Exploring and Exploiting Diversity for Image Segmentation
Semantic image segmentation is an important computer vision task that is difficult because it consists of both recognition and segmentation. The task is often cast as a structured output problem on an exponentially large output-space, which is typically modeled by a discrete probabilistic model. The best segmentation is found by inferring the Maximum a-Posteriori (MAP) solution over the output distribution defined by the model. Due to limitations in optimization, the model cannot be arbitrarily complex. This leads to a trade-off: devise a more accurate model that incorporates rich high-order interactions between image elements at the cost of inaccurate and possibly intractable optimization OR leverage a tractable model which produces less accurate MAP solutions but may contain high quality solutions as other modes of its output distribution. This thesis investigates the latter and presents a two stage approach to semantic segmentation. In the first stage a tractable segmentation model outputs a set of high probability segmentations from the underlying distribution that are not just minor perturbations of each other. Critically the output of this stage is a diverse set of plausible solutions and not just a single one. In the second stage, a discriminatively trained re-ranking model selects the best segmentation from this set. The re-ranking stage can use much more complex features than what could be tractably used in the segmentation model, allowing a better exploration of the solution space than simply returning the MAP solution. The formulation is agnostic to the underlying segmentation model (e.g. CRF, CNN, etc.) and optimization algorithm, which makes it applicable to a wide range of models and inference methods. Evaluation of the approach on a number of semantic image segmentation benchmark datasets highlight its superiority over inferring the MAP solution.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityImage SegmentationRe-RankingSegmentationSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Exploring Spatial Diversity for Region-based Active Learning
State-of-the-art methods for semantic segmentation are based on deep neural networks trained on large-scale labeled datasets. Acquiring such datasets would incur large annotation costs, especially for dense pixel-level p…
Semantic SegmentationActive LearningBeyond Semantic Image Segmentation : Exploring Efficient Inference in Video
We explore the efficiency of the CRF inference module beyond image level semantic segmentation. The key idea is to combine the best of two worlds of semantic co-labeling and exploiting more expressive models. Similar to …
Image SegmentationSegmentationSemantic SegmentationVideo Semantic SegmentationWeakly Supervised Semantic Segmentation with Boundary Exploration
Weakly supervised semantic segmentation with image-level labels has attracted a lot of attention recently because these labels are already available in most datasets. To obtain semantic segmentation under weak supervisio…
SegmentationSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic SegmentationBoosting Semi-Supervised Medical Image Segmentation via Masked Image Consistency and Discrepancy Learning
Semi-supervised learning is of great significance in medical image segmentation by exploiting unlabeled data. Among its strategies, the co-training framework is prominent. However, previous co-training studies predominan…
DecoderDiversityImage SegmentationMedical Image Segmentation+3Exploiting Knowledge Distillation for Few-Shot Image Generation
Few-shot image generation, which trains generative models on limited examples, is of practical importance. The existing pipeline is first pretraining a source model (which contains a generator and a discriminator) on a l…
DiversityImage GenerationKnowledge DistillationRelation