mlsanityData to 7 Oct 2026

Target-aware Bi-Transformer for Few-shot Segmentation

arXiv 2309.09492 ↗First posted 18 Sep 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Traditional semantic segmentation tasks require a large number of labels and are difficult to identify unlearned categories. Few-shot semantic segmentation (FSS) aims to use limited labeled support images to identify the segmentation of new classes of objects, which is very practical in the real world. Previous researches were primarily based on prototypes or correlations. Due to colors, textures, and styles are similar in the same image, we argue that the query image can be regarded as its own support image. In this paper, we proposed the Target-aware Bi-Transformer Network (TBTNet) to equivalent treat of support images and query image. A vigorous Target-aware Transformer Layer (TTL) also be designed to distill correlations and force the model to focus on foreground information. It treats the hypercorrelation as a feature, resulting a significant reduction in the number of feature channels. Benefit from this characteristic, our model is the lightest up to now with only 0.4M learnable parameters. Futhermore, TBTNet converges in only 10% to 25% of the training epochs compared to traditional methods. The excellent performance on standard FSS benchmarks of PASCAL-5i and COCO-20i proves the efficiency of our method. Extensive ablation studies were also carried out to evaluate the effectiveness of Bi-Transformer architecture and TTL.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 28 references that are in the map. First posted on arXiv 18 Sep 2023.

Builds on

25 of 28 references.

References · 25

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  6. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  7. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  8. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  9. 2017One-Shot Learning for Semantic Segmentationcited by 337
  10. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  11. 2022Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labelscited by 218
  12. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
13 more
  1. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  2. 2018SG-One: Similarity Guidance Network for One-Shot Semantic Segmentationcited by 169
  3. 2014Simultaneous Detection and Segmentationcited by 158
  4. 2021Few-Shot Segmentation via Cycle-Consistent Transformercited by 133
  5. 2022Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentationcited by 114
  6. 2022Self-Support Few-Shot Semantic Segmentationcited by 96
  7. 2022Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentationcited by 65
  8. 2022Weakly Supervised Semantic Segmentation using Out-of-Distribution Datacited by 58
  9. 2021Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localizationcited by 46
  10. 2022Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentationcited by 37
  11. 2021Few-shot Segmentation with Optimal Transport Matching and Message Flowcited by 36
  12. 2022Integrative Few-Shot Learning for Classification and Segmentationcited by 25
  13. 2022Interclass Prototype Relation for Few-Shot Segmentationcited by 25

Built on by

Not cited yet.