Related papers: Positive-Negative Equal Contrastive Loss for Seman…

In standard supervised machine learning, it is necessary to provide a label for every input in the data. While raw data in many application domains is easily obtainable on the Internet, manual labelling of this data is prohibitively…

We introduce Patch Aligned Contrastive Learning (PACL), a modified compatibility function for CLIP's contrastive loss, intending to train an alignment between the patch tokens of the vision encoder and the CLS token of the text encoder.…

Contrastive learning is a powerful technique to learn representations that are semantically distinctive and geometrically invariant. While most of the earlier approaches have demonstrated its effectiveness on single-modality learning tasks…

Semantic segmentation is the task of assigning a label to each pixel in the image.In recent years, deep convolutional neural networks have been driving advances in multiple tasks related to cognition. Although, DCNNs have resulted in…

Contrastive representation learning has proven to be an effective self-supervised learning method. Most successful approaches are based on Noise Contrastive Estimation (NCE) and use different views of an instance as positives that should be…

Visual Semantic Embedding (VSE) aims to extract the semantics of images and their descriptions, and embed them into the same latent space for cross-modal information retrieval. Most existing VSE networks are trained by adopting a hard…

Unsupervised learning has recently made exceptional progress because of the development of more effective contrastive learning methods. However, CNNs are prone to depend on low-level features that humans deem non-semantic. This dependency…

State-of-the-art pre-trained image models predominantly adopt a two-stage approach: initial unsupervised pre-training on large-scale datasets followed by task-specific fine-tuning using Cross-Entropy loss~(CE). However, it has been…

Contrastive learning is a powerful self-supervised learning method, but we have a limited theoretical understanding of how it works and why it works. In this paper, we prove that contrastive learning with the standard InfoNCE loss is…

Semantic segmentation has made tremendous progress in recent years. However, satisfying performance highly depends on a large number of pixel-level annotations. Therefore, in this paper, we focus on the semi-supervised segmentation problem…

Since the meaning representations are detailed and accurate annotations which express fine-grained sequence-level semtantics, it is usually hard to train discriminative semantic parsers via Maximum Likelihood Estimation (MLE) in an…

Recent advances in self-supervised contrastive learning yield good image-level representation, which favors classification tasks but usually neglects pixel-level detailed information, leading to unsatisfactory transfer performance to dense…

Fine-grained classification involves dealing with datasets with larger number of classes with subtle differences between them. Guiding the model to focus on differentiating dimensions between these commonly confusable classes is key to…

Learning discriminative image representations plays a vital role in long-tailed image classification because it can ease the classifier learning in imbalanced cases. Given the promising performance contrastive learning has shown recently in…

We introduce a novel approach to unsupervised and semi-supervised domain adaptation for semantic segmentation. Unlike many earlier methods that rely on adversarial learning for feature alignment, we leverage contrastive learning to bridge…

Autonomous robotic systems applied to new domains require an abundance of expensive, pixel-level dense labels to train robust semantic segmentation models under full supervision. This study proposes a model-agnostic Depth Edge Alignment…

Contrastive Self-supervised Learning (CSL) is a practical solution that learns meaningful visual representations from massive data in an unsupervised approach. The ordinary CSL embeds the features extracted from neural networks onto…

The success of deep learning heavily depends on the availability of large labeled training sets. However, it is hard to get large labeled datasets in medical image domain because of the strict privacy concern and costly labeling efforts.…

Semantic segmentation and instance level segmentation made substantial progress in recent years due to the emergence of deep neural networks (DNNs). A number of deep architectures with Convolution Neural Networks (CNNs) were proposed that…

Image segmentation is the foundation of several computer vision tasks, where pixel-wise knowledge is a prerequisite for achieving the desired target. Deep learning has shown promising performance in supervised image segmentation. However,…