AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

ForestHash: Semantic Hashing With Shallow Random Forests and Tiny Convolutional Networks

Qiang Qiu, Jose Lezama, Alex Bronstein, Guillermo Sapiro

ECCV 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 8 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add unsupervised information-theoretic code aggregation instead of random aggregation (ablation)ForestHash · CIFAR-10 retrieval (reduced training, 48-bit, radius 0)precision (%): 31.37 -> 34.02Improved
add supervised information-theoretic aggregation instead of random aggregation (ablation)ForestHash · CIFAR-10 retrieval (reduced training, 48-bit, radius 0)precision (%): 31.37 -> 33.86Improved
add semi-supervised aggregation instead of random aggregation (ablation)ForestHash · CIFAR-10 retrieval (reduced training, 48-bit, radius 0)precision (%): 31.37 -> 34.05Improved
add semi-supervised aggregation instead of random aggregation (ablation)ForestHash · CIFAR-10 retrieval (reduced training, 48-bit, radius 0)recall (%): 2.74 -> 4.12Improved
add semi-supervised instead of unsupervised aggregation (ablation)ForestHash · CIFAR-10 retrieval (reduced training, 48-bit, radius <= 2)precision (%): 34.55 -> 33.73Mixed
add low-rank loss instead of softmax loss only (ablation)ForestHash CNN4 · CIFAR-10 retrieval (reduced training, 48-bit, radius 0)precision (%): 22.72 -> 28.66Improved
add low-rank loss instead of softmax loss only (ablation)ForestHash CNN2 · CIFAR-10 retrieval (reduced training, 48-bit, radius 0)precision (%): 23.00 -> 29.30Improved
use more complex CNN4 learner instead of CNN2 under reduced training (ablation)ForestHash · CIFAR-10 retrieval (reduced training, 48-bit, radius 0)precision (%): 29.30 -> 28.66No clear effect
use CNN4 instead of CNN2 learner with full training set (ablation)ForestHash · CIFAR-10 retrieval (50k train, official split), 48-bitmAP: 0.80 -> 0.84Improved
use VGG16 instead of CNN4 learner with full training set (ablation)ForestHash · CIFAR-10 retrieval (50k train, official split), 48-bitmAP: 0.84 -> 0.89Improved
embed light-weight CNN2 weak learner instead of RBF kernel learner (ablation)ForestHash · MNIST retrieval (36-bit, radius 0), 6,000 samples per classprecision (%): 86.53 -> 97.99Improved
embed light-weight CNN2 weak learner instead of RBF kernel learner (ablation)ForestHash · MNIST retrieval (36-bit, radius 0), 30 samples per classprecision (%): 79.38 -> 89.56Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy