Related papers: Text-To-Concept (and Back) via Cross-Model Alignme…
Besides image classification, Contrastive Language-Image Pre-training (CLIP) has accomplished extraordinary success for a wide range of vision tasks, including object-level and 3D space understanding. However, it's still challenging to…
Text classification is an important and classical problem in natural language processing. There have been a number of studies that applied convolutional neural networks (convolution on regular grid, e.g., sequence) to classification.…
CLIP embeddings have demonstrated remarkable performance across a wide range of multimodal applications. However, these high-dimensional, dense vector representations are not easily interpretable, limiting our understanding of the rich…
Large-scale contrastive vision-language pre-training has shown significant progress in visual representation learning. Unlike traditional visual systems trained by a fixed set of discrete labels, a new paradigm was introduced in…
Image-to-image translation aims to learn a mapping between a source and a target domain, enabling tasks such as style transfer, appearance transformation, and domain adaptation. In this work, we explore a diffusion-based framework for…
In text-to-image diffusion models, the cross-attention map of each text token indicates the specific image regions attended. Comparing these maps of syntactically related tokens provides insights into how well the generated image reflects…
Contrastive Language-Image Pre-training (CLIP) models excel in zero-shot classification, yet face challenges in complex multi-object scenarios. This study offers a comprehensive analysis of CLIP's limitations in these contexts using a…
Advances in multi-modal embeddings, and in particular CLIP, have recently driven several breakthroughs in Computer Vision (CV). CLIP has shown impressive performance on a variety of tasks, yet, its inherently opaque architecture may hinder…
What distinguishes robust models from non-robust ones? While for ImageNet distribution shifts it has been shown that such differences in robustness can be traced back predominantly to differences in training data, so far it is not known…
Open-world object detection, as a more general and challenging goal, aims to recognize and localize objects described by arbitrary category names. The recent work GLIP formulates this problem as a grounding problem by concatenating all…
Contrastive learning has emerged as a transformative method for learning effective visual representations through the alignment of image and text embeddings. However, pairwise similarity computation in contrastive loss between image and…
As vision-language models are deployed at scale, understanding their internal mechanisms becomes increasingly critical. Existing interpretability methods predominantly rely on activations, making them dataset-dependent, vulnerable to data…
The Stable Diffusion model is a prominent text-to-image generation model that relies on a text prompt as its input, which is encoded using the Contrastive Language-Image Pre-Training (CLIP). However, text prompts have limitations when it…
Pre-trained vision-language models have notably accelerated progress of open-world concept recognition. Their impressive zero-shot ability has recently been transferred to multi-label image classification via prompt tuning, enabling to…
Most existing semantic communication (SemCom) systems use deep joint source-channel coding (DeepJSCC) to encode task-specific semantics in a goal-oriented manner. However, their reliance on predefined tasks and datasets significantly limits…
Transductive zero-shot learning with vision-language models leverages image-image similarities within the dataset to achieve better classification accuracy compared to the inductive setting. However, there is little work that explores the…
Recent advances in text-to-image diffusion models have enabled the photorealistic generation of images from text prompts. Despite the great progress, existing models still struggle to generate compositional multi-concept images naturally,…
Numerous methods have been proposed to adapt a pre-trained foundational CLIP model for few-shot classification. As CLIP is trained on a large corpus, it generalises well through adaptation to few-shot classification. In this work, we…
The CLIP network measures the similarity between natural text and images; in this work, we investigate the entanglement of the representation of word images and natural images in its image encoder. First, we find that the image encoder has…
Recently, zero-shot and few-shot learning via Contrastive Vision-Language Pre-training (CLIP) have shown inspirational performance on 2D visual recognition, which learns to match images with their corresponding texts in open-vocabulary…