Related papers: Correlational Image Modeling for Self-Supervised V…
Quantifying and evaluating image complexity can be instrumental in enhancing the performance of various computer vision tasks. Supervised learning can effectively learn image complexity features from well-annotated datasets. However,…
Conventional deep learning models deal with images one-by-one, requiring costly and time-consuming expert labeling in the field of medical imaging, and domain-specific restriction limits model generalizability. Visual in-context learning…
Masked image modeling (MIM) learns visual representation by masking and reconstructing image patches. Applying the reconstruction supervision on the CLIP representation has been proven effective for MIM. However, it is still under-explored…
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…
Language-image pre-training is an effective technique for learning powerful representations in general domains. However, when directly turning to person representation learning, these general pre-training methods suffer from unsatisfactory…
Vision-language models (VLMs) like CLIP have showcased a remarkable ability to extract transferable features for downstream tasks. Nonetheless, the training process of these models is usually based on a coarse-grained contrastive loss…
Masked Image Modeling (MIM) is a self-supervised learning technique that involves masking portions of an image, such as pixels, patches, or latent representations, and training models to predict the missing information using the visible…
Like masked language modeling (MLM) in natural language processing, masked image modeling (MIM) aims to extract valuable insights from image patches to enhance the feature extraction capabilities of the underlying deep neural network (DNN).…
Text images are unique in their dual nature, encompassing both visual and linguistic information. The visual component encompasses structural and appearance-based features, while the linguistic dimension incorporates contextual and semantic…
Referring image segmentation aims to segment a referent via a natural linguistic expression.Due to the distinct data properties between text and image, it is challenging for a network to well align text and pixel-level features. Existing…
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…
Contrastive learning based on instance discrimination trains model to discriminate different transformations of the anchor sample from other samples, which does not consider the semantic similarity among samples. This paper proposes a new…
Masked Image Modeling (MIM) achieves outstanding success in self-supervised representation learning. Unfortunately, MIM models typically have huge computational burden and slow learning process, which is an inevitable obstacle for their…
Recently introduced self-supervised methods for image representation learning provide on par or superior results to their fully supervised competitors, yet the corresponding efforts to explain the self-supervised approaches lag behind.…
Modern self-supervised learning algorithms typically enforce persistency of instance representations across views. While being very effective on learning holistic image and video representations, such an objective becomes sub-optimal for…
Contrastive Language-Image Pretraining (CLIP) has emerged as a novel paradigm to learn visual models from language supervision. While researchers continue to push the frontier of CLIP, reproducing these works remains challenging. This is…
While image-text representation learning has become very popular in recent years, existing models tend to lack spatial awareness and have limited direct applicability for dense understanding tasks. For this reason, self-supervised…
Multimodal models, such as the Contrastive Language-Image Pre-training (CLIP) model, have demonstrated remarkable success in aligning visual and linguistic representations. However, these models exhibit limitations when applied to…
Image-caption pretraining has been quite successfully used for downstream vision tasks like zero-shot image classification and object detection. However, image-caption pretraining is still a hard problem -- it requires multiple concepts…
Person image generation aims to perform non-rigid deformation on source images, which generally requires unaligned data pairs for training. Recently, self-supervised methods express great prospects in this task by merging the disentangled…