n student without changing the student’s inference architecture. CSCWD aligns teacher P2 features with student P3 while also applying same‑scale distillation at deeper pyramid levels, yielding a 2.92‑point mAP@0.5 improvement over the baseline and a 2.09‑point gain over same‑scale distillation alone. In zero‑shot tests on DUT‑Anti‑UAV and on a Raspberry Pi 5, the 2.58‑million‑parameter student reaches 50.32% mAP@0.5 at 82.32 ms latency (12.15 fps) with negligible runtime or memory increase.