相关论文: RefAM: Attention Magnets for Zero-Shot Referral Se…

Text-guided object segmentation requires both cross-modal reasoning and pixel grounding abilities. Most recent methods treat text-guided segmentation as one-shot grounding, where the model predicts pixel prompts in a single forward pass to…

Despite their success, Segment Anything Models (SAMs) experience significant performance drops on severely degraded, low-quality images, limiting their effectiveness in real-world scenarios. To address this, we propose GleSAM, which…

While Transformers have revolutionized deep learning, their quadratic attention complexity hinders their ability to process infinitely long inputs. We propose Feedback Attention Memory (FAM), a novel Transformer architecture that leverages…

Entrusted with the goal of pixel-level object classification, the semantic segmentation networks entail the laborious preparation of pixel-level annotation masks. To obtain pixel-level annotation masks for a given class without human…

Referring image segmentation aims to segment the target object referred by a natural language expression. However, previous methods rely on the strong assumption that one sentence must describe one target in the image, which is often not…

In weakly-supervised semantic segmentation (WSSS) using only image-level class labels, a problem with CNN-based Class Activation Maps (CAM) is that they tend to activate the most discriminative local regions of objects. On the other hand,…

Diffusion Models (DMs) have exhibited superior performance in generating high-quality and diverse images. However, this exceptional performance comes at the cost of expensive architectural design, particularly due to the attention module…

Referring Expression Segmentation (RES) is an emerging task in computer vision, which segments the target instances in images based on text descriptions. However, its development is plagued by the expensive segmentation labels. To address…

Referring expression segmentation (RES), a task that involves localizing specific instance-level objects based on free-form linguistic descriptions, has emerged as a crucial frontier in human-AI interaction. It demands an intricate…

The pre-trained text-image discriminative models, such as CLIP, has been explored for open-vocabulary semantic segmentation with unsatisfactory results due to the loss of crucial localization information and awareness of object shapes.…

Given a language expression, referring remote sensing image segmentation (RRSIS) aims to identify ground objects and assign pixel-wise labels within the imagery. The one of key challenges for this task is to capture discriminative…

Prior methods propose to offset the escalating costs of modern foundation models by dropping specific parts of their contexts with hand-designed rules, while attempting to preserve their original performance. We overcome this trade-off with…

Referring Expressions Generation (REG) aims to produce textual descriptions that unambiguously identifies specific objects within a visual scene. Traditionally, this has been achieved through supervised learning methods, which perform well…

Semantic segmentation, which aims to acquire a detailed understanding of images, is an essential issue in computer vision. However, in practical scenarios, new categories that are different from the categories in training usually appear.…

Referring expression grounding aims at locating certain objects or persons in an image with a referring expression, where the key challenge is to comprehend and align various types of information from visual and textual domain, such as…

The so-called "attention" is an efficient mechanism to improve the performance of convolutional neural networks. It uses contextual information to recalibrate the input to strengthen the propagation of informative features. However, the…

We propose an approach to semantic segmentation that achieves state-of-the-art supervised performance when applied in a zero-shot setting. It thus achieves results equivalent to those of the supervised methods, on each of the major semantic…

Image segmentation from referring expressions is a joint vision and language modeling task, where the input is an image and a textual expression describing a particular region in the image; and the goal is to localize and segment the…

By integrating the generative strengths of diffusion models with the representation capabilities of frequency-domain attention, DFAM effectively enhances reconstruction performance under low-SNR condi-tions. Experimental results demonstrate…

Semantic Segmentation is one of the most challenging vision tasks, usually requiring large amounts of training data with expensive pixel level annotations. With the success of foundation models and especially vision-language models, recent…