paper-with-me

Exemplar-Free Counting 벤치마크

Exemplar-Free Counting on FSC147

9개 결과 · ⬇ CSV · JSON

MAE(test) 낮을수록 좋음

8.92 14.76 20.59 26.43 32.27 2021-04 2026-09 FamNet — 32.27 (2021-04-16) RepRPN-Counter — 26.66 (2022-01-05) RCC — 17.12 (2022-05-20) CounTR — 14.71 (2022-08-29) LOCA — 16.2 (2022-11-15) DAVE — 15.14 (2024-04-25) GCA-SUN — 14.0 (2024-09-18) GeCo — 13.3 (2024-09-27) SAVE — 8.92 (2025-02-10) FamNet — 32.27 (2021-04-16) RepRPN-Counter — 26.66 (2022-01-05) RCC — 17.12 (2022-05-20) CounTR — 14.71 (2022-08-29) GCA-SUN — 14.0 (2024-09-18) GeCo — 13.3 (2024-09-27) SAVE — 8.92 (2025-02-10)
RankModel MAE(test)RMSE(test)MAE(val)RMSE(val) PaperCodeYear
1 SAVE 8.9280.398.8935.83 SAVE: Self-Attention on Visual Embedding for Zero-Shot Generic Object Counting AhmedZgaren/Save 2025
2 GeCo 13.30108.7214.8164.95 A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation jerpelhan/GeCo 2024
3 GCA-SUN 14.0092.1916.0653.04 GCA-SUNet: A Gated Context-Aware Swin-UNet for Exemplar-Free Counting 2024
4 CounTR 14.71106.8718.0771.84 CounTR: Transformer-based Generalised Visual Counting Verg-Avesta/CounTR 2022
5 DAVE 15.14103.4915.5452.67 DAVE -- A Detect-and-Verify Paradigm for Low-Shot Counting jerpelhan/dave 2024
6 LOCA 16.2103.9617.4354.96 A Low-Shot Object Counting Network With Iterative Prototype Adaptation djukicn/loca 2022
7 RCC 17.12104.5317.4958.81 Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervision SinicaGroup/Class-agnostic-Few-shot-Object-Counting · activevisionlab/learningtocountanything 2022
8 RepRPN-Counter 26.66129.1129.2498.11 Exemplar-free Class Incremental Learning via Discriminative and Comparable One-class Classifiers SunWenJu123/DCPOC 2022
9 FamNet 32.27131.4632.1598.75 Learning To Count Everything cvlab-stonybrook/LearningToCountEverything 2021
1–9 / 9 페이지당 10 20 50 100