AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Exploring Tuning Characteristics of Ventral Stream’s Neurons for Few-Shot Image Classification

Lintao Dong, Wei Zhai, Zheng-Jun Zha

AAAI 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot object detection

Read the paper

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
Apply HFR and foreground segmentationRENet and Distribution Calibration variants · CUB, miniImageNet, CIFAR-FS, and tieredImageNet; 5-way 1-shot and 5-shotaccuracy: RENet: +3.84, +1.86, +2.11, +1.65, +1.31, +0.85, +2.33, +1.87; LR-DC: +2.70, +1.93, +1.41, +1.34, +1.07, +0.74, +1.29, +Improved
Add shape-cue neuron regularization (ablation)RENet · CUB and miniImageNet 5-way 1-shotaccuracy: +1.27; +1.13Improved
Add color-cue neuron regularization after shape cues (ablation)RENet · CUB and miniImageNet 5-way 1-shotaccuracy: 80.83 (+1.27) -> 81.17 (+1.61); 68.73 (+1.13) -> 68.98 (+1.38)Improved
Add foreground segmentation for belongingness after shape and color cues (ablation)RENet · CUB and miniImageNet 5-way 1-shotaccuracy: 81.17 (+1.61) -> 82.26 (+2.70); 68.98 (+1.38) -> 69.71 (+2.11)Improved
Add V2 and V4 regularization after V1 regularization (ablation)RENet · CUB and miniImageNet 5-way 1-shotaccuracy: 81.76 (+2.27) -> 82.57 (+3.08) -> 83.14 (+3.65); 68.21 (+0.61) -> 68.67 (+1.07) -> 68.98 (+1.38)Improved
Reverse the V1→V2→V4 regularization order (ablation)RENet HFR · CUB and miniImageNet 5-way 1-shotaccuracy: 83.14 -> 82.17; 68.98 -> 68.34Hurt
Concatenate neuron responses with model input (ablation)RENet · CUB and miniImageNet 5-way 1-shotaccuracy: 79.49 -> 77.65; 67.60 -> 66.13Hurt
Concatenate neuron responses with features before the fully connected layer (ablation)RENet · CUB and miniImageNet 5-way 1-shotaccuracy: 79.49 -> 79.11; 67.60 -> 67.26Hurt
Transfer neuron-model knowledge by distillation (ablation)RENet · CUB and miniImageNet 5-way 1-shotaccuracy: 79.49 -> 81.01; 67.60 -> 68.14Improved
Use hierarchical feature regularization instead of distillation (ablation)RENet · CUB and miniImageNet 5-way 1-shotaccuracy: 81.01 -> 83.14; 68.14 -> 68.98Improved

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