Related papers: Center-wise Local Image Mixture For Contrastive Re…
This paper proposes to perform online clustering by conducting twin contrastive learning (TCL) at the instance and cluster level. Specifically, we find that when the data is projected into a feature space with a dimensionality of the target…
Contrastive learning, which aims to capture general representation from unlabeled images to initialize the medical analysis models, has been proven effective in alleviating the high demand for expensive annotations. Current methods mainly…
Contrastive learning (CL) has become a powerful approach for learning representations from unlabeled images. However, existing CL methods focus predominantly on visual appearance features while neglecting topological characteristics (e.g.,…
Self-supervised learning enables networks to learn discriminative features from massive data itself. Most state-of-the-art methods maximize the similarity between two augmentations of one image based on contrastive learning. By utilizing…
Contrastive learning produces coherent semantic feature embeddings by encouraging positive samples to cluster closely while separating negative samples. However, existing contrastive learning methods lack principled guarantees on coverage…
Unsupervised learning algorithms are beginning to achieve accuracies comparable to their supervised counterparts on benchmark computer vision tasks, but their utility for practical applications has not yet been demonstrated. In this work,…
Recent self-supervised contrastive methods have been able to produce impressive transferable visual representations by learning to be invariant to different data augmentations. However, these methods implicitly assume a particular set of…
Real-scene image super-resolution aims to restore real-world low-resolution images into their high-quality versions. A typical RealSR framework usually includes the optimization of multiple criteria which are designed for different image…
Contrastive learning is a recent promising approach in unsupervised representation learning where a feature representation of data is learned by solving a pseudo classification problem from unlabelled data. However, it is not…
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…
Contrastive Language-Image Pre-training (CLIP) has achieved excellent performance over a wide range of tasks. However, the effectiveness of CLIP heavily relies on a substantial corpus of pre-training data, resulting in notable consumption…
Instance-level Image Retrieval (IIR), or simply Instance Retrieval, deals with the problem of finding all the images within an dataset that contain a query instance (e.g. an object). This paper makes the first attempt that tackles this…
Recent advances in unsupervised representation learning often rely on knowing the number of classes to improve feature extraction and clustering. However, this assumption raises an important question: is the number of classes always…
Contrastive learning methods train visual encoders by comparing views from one instance to others. Typically, the views created from one instance are set as positive, while views from other instances are negative. This binary instance…
Existing contrastive language-image pre-training aims to learn a joint representation by matching abundant image-text pairs. However, the number of image-text pairs in medical datasets is usually orders of magnitude smaller than that in…
Image clustering, which involves grouping images into different clusters without labels, is a key task in unsupervised learning. Although previous deep clustering methods have achieved remarkable results, they only explore the intrinsic…
In this paper, we focus on unsupervised representation learning for clustering of images. Recent advances in deep clustering and unsupervised representation learning are based on the idea that different views of an input image (generated…
Many contrastive representation learning methods learn a single global representation of an entire image. However, dense contrastive representation learning methods such as DenseCL (Wang et al., 2021) can learn better representations for…
Recently, contrastive learning approaches (e.g., CLIP (Radford et al., 2021)) have received huge success in multimodal learning, where the model tries to minimize the distance between the representations of different views (e.g., image and…
Asymmetric appearance between positive pair effectively reduces the risk of representation degradation in contrastive learning. However, there are still a mass of appearance similarities between positive pair constructed by the existing…