相关论文: Choosing Wisely and Learning Deeply: Selective Cro…

Though convolutional neural networks are widely used in different tasks, lack of generalization capability in the absence of sufficient and representative data is one of the challenges that hinder their practical application. In this paper,…

The multimodal deep neural networks, represented by CLIP, have generated rich downstream applications owing to their excellent performance, thus making understanding the decision-making process of CLIP an essential research topic. Due to…

Cross-Modal Retrieval (CMR) is an important research topic across multimodal computing and information retrieval, which takes one type of data as the query to retrieve relevant data of another type. It has been widely used in many…

Referring image segmentation (RIS) is a fundamental vision-language task that intends to segment a desired object from an image based on a given natural language expression. Due to the essentially distinct data properties between image and…

Dataset distillation (DD) aims to minimize the time and memory consumption needed for training deep neural networks on large datasets, by creating a smaller synthetic dataset that has similar performance to that of the full real dataset.…

Domain Generalized Semantic Segmentation (DGSS) deals with training a model on a labeled source domain with the aim of generalizing to unseen domains during inference. Existing DGSS methods typically effectuate robust features by means of…

This paper examines the robustness of a multi-modal computer vision model, CLIP (Contrastive Language-Image Pretraining), in the context of unsupervised learning. The main objective is twofold: first, to evaluate the robustness of CLIP, and…

In recent years, knowledge distillation has been proved to be an effective solution for model compression. This approach can make lightweight student models acquire the knowledge extracted from cumbersome teacher models. However, previous…

Vision foundation models (VFMs) such as DINO have led to a paradigm shift in 2D camera-based perception towards extracting generalized features to support many downstream tasks. Recent works introduce self-supervised cross-modal knowledge…

Large vision-language representation learning models like CLIP have demonstrated impressive performance for zero-shot transfer to downstream tasks while largely benefiting from inter-modal (image-text) alignment via contrastive objectives.…

Domain Generalization (DG) is essentially a sub-branch of out-of-distribution generalization, which trains models from multiple source domains and generalizes to unseen target domains. Recently, some domain generalization algorithms have…

Knowledge distillation is a key technique for transferring the capabilities of large language models (LLMs) into smaller, more efficient student models. Existing distillation approaches often overlook two critical factors: the learning…

Domain generalization (DG) aims to generalize a model trained on multiple source (i.e., training) domains to a distributionally different target (i.e., test) domain. In contrast to the conventional DG that strictly requires the availability…

Continual learning (CL) empowers pre-trained vision-language models to adapt effectively to novel or previously underrepresented data distributions without comprehensive retraining, enhancing their adaptability and efficiency. While…

Contrastive Language-Image Pre-training (CLIP) has been shown to improve zero-shot generalization capabilities of language and vision models. In this paper, we extend CLIP for efficient knowledge distillation, by utilizing embeddings as…

The goal of domain generalization is to learn from multiple source domains to generalize to unseen target domains under distribution discrepancy. Current state-of-the-art methods in this area are fully supervised, but for many real-world…

Single-source domain generalization (SDG) aims to learn a model from a single source domain that can generalize well on unseen target domains. This is an important task in computer vision, particularly relevant to medical imaging where…

This work introduces CLIP-aware Domain-Adaptive Super-Resolution (CDASR), a novel framework that addresses the critical challenge of domain generalization in single image super-resolution. By leveraging the semantic capabilities of CLIP…

Gaze estimation methods often experience significant performance degradation when evaluated across different domains, due to the domain gap between the testing and training data. Existing methods try to address this issue using various…

Domain generalization (DG) remains a significant challenge for perception based on deep neural networks (DNNs), where domain shifts occur due to synthetic data, lighting, weather, or location changes. Vision-language models (VLMs) marked a…