Rethinking Saliency-Guided Weakly-Supervised Semantic Segmentation
- URL: http://arxiv.org/abs/2404.00918v2
- Date: Tue, 2 Apr 2024 10:20:28 GMT
- Title: Rethinking Saliency-Guided Weakly-Supervised Semantic Segmentation
- Authors: Beomyoung Kim, Donghyun Kim, Sung Ju Hwang,
- Abstract summary: This paper presents a fresh perspective on the role of saliency maps in weakly-supervised semantic segmentation (WSSS)
We observe that the quality of the saliency map is a critical factor in saliency-guided WSSS approaches.
We introduce textttWSSS-BED, a standardized framework for conducting research under unified conditions.
- Score: 57.9703659407207
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This paper presents a fresh perspective on the role of saliency maps in weakly-supervised semantic segmentation (WSSS) and offers new insights and research directions based on our empirical findings. We conduct comprehensive experiments and observe that the quality of the saliency map is a critical factor in saliency-guided WSSS approaches. Nonetheless, we find that the saliency maps used in previous works are often arbitrarily chosen, despite their significant impact on WSSS. Additionally, we observe that the choice of the threshold, which has received less attention before, is non-trivial in WSSS. To facilitate more meaningful and rigorous research for saliency-guided WSSS, we introduce \texttt{WSSS-BED}, a standardized framework for conducting research under unified conditions. \texttt{WSSS-BED} provides various saliency maps and activation maps for seven WSSS methods, as well as saliency maps from unsupervised salient object detection models.
Related papers
- Rethinking Class Activation Maps for Segmentation: Revealing Semantic
Information in Shallow Layers by Reducing Noise [2.462953128215088]
A major limitation to the performance of the class activation maps is the small spatial resolution of the feature maps in the last layer of the convolutional neural network.
We propose a simple gradient-based denoising method to filter the noise by truncating the positive gradient.
Our proposed scheme can be easily deployed in other CAM-related methods, facilitating these methods to obtain higher-quality class activation maps.
arXiv Detail & Related papers (2023-08-04T03:04:09Z) - Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual
Recognition [57.08108545219043]
Recognizing novel sub-categories with scarce samples is an essential and challenging research topic in computer vision.
Existing literature addresses this challenge by employing local-based representation approaches.
This article proposes a novel model, Robust Saliency-aware Distillation (RSaD), for few-shot fine-grained visual recognition.
arXiv Detail & Related papers (2023-05-12T00:13:17Z) - An Alternative to WSSS? An Empirical Study of the Segment Anything Model
(SAM) on Weakly-Supervised Semantic Segmentation Problems [35.547433613976104]
The Segment Anything Model (SAM) has demonstrated exceptional performance and versatility.
This report explores the application of SAM in Weakly-Supervised Semantic (WSSS)
We adapt SAM as the pseudo-label generation pipeline given only the image-level class labels.
arXiv Detail & Related papers (2023-05-02T16:35:19Z) - Segment Anything in Non-Euclidean Domains: Challenges and Opportunities [133.49534701480914]
We explore a novel Segment Non-Euclidean Anything (SNA) paradigm that strives to develop foundation models that can handle the diverse range of graph data within the non-Euclidean domain.
We shed light on unique challenges that arise when applying the SA concept to graph analysis, which involves understanding the differences between the Euclidean and non-Euclidean domains from both the data and task perspectives.
We present several preliminary solutions to tackle the challenges of SNA and detail their corresponding limitations, along with several potential directions to pave the way for future SNA research.
arXiv Detail & Related papers (2023-04-23T10:01:34Z) - Plugin estimators for selective classification with out-of-distribution
detection [67.28226919253214]
Real-world classifiers can benefit from abstaining from predicting on samples where they have low confidence.
These settings have been the subject of extensive but disjoint study in the selective classification (SC) and out-of-distribution (OOD) detection literature.
Recent work on selective classification with OOD detection has argued for the unified study of these problems.
We propose new plugin estimators for SCOD that are theoretically grounded, effective, and generalise existing approaches.
arXiv Detail & Related papers (2023-01-29T07:45:17Z) - Benchmarking the Robustness of LiDAR Semantic Segmentation Models [78.6597530416523]
In this paper, we aim to comprehensively analyze the robustness of LiDAR semantic segmentation models under various corruptions.
We propose a new benchmark called SemanticKITTI-C, which features 16 out-of-domain LiDAR corruptions in three groups, namely adverse weather, measurement noise and cross-device discrepancy.
We design a robust LiDAR segmentation model (RLSeg) which greatly boosts the robustness with simple but effective modifications.
arXiv Detail & Related papers (2023-01-03T06:47:31Z) - Salient Object Detection for Point Clouds [13.852801615283747]
We present a novel view-dependent perspective of salient objects, reasonably reflecting the most eye-catching objects in point cloud scenarios.
We introduce PCSOD, the first dataset proposed for point cloud SOD consisting of 2,872 in-/out-door 3D views.
The proposed model can effectively analyze irregular and unordered points for detecting salient objects.
arXiv Detail & Related papers (2022-07-25T03:35:46Z) - Glimpse-Attend-and-Explore: Self-Attention for Active Visual Exploration [47.01485765231528]
Active visual exploration aims to assist an agent with a limited field of view to understand its environment based on partial observations.
We propose the Glimpse-Attend-and-Explore model which employs self-attention to guide the visual exploration instead of task-specific uncertainty maps.
Our model provides encouraging results while being less dependent on dataset bias in driving the exploration.
arXiv Detail & Related papers (2021-08-26T11:41:03Z) - Towards Novel Target Discovery Through Open-Set Domain Adaptation [73.81537683043206]
Open-set domain adaptation (OSDA) considers that the target domain contains samples from novel categories unobserved in external source domain.
We propose a novel framework to accurately identify the seen categories in target domain, and effectively recover the semantic attributes for unseen categories.
arXiv Detail & Related papers (2021-05-06T04:22:29Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.