# Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?

arXiv: https://arxiv.org/abs/2012.06166 · HTML: https://mlsanity.com/paper/2012.06166/

## Key facts

- Cited by 135 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Dec 2020.

## Built on by (most cited first, 30 of 135)

- [Language-driven Semantic Segmentation](https://mlsanity.com/paper/2201.03546/) (2022)
- [Image Segmentation Using Text and Image Prompts](https://mlsanity.com/paper/2112.10003/) (2021)
- [Hypercorrelation Squeeze for Few-Shot Segmentation](https://mlsanity.com/paper/2104.01538/) (2021)
- [Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation](https://mlsanity.com/paper/2207.10866/) (2022)
- [Self-Support Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2207.11549/) (2022)
- [Hierarchical Dense Correlation Distillation for Few-Shot Segmentation](https://mlsanity.com/paper/2303.14652/) (2023)
- [VRP-SAM: SAM with Visual Reference Prompt](https://mlsanity.com/paper/2402.17726/) (2024)
- [Mining Latent Classes for Few-shot Segmentation](https://mlsanity.com/paper/2103.15402/) (2021)
- [Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation](https://mlsanity.com/paper/2207.08549/) (2022)
- [Feature-Proxy Transformer for Few-Shot Segmentation](https://mlsanity.com/paper/2210.06908/) (2022)
- [Learning Non-target Knowledge for Few-shot Semantic Segmentation](https://mlsanity.com/paper/2205.04903/) (2022)
- [LLaFS: When Large Language Models Meet Few-Shot Segmentation](https://mlsanity.com/paper/2311.16926/) (2023)
- [Source-Free Domain Adaptation for Image Segmentation](https://mlsanity.com/paper/2108.03152/) (2021)
- [Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2204.10638/) (2022)
- [Open-vocabulary Semantic Segmentation with Frozen Vision-Language Models](https://mlsanity.com/paper/2210.15138/) (2022)
- [Parametric Information Maximization for Generalized Category Discovery](https://mlsanity.com/paper/2212.00334/) (2022)
- [Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2210.06780/) (2022)
- [Few-shot Segmentation with Optimal Transport Matching and Message Flow](https://mlsanity.com/paper/2108.08518/) (2021)
- [Bridge the Points: Graph-based Few-shot Segment Anything Semantically](https://mlsanity.com/paper/2410.06964/) (2024)
- [Few-shot Image Generation via Adaptation-Aware Kernel Modulation](https://mlsanity.com/paper/2210.16559/) (2022)
- [PFENet++: Boosting Few-shot Semantic Segmentation with the Noise-filtered Context-aware Prior Mask](https://mlsanity.com/paper/2109.13788/) (2021)
- [Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Mining](https://mlsanity.com/paper/2401.08407/) (2024)
- [APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2406.08372/) (2024)
- [Integrative Few-Shot Learning for Classification and Segmentation](https://mlsanity.com/paper/2203.15712/) (2022)
- [Interclass Prototype Relation for Few-Shot Segmentation](https://mlsanity.com/paper/2211.08681/) (2022)
- [Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentation](https://mlsanity.com/paper/2307.03407/) (2023)
- [Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentation](https://mlsanity.com/paper/2208.00306/) (2022)
- [A Strong Baseline for Generalized Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2211.14126/) (2022)
- [Mask Matching Transformer for Few-Shot Segmentation](https://mlsanity.com/paper/2301.01208/) (2022)
- [FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network](https://mlsanity.com/paper/2301.08160/) (2023)

## Abstract (arXiv)

We show that the way inference is performed in few-shot segmentation tasks has a substantial effect on performances -- an aspect often overlooked in the literature in favor of the meta-learning paradigm. We introduce a transductive inference for a given query image, leveraging the statistics of its unlabeled pixels, by optimizing a new loss containing three complementary terms: i) the cross-entropy on the labeled support pixels; ii) the Shannon entropy of the posteriors on the unlabeled query-image pixels; and iii) a global KL-divergence regularizer based on the proportion of the predicted foreground. As our inference uses a simple linear classifier of the extracted features, its computational load is comparable to inductive inference and can be used on top of any base training. Foregoing episodic training and using only standard cross-entropy training on the base classes, our inference yields competitive performances on standard benchmarks in the 1-shot scenarios. As the number of available shots increases, the gap in performances widens: on PASCAL-5i, our method brings about 5% and 6% improvements over the state-of-the-art, in the 5- and 10-shot scenarios, respectively. Furthermore, we introduce a new setting that includes domain shifts, where the base and novel classes are drawn from different datasets. Our method achieves the best performances in this more realistic setting. Our code is freely available online: https://github.com/mboudiaf/RePRI-for-Few-Shot-Segmentation.