Related papers: Learning from Semantic Dictionaries: Discriminativ…

Recent advances in generative deep learning have enabled the creation of high-quality synthetic images in text-to-image generation. Prior work shows that fine-tuning a pretrained diffusion model on ImageNet and generating synthetic training…

Existing methods for vision-and-language learning typically require designing task-specific architectures and objectives for each task. For example, a multi-label answer classifier for visual question answering, a region scorer for…

Intelligent behaviour in the real-world requires the ability to acquire new knowledge from an ongoing sequence of experiences while preserving and reusing past knowledge. We propose a novel algorithm for unsupervised representation learning…

Automatically highlighting words that cause semantic differences between two documents could be useful for a wide range of applications. We formulate recognizing semantic differences (RSD) as a token-level regression task and study three…

Self-training methods have proven to be effective in exploiting abundant unlabeled data in semi-supervised learning, particularly when labeled data is scarce. While many of these approaches rely on a cross-entropy loss function (CE), recent…

In self-supervised learning (SSL), representations are learned via an auxiliary task without annotated labels. A common task is to classify augmentations or different modalities of the data, which share semantic content (e.g. an object in…

Contrastive learning has been demonstrated to be effective in enhancing pre-trained language models (PLMs) to derive superior universal sentence embeddings. However, existing contrastive methods still have two limitations. Firstly, previous…

Unsupervised sentence embeddings task aims to convert sentences to semantic vector representations. Most previous works directly use the sentence representations derived from pretrained language models. However, due to the token bias in…

Supervised learning for semantic segmentation requires a large number of labeled samples, which is difficult to obtain in the field of remote sensing. Self-supervised learning (SSL), can be used to solve such problems by pre-training a…

Contrastively trained vision-language models have achieved remarkable progress in vision and language representation learning, leading to state-of-the-art models for various downstream multimodal tasks. However, recent research has…

Recent multimodal models such as Contrastive Language-Image Pre-training (CLIP) have shown remarkable ability to align visual and linguistic representations. However, domains where small visual differences carry large semantic significance,…

Masked language modeling, widely used in discriminative language model (e.g., BERT) pretraining, commonly adopts a random masking strategy. However, random masking does not consider the importance of the different words in the sentence…

Collaborative learning enables distributed clients to learn a shared model for prediction while keeping the training data local on each client. However, existing collaborative learning methods require fully-labeled data for training, which…

We present EASE, a novel method for learning sentence embeddings via contrastive learning between sentences and their related entities. The advantage of using entity supervision is twofold: (1) entities have been shown to be a strong…

Recent self-supervised contrastive learning provides an effective approach for unsupervised person re-identification (ReID) by learning invariance from different views (transformed versions) of an input. In this paper, we incorporate a…

Visual-Semantic Embedding (VSE) is a prevalent approach in image-text retrieval by learning a joint embedding space between the image and language modalities where semantic similarities would be preserved. The triplet loss with…

Gloss-free Sign Language Translation (SLT) has advanced rapidly, achieving strong performances without relying on gloss annotations. However, these gains have often come with increased model complexity and high computational demands,…

Accurate segmentation of retinal fluids in 3D Optical Coherence Tomography images is key for diagnosis and personalized treatment of eye diseases. While deep learning has been successful at this task, trained supervised models often fail…

This paper proposes a scalable and straightforward pre-training paradigm for efficient visual conceptual representation called occluded image contrastive learning (OCL). Our OCL approach is simple: we randomly mask patches to generate…

In seismic interpretation, pixel-level labels of various rock structures can be time-consuming and expensive to obtain. As a result, there oftentimes exists a non-trivial quantity of unlabeled data that is left unused simply because…