Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2305.04276 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914713564086272 |
|---|---|
| author | Lin, Jiacheng Chen, Jiajun Yang, Kailun Roitberg, Alina Li, Siyu Li, Zhiyong Li, Shutao |
| author_facet | Lin, Jiacheng Chen, Jiajun Yang, Kailun Roitberg, Alina Li, Siyu Li, Zhiyong Li, Shutao |
| contents | Interactive Image Segmentation (IIS) has emerged as a promising technique for decreasing annotation time. Substantial progress has been made in pre- and post-processing for IIS, but the critical issue of interaction ambiguity, notably hindering segmentation quality, has been under-researched. To address this, we introduce AdaptiveClick -- a click-aware transformer incorporating an adaptive focal loss that tackles annotation inconsistencies with tools for mask- and pixel-level ambiguity resolution. To the best of our knowledge, AdaptiveClick is the first transformer-based, mask-adaptive segmentation framework for IIS. The key ingredient of our method is the Click-Aware Mask-adaptive transformer Decoder (CAMD), which enhances the interaction between click and image features. Additionally, AdaptiveClick enables pixel-adaptive differentiation of hard and easy samples in the decision space, independent of their varying distributions. This is primarily achieved by optimizing a generalized Adaptive Focal Loss (AFL) with a theoretical guarantee, where two adaptive coefficients control the ratio of gradient values for hard and easy pixels. Our analysis reveals that the commonly used Focal and BCE losses can be considered special cases of the proposed AFL. With a plain ViT backbone, extensive experimental results on nine datasets demonstrate the superiority of AdaptiveClick compared to state-of-the-art methods. The source code is publicly available at https://github.com/lab206/AdaptiveClick. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_04276 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | AdaptiveClick: Clicks-aware Transformer with Adaptive Focal Loss for Interactive Image Segmentation Lin, Jiacheng Chen, Jiajun Yang, Kailun Roitberg, Alina Li, Siyu Li, Zhiyong Li, Shutao Computer Vision and Pattern Recognition Artificial Intelligence Image and Video Processing Interactive Image Segmentation (IIS) has emerged as a promising technique for decreasing annotation time. Substantial progress has been made in pre- and post-processing for IIS, but the critical issue of interaction ambiguity, notably hindering segmentation quality, has been under-researched. To address this, we introduce AdaptiveClick -- a click-aware transformer incorporating an adaptive focal loss that tackles annotation inconsistencies with tools for mask- and pixel-level ambiguity resolution. To the best of our knowledge, AdaptiveClick is the first transformer-based, mask-adaptive segmentation framework for IIS. The key ingredient of our method is the Click-Aware Mask-adaptive transformer Decoder (CAMD), which enhances the interaction between click and image features. Additionally, AdaptiveClick enables pixel-adaptive differentiation of hard and easy samples in the decision space, independent of their varying distributions. This is primarily achieved by optimizing a generalized Adaptive Focal Loss (AFL) with a theoretical guarantee, where two adaptive coefficients control the ratio of gradient values for hard and easy pixels. Our analysis reveals that the commonly used Focal and BCE losses can be considered special cases of the proposed AFL. With a plain ViT backbone, extensive experimental results on nine datasets demonstrate the superiority of AdaptiveClick compared to state-of-the-art methods. The source code is publicly available at https://github.com/lab206/AdaptiveClick. |
| title | AdaptiveClick: Clicks-aware Transformer with Adaptive Focal Loss for Interactive Image Segmentation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Image and Video Processing |
| url | https://arxiv.org/abs/2305.04276 |