Related papers: OTSeg: Multi-prompt Sinkhorn Attention for Zero-Sh…

To address the annotation scarcity issue in some cases of semantic segmentation, there have been a few attempts to develop the segmentation model in the few-shot learning paradigm. However, most existing methods only focus on the…

Recently, Referring Image Segmentation (RIS) frameworks that pair the Multimodal Large Language Model (MLLM) with the Segment Anything Model (SAM) have achieved impressive results. However, adapting MLLM to segmentation is computationally…

We present a new embedding-based framework for zero-shot learning (ZSL). Most embedding-based methods aim to learn the correspondence between an image classifier (visual representation) and its class prototype (semantic representation) for…

Optimal transport (OT) is a widely used tool in machine learning, but computing high-accuracy solutions for large instances remains costly. Entropic regularization and the Sinkhorn algorithm improve scalability; however, when the…

Modern online multiple object tracking (MOT) methods usually focus on two directions to improve tracking performance. One is to predict new positions in an incoming frame based on tracking information from previous frames, and the other is…

Segmentation of moving objects in dynamic scenes is a key process in scene understanding for navigation tasks. Classical cameras suffer from motion blur in such scenarios rendering them effete. On the contrary, event cameras, because of…

Recently, learning open-vocabulary semantic segmentation from text supervision has achieved promising downstream performance. Nevertheless, current approaches encounter an alignment granularity gap owing to the absence of dense annotations,…

We tackle the challenging task of few-shot segmentation in this work. It is essential for few-shot semantic segmentation to fully utilize the support information. Previous methods typically adopt masked average pooling over the support…

Autonomous driving vehicles and robotic systems rely on accurate perception of their surroundings. Scene understanding is one of the crucial components of perception modules. Among all available sensors, LiDARs are one of the essential…

Vision-language models (VLMs) such as CLIP demonstrate strong generalization in zero-shot classification but remain highly vulnerable to adversarial perturbations. Existing methods primarily focus on adversarial fine-tuning or prompt…

Semantic segmentation in open-vocabulary scenarios presents significant challenges due to the wide range and granularity of semantic categories. Existing weakly-supervised methods often rely on category-specific supervision and ill-suited…

Due to the impressive zero-shot capabilities, pre-trained vision-language models (e.g. CLIP), have attracted widespread attention and adoption across various domains. Nonetheless, CLIP has been observed to be susceptible to adversarial…

Open-vocabulary segmentation (OVS) extends the zero-shot recognition capabilities of vision-language models (VLMs) to pixel-level prediction, enabling segmentation of arbitrary categories specified by text prompts. Despite recent progress,…

Deep Learning (DL) is undergoing a paradigm shift with the emergence of foundation models. In this work, we focus on Contrastive Language-Image Pre-training (CLIP), a Vision-Language foundation model that achieves high accuracy across…

To break through the limitations of pre-training models on fixed categories, Open-Set Object Detection (OSOD) and Open-Set Segmentation (OSS) have attracted a surge of interest from researchers. Inspired by large language models, mainstream…

Humans have a unique ability to learn new representations from just a handful of examples with little to no supervision. Deep learning models, however, require an abundance of data and supervision to perform at a satisfactory level.…

Motion planning is still an open problem for many disciplines, e.g., robotics, autonomous driving, due to their need for high computational resources that hinder real-time, efficient decision-making. A class of methods striving to provide…

Recent approaches leveraging multi-modal pre-trained models like CLIP for Unsupervised Domain Adaptation (UDA) have shown significant promise in bridging domain gaps and improving generalization by utilizing rich semantic knowledge and…

Despite Multimodal Large Language Models (MLLMs) showing promising results on general zero-shot image classification tasks, fine-grained image classification remains challenging. It demands precise attention to subtle visual details to…

Vision-Language Models (VLMs) such as CLIP demonstrate strong zero-shot generalization, but their performance significantly degrades in cross-domain scenarios with scarce target-domain training data (Cross-Domain Few-Shot Learning, CDFSL).…