Related papers: Unicom: Universal and Compact Representation Learn…

We propose to bridge the gap between semi-supervised and unsupervised image recognition with a flexible method that performs well for both generalized category discovery (GCD) and image clustering. Despite the overlap in motivation between…

Multi-modal language-vision models trained on hundreds of millions of image-text pairs (e.g. CLIP, DALL-E) gained a recent surge, showing remarkable capability to perform zero- or few-shot learning and transfer even in absence of per-sample…

Image-language learning has made unprecedented progress in visual understanding. These developments have come at high costs, as contemporary vision-language models require large model scales and amounts of data. We here propose a much…

Vision-language contrastive learning frameworks such as CLIP enable learning representations from natural language supervision and provide strong zero-shot classification capabilities. However, due to the nature of the supervisory signal in…

We present BRICS, a bi-level feature representation for image collections, which consists of a key code space on top of a feature grid space. Specifically, our representation is learned by an autoencoder to encode images into continuous key…

Most of the achievements in artificial intelligence so far were accomplished by supervised learning which requires numerous annotated training data and thus costs innumerable manpower for labeling. Unsupervised learning is one of the…

As a fundamental visual attribute, image complexity significantly influences both human perception and the performance of computer vision models. However, accurately assessing and quantifying image complexity remains a challenging task. (1)…

Existing multi-view representation learning methods typically follow a specific-to-uniform pipeline, extracting latent features from each view and then fusing or aligning them to obtain the unified object representation. However, the…

During the preceding biennium, vision-language pre-training has achieved noteworthy success on several downstream tasks. Nevertheless, acquiring high-quality image-text pairs, where the pairs are entirely exclusive of each other, remains a…

In the large-scale image retrieval task, the two most important requirements are the discriminability of image representations and the efficiency in computation and storage of representations. Regarding the former requirement, Convolutional…

Contrastive Language-Image Pre-training (CLIP) provides a foundation model by integrating natural language into visual concepts, enabling zero-shot recognition on downstream tasks. It is usually expected that satisfactory overall accuracy…

In recent literature, few-shot classification has predominantly been defined by the N-way k-shot meta-learning problem. Models designed for this purpose are usually trained to excel on standard benchmarks following a restricted setup,…

Unsupervised representation learning with contrastive learning achieved great success. This line of methods duplicate each training batch to construct contrastive pairs, making each training batch and its augmented version forwarded…

Contrastive language-image pre-training aligns the features of text-image pairs in a common latent space via distinct encoders for each modality. While this approach achieves impressive performance in several zero-shot tasks, it cannot…

We consider the problem of image representation for the tasks of unsupervised learning and semi-supervised learning. In those learning tasks, the raw image vectors may not provide enough representation for their intrinsic structures due to…

The accelerating advancement of generative models has introduced new challenges for detecting AI-generated images, especially in real-world scenarios where novel generation techniques emerge rapidly. Existing learning paradigms are likely…

Generalized Category Discovery (GCD) requires a model to both classify known categories and cluster unknown categories in unlabeled data. Prior methods leveraged self-supervised pre-training combined with supervised fine-tuning on the…

Advances in high resolution remote sensing image analysis are currently hampered by the difficulty of gathering enough annotated data for training deep learning methods, giving rise to a variety of small datasets and associated…

After pre-training on extensive image-text pairs, Contrastive Language-Image Pre-training (CLIP) demonstrates promising performance on a wide variety of benchmarks. However, a substantial volume of multimodal interleaved documents remains…

The Vision-Language Pre-training (VLP) models like CLIP have gained popularity in recent years. However, many works found that the social biases hidden in CLIP easily manifest in downstream tasks, especially in image retrieval, which can…