Related papers: CoCoNO: Attention Contrast-and-Complete for Initia…

Contrastive learning has gained popularity and pushes state-of-the-art performance across numerous large-scale benchmarks. In contrastive learning, the contrastive loss function plays a pivotal role in discerning similarities between…

Recent work uses reinforcement learning (RL) to fine-tune text-to-image diffusion models, improving text-image alignment and sample quality. However, existing approaches introduce unnecessary complexity: they cache the full sampling…

There has been tremendous progress in large-scale text-to-image synthesis driven by diffusion models enabling versatile downstream applications such as 3D object synthesis from texts, image editing, and customized generation. We present a…

Feature representation via self-supervised learning has reached remarkable success in image-level contrastive learning, which brings impressive performances on image classification tasks. While image-level feature representation mainly…

We show that bringing intermediate layers' representations of two augmented versions of an image closer together in self-supervised learning helps to improve the momentum contrastive (MoCo) method. To this end, in addition to the…

One of the major challenges in training deep neural networks for text-to-image generation is the significant linguistic discrepancy between ground-truth captions of each image in most popular datasets. The large difference in the choice of…

In this paper, we present a general framework for low-level vision tasks including image compression artifacts reduction and image denoising. Under this framework, a novel concatenated attention neural network (CANet) is specifically…

Diffusion models (DMs) have recently gained attention with state-of-the-art performance in text-to-image synthesis. Abiding by the tradition in deep learning, DMs are trained and evaluated on the images with fixed sizes. However, users are…

Layout-guided text-to-image models offer greater control over the generation process by explicitly conditioning image synthesis on the spatial arrangement of elements. As a result, their adoption has increased in many computer vision…

Contrastive Language and Image Pairing (CLIP), a transformative method in multimedia retrieval, typically trains two neural networks concurrently to generate joint embeddings for text and image pairs. However, when applied directly, these…

Current state-of-the-art object detection algorithms still suffer the problem of imbalanced distribution of training data over object classes and background. Recent work introduced a new loss function called focal loss to mitigate this…

Transferring visual style between images while preserving semantic correspondence between similar objects remains a central challenge in computer vision. While existing methods have made great strides, most of them operate at global level…

In an unpaired setting, lacking sufficient content constraints for image-to-image translation (I2I) tasks, GAN-based approaches are usually prone to model collapse. Current solutions can be divided into two categories, reconstruction-based…

With the development of deep learning, medical image processing has been widely used to assist clinical research. This paper focuses on the denoising problem of low-dose computed tomography using deep learning. Although low-dose computed…

Visual generative AI models often encounter challenges related to text-image alignment and reasoning limitations. This paper presents a novel method for selectively enhancing the signal at critical denoising steps, optimizing image…

Continual learning aims to learn multiple tasks sequentially while preserving prior knowledge, but faces the challenge of catastrophic forgetting when adapting to new tasks. Recently, approaches leveraging pre-trained models have gained…

Recent advancements in text-to-image generation models have dramatically enhanced the generation of photorealistic images from textual prompts, leading to an increased interest in personalized text-to-image applications, particularly in…

Training-free consistent text-to-image generation depicting the same subjects across different images is a topic of widespread recent interest. Existing works in this direction predominantly rely on cross-frame self-attention; which…

To date, most existing self-supervised learning methods are designed and optimized for image classification. These pre-trained models can be sub-optimal for dense prediction tasks due to the discrepancy between image-level prediction and…

Image-text retrieval is a central problem for understanding the semantic relationship between vision and language, and serves as the basis for various visual and language tasks. Most previous works either simply learn coarse-grained…