Related papers: Adapting Vision-Language Model with Fine-grained S…

Open-vocabulary semantic segmentation aims at segmenting arbitrary categories expressed in textual form. Previous works have trained over large amounts of image-caption pairs to enforce pixel-level multimodal alignments. However, captions…

An old-school recipe for training a classifier is to (i) learn a good feature extractor and (ii) optimize a linear layer atop. When only a handful of samples are available per category, as in Few-Shot Adaptation (FSA), data are insufficient…

Visual language models (VLMs) have made significant advances in accuracy in recent years. However, their efficiency has received much less attention. This paper introduces NVILA, a family of open VLMs designed to jointly optimize efficiency…

Open-Vocabulary Camouflaged Object Segmentation (OVCOS) seeks to segment and classify camouflaged objects from arbitrary categories, presenting unique challenges due to visual ambiguity and unseen categories.Recent approaches typically…

In vision-language pre-training (VLP), masked image modeling (MIM) has recently been introduced for fine-grained cross-modal alignment. However, in most existing methods, the reconstruction targets for MIM lack high-level semantics, and…

Situational awareness applications rely heavily on real-time processing of visual and textual data to provide actionable insights. Vision language models (VLMs) have become essential tools for interpreting complex environments by connecting…

Pre-trained vision-language models (VLMs) learn to align vision and language representations on large-scale datasets, where each image-text pair usually contains a bag of semantic concepts. However, existing open-vocabulary object detectors…

Vision-language models (VLMs) demonstrate impressive zero-shot and few-shot learning capabilities, making them essential for several downstream tasks. However, fine-tuning these models at scale remains challenging, particularly in federated…

Recent advancements have empowered Large Language Models for Vision (vLLMs) to generate detailed perceptual outcomes, including bounding boxes and masks. Nonetheless, there are two constraints that restrict the further application of these…

Large vision-language models (LVLMs) have achieved impressive results in various vision-language tasks. However, despite showing promising performance, LVLMs suffer from hallucinations caused by language bias, leading to diminished focus on…

Open-vocabulary semantic segmentation (OVSS) aims to segment objects from arbitrary text categories without requiring densely annotated datasets. Although contrastive learning based models enable zero-shot segmentation, they often lose fine…

Temporal Action Segmentation (TAS) requires dividing videos into action segments, yet the vast space of activities and alternative breakdowns makes collecting comprehensive datasets infeasible. Existing methods remain limited to closed…

Despite the impressive advancements of Large Vision-Language Models (LVLMs), existing approaches suffer from a fundamental bottleneck: inefficient visual-language integration. Current methods either disrupt the model's inherent structure or…

Foundation models have advanced computer vision by enabling strong performance across diverse tasks through large-scale pretraining and supervised fine-tuning. However, they may underperform in domains with distribution shifts and scarce…

Dual-encoder Vision-Language Models (VLMs) such as CLIP are often characterized as bag-of-words systems due to their poor performance on compositional benchmarks. We argue that this limitation may stem less from deficient representations…

Semantic segmentation is essential in computer vision for various applications, yet traditional approaches face significant challenges, including the high cost of annotation and extensive training for supervised learning. Additionally, due…

Active learning aims to reduce annotation cost by selectively querying informative samples for supervision under a limited labeling budget. In this work, we investigate how vision-language models (VLMs) can be leveraged to further reduce…

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,…

Many image restoration (IR) tasks require both pixel-level fidelity and high-level semantic understanding to recover realistic photos with fine-grained details. However, previous approaches often struggle to effectively leverage both the…

Utilizing vision and language models (VLMs) pre-trained on large-scale image-text pairs is becoming a promising paradigm for open-vocabulary visual recognition. In this work, we extend this paradigm by leveraging motion and audio that…