相关论文: Captured by Captions: On Memorization and its Miti…

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…

Image-text contrastive learning models such as CLIP have demonstrated strong task transfer ability. The high generality and usability of these visual models is achieved via a web-scale data collection process to ensure broad concept…

Recently, CLIP has become an important model for aligning images and text in multi-modal contexts. However, researchers have identified limitations in the ability of CLIP's text and image encoders to extract detailed knowledge from pairs of…

Image captioning model is a cross-modality knowledge discovery task, which targets at automatically describing an image with an informative and coherent sentence. To generate the captions, the previous encoder-decoder frameworks directly…

Visual perceptual tasks aim to predict human judgment of images (e.g., emotions invoked by images, image quality assessment). Unlike objective tasks such as object/scene recognition, perceptual tasks rely on subjective human assessments,…

Attention mechanisms have attracted considerable interest in image captioning because of its powerful performance. Existing attention-based models use feedback information from the caption generator as guidance to determine which of the…

We present our work in progress exploring the possibilities of a shared embedding space between textual and visual modality. Leveraging the textual nature of object detection labels and the hypothetical expressiveness of extracted visual…

The Contrastive Language-Image Pre-training (CLIP) has recently shown remarkable generalization on "zero-shot" training and has applied to many downstream tasks. We explore the adaptation of CLIP to achieve a more efficient and generalized…

Contrastive Language-Image Pre-training (CLIP) has drawn increasing attention recently for its transferable visual representation learning. However, due to the semantic gap within datasets, CLIP's pre-trained image-text alignment becomes…

We present a novel data-efficient semi-supervised framework to improve the generalization of image captioning models. Constructing a large-scale labeled image captioning dataset is an expensive task in terms of labor, time, and cost. In…

Multimodal contrastive learning (MCL) has shown remarkable advances in zero-shot classification by learning from millions of image-caption pairs crawled from the Internet. However, this reliance poses privacy risks, as hackers may…

Pretrained models like CLIP have demonstrated impressive zero-shot classification capabilities across diverse visual domains, spanning natural images, artistic renderings, and abstract representations. However, real-world applications often…

Pretraining general-purpose visual features has become a crucial part of tackling many computer vision tasks. While one can learn such features on the extensively-annotated ImageNet dataset, recent approaches have looked at ways to allow…

Contrastive learning has emerged as an efficient framework to learn multimodal representations. CLIP, a seminal work in this area, achieved impressive results by training on paired image-text data using the contrastive loss. Recent work…

Large-scale pre-trained Vision-Language Models (VLMs), such as CLIP, establish the correlation between texts and images, achieving remarkable success on various downstream tasks with fine-tuning. In existing fine-tuning methods, the…

Despite CLIP being the foundation model in numerous vision-language applications, the CLIP suffers from a severe text spotting bias. Such bias causes CLIP models to `Parrot' the visual text embedded within images while disregarding the…

Self supervision and natural language supervision have emerged as two exciting ways to train general purpose image encoders which excel at a variety of downstream tasks. Recent works such as M3AE and SLIP have suggested that these…

Recently, there have been breakthroughs in computer vision ("CV") models that are more generalizable with the advent of models such as CLIP and ALIGN. In this paper, we analyze CLIP and highlight some of the challenges such models pose.…

We describe a protocol to study text-to-video retrieval training with unlabeled videos, where we assume (i) no access to labels for any videos, i.e., no access to the set of ground-truth captions, but (ii) access to labeled images in the…

We propose a novel memory-modular learner for image classification that separates knowledge memorization from reasoning. Our model enables effective generalization to new classes by simply replacing the memory contents, without the need for…