Related papers: MoRe: Class Patch Attention Needs Regularization f…

Moving objects can greatly jeopardize the performance of a visual simultaneous localization and mapping (vSLAM) system which relies on the static-world assumption. Motion removal have seen successful on solving this problem. Two main…

State-of-the-art techniques in weakly-supervised semantic segmentation (WSSS) using image-level labels exhibit severe performance degradation on driving scene datasets such as Cityscapes. To address this challenge, we develop a new WSSS…

Fully supervised change detection methods have achieved significant advancements in performance, yet they depend severely on acquiring costly pixel-level labels. Considering that the patch-level annotations also contain abundant information…

Weakly-supervised segmentation (WSS) methods, reliant on image-level labels indicating object presence, lack explicit correspondence between labels and regions of interest (ROIs), posing a significant challenge. Despite this, WSS methods…

Citrus juices and fruits are commodities with great economic potential in the international market, but productivity losses caused by mites and other pests are still far from being a good mark. Despite the integrated pest mechanical aspect,…

Software vulnerability detection has emerged as a significant concern in the field of software security recently, capturing the attention of numerous researchers and developers. Most previous approaches focus on coarse-grained vulnerability…

Modality-agnostic Semantic Segmentation (MaSS) aims to achieve robust scene understanding across arbitrary combinations of input modality. Existing methods typically rely on explicit feature alignment to achieve modal homogenization, which…

Current feature matching methods focus on point-level matching, pursuing better representation learning of individual features, but lacking further understanding of the scene. This results in significant performance degradation when…

Weakly supervised image segmentation (WSSS) from image tags remains challenging due to its under-constraint nature. Most mainstream work focus on the extraction of class activation map (CAM) and imposing various additional regularization.…

Existing salient instance detection (SID) methods typically learn from pixel-level annotated datasets. In this paper, we present the first weakly-supervised approach to the SID problem. Although weak supervision has been considered in…

Large scale object detection with thousands of classes introduces the problem of many contradicting false positive detections, which have to be suppressed. Class-independent non-maximum suppression has traditionally been used for this step,…

This work aims to leverage pre-trained foundation models, such as contrastive language-image pre-training (CLIP) and segment anything model (SAM), to address weakly supervised semantic segmentation (WSSS) using image-level labels. To this…

Pixel-level annotations are expensive and time consuming to obtain. Hence, weak supervision using only image tags could have a significant impact in semantic segmentation. Recently, CNN-based methods have proposed to fine-tune pre-trained…

Though image-level weakly supervised semantic segmentation (WSSS) has achieved great progress with Class Activation Maps (CAMs) as the cornerstone, the large supervision gap between classification and segmentation still hampers the model to…

Weakly supervised semantic segmentation produces a pixel-level localization from a classifier, but it is likely to restrict its focus to a small discriminative region of the target object. AdvCAM is an attribution map of an image that is…

The Segment Anything Model (SAM) achieves strong open-vocabulary segmentation, but its ViT-based image encoders dominate inference latency and memory. Existing activation compression methods, such as token merging, reduce the token length…

The explosive growth of digital images and the widespread availability of image editing tools have made image manipulation detection an increasingly critical challenge. Current deep learning-based manipulation detection methods excel in…

The task of temporally grounding textual queries in videos is to localize one video segment that semantically corresponds to the given query. Most of the existing approaches rely on segment-sentence pairs (temporal annotations) for…

Image Manipulation Localization (IML) aims to identify edited regions in an image. However, with the increasing use of modern image editing and generative models, many manipulations no longer exhibit obvious low-level artifacts. Instead,…

Salient object detection aims at detecting the most visually distinct objects and producing the corresponding masks. As the cost of pixel-level annotations is high, image tags are usually used as weak supervisions. However, an image tag can…