Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userA Self-Distillation Embedded Supervised Affinity Attention Model for Few-Shot Segmentation
131
0
0.0
(
0
)
Added by
Binghao Liu
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Few-shot semantic segmentation is a challenging task of predicting object categories in pixel-wise with only few annotated samples. However, existing approaches still face two main challenges. First, huge feature distinction between support and query images causes knowledge transferring barrier, which harms the segmentation performance. Second, few support samples cause unrepresentative of support features, hardly to guide high-quality query segmentation. To deal with the above two issues, we propose self-distillation embedded supervised affinity attention model (SD-AANet) to improve the performance of few-shot segmentation task. Specifically, the self-distillation guided prototype module (SDPM) extracts intrinsic prototype by self-distillation between support and query to capture representative features. The supervised affinity attention module (SAAM) adopts support ground truth to guide the production of high quality query attention map, which can learn affinity information to focus on whole area of query target. Extensive experiments prove that our SD-AANet significantly improves the performance comparing with existing methods. Comprehensive ablation experiments and visualization studies also show the significant effect of SDPM and SAAM for few-shot segmentation task. On benchmark datasets, PASCAL-5i and COCO-20i, our proposed SD-AANet both achieve state-of-the-art results. Our code will be publicly available soon.
rate research
Read More
Few-shot segmentation aims at assigning a category label to each image pixel with few annotated samples. It is a challenging task since the dense prediction can only be achieved under the guidance of latent features defined by sparse annotations. Existing meta-learning method tends to fail in generating category-specifically discriminative descriptor when the visual features extracted from support images are marginalized in embedding space. To address this issue, this paper presents an adaptive tuning framework, in which the distribution of latent features across different episodes is dynamically adjusted based on a self-segmentation scheme, augmenting category-specific descriptors for label prediction. Specifically, a novel self-supervised inner-loop is firstly devised as the base learner to extract the underlying semantic features from the support image. Then, gradient maps are calculated by back-propagating self-supervised loss through the obtained features, and leveraged as guidance for augmenting the corresponding elements in embedding space. Finally, with the ability to continuously learn from different episodes, an optimization-based meta-learner is adopted as outer loop of our proposed framework to gradually refine the segmentation results. Extensive experiments on benchmark PASCAL-$5^{i}$ and COCO-$20^{i}$ datasets demonstrate the superiority of our proposed method over state-of-the-art.
Weakly supervised semantic segmentation is receiving great attention due to its low human annotation cost. In this paper, we aim to tackle bounding box supervised semantic segmentation, i.e., training accurate semantic segmentation models using bounding box annotations as supervision. To this end, we propose Affinity Attention Graph Neural Network ($A^2$GNN). Following previous practices, we first generate pseudo semantic-aware seeds, which are then formed into semantic graphs based on our newly proposed affinity Convolutional Neural Network (CNN). Then the built graphs are input to our $A^2$GNN, in which an affinity attention layer is designed to acquire the short- and long- distance information from soft graph edges to accurately propagate semantic labels from the confident seeds to the unlabeled pixels. However, to guarantee the precision of the seeds, we only adopt a limited number of confident pixel seed labels for $A^2$GNN, which may lead to insufficient supervision for training. To alleviate this issue, we further introduce a new loss function and a consistency-checking mechanism to leverage the bounding box constraint, so that more reliable guidance can be included for the model optimization. Experiments show that our approach achieves new state-of-the-art performances on Pascal VOC 2012 datasets (val: 76.5%, test: 75.2%). More importantly, our approach can be readily applied to bounding box supervised instance segmentation task or other weakly supervised semantic segmentation tasks, with state-of-the-art or comparable performance among almot all weakly supervised tasks on PASCAL VOC or COCO dataset. Our source code will be available at https://github.com/zbf1991/A2GNN.
Weakly Supervised Object Detection (WSOD) has emerged as an effective tool to train object detectors using only the image-level category labels. However, without object-level labels, WSOD detectors are prone to detect bounding boxes on salient objects, clustered objects and discriminative object parts. Moreover, the image-level category labels do not enforce consistent object detection across different transformations of the same images. To address the above issues, we propose a Comprehensive Attention Self-Distillation (CASD) training approach for WSOD. To balance feature learning among all object instances, CASD computes the comprehensive attention aggregated from multiple transformations and feature layers of the same images. To enforce consistent spatial supervision on objects, CASD conducts self-distillation on the WSOD networks, such that the comprehensive attention is approximated simultaneously by multiple transformations and feature layers of the same images. CASD produces new state-of-the-art WSOD results on standard benchmarks such as PASCAL VOC 2007/2012 and MS-COCO.
Significant progress has been made recently in developing few-shot object segmentation methods. Learning is shown to be successful in few-shot segmentation settings, using pixel-level, scribbles and bounding box supervision. This paper takes another approach, i.e., only requiring image-level label for few-shot object segmentation. We propose a novel multi-modal interaction module for few-shot object segmentation that utilizes a co-attention mechanism using both visual and word embedding. Our model using image-level labels achieves 4.8% improvement over previously proposed image-level few-shot object segmentation. It also outperforms state-of-the-art methods that use weak bounding box supervision on PASCAL-5i. Our results show that few-shot segmentation benefits from utilizing word embeddings, and that we are able to perform few-shot segmentation using stacked joint visual semantic processing with weak image-level labels. We further propose a novel setup, Temporal Object Segmentation for Few-shot Learning (TOSFL) for videos. TOSFL can be used on a variety of public video data such as Youtube-VOS, as demonstrated in both instance-level and category-level TOSFL experiments.
Reducing the amount of supervision required by neural networks is especially important in the context of semantic segmentation, where collecting dense pixel-level annotations is particularly expensive. In this paper, we address this problem from a new perspective: Incremental Few-Shot Segmentation. In particular, given a pretrained segmentation model and few images containing novel classes, our goal is to learn to segment novel classes while retaining the ability to segment previously seen ones. In this context, we discover, against all beliefs, that fine-tuning the whole architecture with these few images is not only meaningful, but also very effective. We show how the main problems of end-to-end training in this scenario are i) the drift of the batch-normalization statistics toward novel classes that we can fix with batch renormalization and ii) the forgetting of old classes, that we can fix with regularization strategies. We summarize our findings with five guidelines that together consistently lead to the state of the art on the COCO and Pascal-VOC 2012 datasets, with different number of images per class and even with multiple learning episodes.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
