Related papers: Beyond CLIP Generalization: Against Forward&Backwa…

Vision-language models (VLMs) have shown remarkable ability in aligning visual and textual representations, enabling a wide range of multimodal applications. However, their large-scale training data inevitably raises concerns about privacy,…

Continual learning aims to acquire new knowledge while retaining past information. Class-incremental learning (CIL) presents a challenging scenario where classes are introduced sequentially. For video data, the task becomes more complex…

We introduce the first multitasking vision transformer adapters that learn generalizable task affinities which can be applied to novel tasks and domains. Integrated into an off-the-shelf vision transformer backbone, our adapters can…

Vision-Language Models (VLMs) like CLIP have demonstrated remarkable generalization in zero- and few-shot settings, but adapting them efficiently to decentralized, heterogeneous data remains a challenge. While prompt tuning has emerged as a…

Contrastive Language-Image Pre-training (CLIP) has been shown to learn visual representations with great transferability, which achieves promising accuracy for zero-shot classification. To further improve its downstream performance,…

Recently, pre-trained vision-language models have been increasingly used to tackle the challenging zero-shot segmentation task. Typical solutions follow the paradigm of first generating mask proposals and then adopting CLIP to classify…

Vision-language models (VLMs) such as CLIP demonstrate strong performance but struggle when adapted to downstream tasks. Prompt learning has emerged as an efficient and effective strategy to adapt VLMs while preserving their pre-trained…

Cross-Domain Few-Shot Learning (CDFSL) aims to adapt large-scale pretrained models to specialized target domains with limited samples, yet the few-shot fine-tuning of vision-language models like CLIP remains underexplored. By establishing…

Face anti-spoofing (FAS) aims to construct a robust system that can withstand diverse attacks. While recent efforts have concentrated mainly on cross-domain generalization, two significant challenges persist: limited semantic understanding…

Most existing Vision-and-Language (V&L) models rely on pre-trained visual encoders, using a relatively small set of manually-annotated data (as compared to web-crawled data), to perceive the visual world. However, it has been observed that…

Visual foundation models like CLIP excel in learning feature representations from extensive datasets through self-supervised methods, demonstrating remarkable transfer learning and generalization capabilities. A growing number of…

Modern computer vision applications suffer from catastrophic forgetting when incrementally learning new concepts over time. The most successful approaches to alleviate this forgetting require extensive replay of previously seen data, which…

Multi-view learning (MVL) has gained great success in integrating information from multiple perspectives of a dataset to improve downstream task performance. To make MVL methods more practical in an open-ended environment, this paper…

CLIP has shown a remarkable zero-shot capability on a wide range of vision tasks. Previously, CLIP is only regarded as a powerful visual encoder. However, after being pre-trained by language supervision from a large amount of image-caption…

The scarcity of annotated data has sparked significant interest in unsupervised pre-training methods that leverage medical reports as auxiliary signals for medical visual representation learning. However, existing research overlooks the…

The recent CLIP-based methods have shown promising zero-shot and few-shot performance on image classification tasks. Existing approaches such as CoOp and Tip-Adapter only focus on high-level visual features that are fully aligned with…

Contrastive Language-Image Pretraining (CLIP) has achieved remarkable success, leading to rapid advancements in multimodal studies. However, CLIP faces a notable challenge in terms of inefficient data utilization. It relies on a single…

Pre-trained vision-language models like CLIP have shown powerful zero-shot inference ability via image-text matching and prove to be strong few-shot learners in various downstream tasks. However, in real-world scenarios, adapting CLIP to…

Current pre-trained vison-language models (PVLMs) achieve excellent performance on a range of multi-modal datasets. Recent work has aimed at building multilingual models, and a range of novel multilingual multi-modal datasets have been…

Despite the recent progress in incremental learning, addressing catastrophic forgetting under distributional drift is still an open and important problem. Indeed, while state-of-the-art domain incremental learning (DIL) methods perform…