Related papers: Contrastive Monotonic Pixel-Level Modulation
Contrastive learning is a discriminative approach that aims at grouping similar samples closer and diverse samples far from each other. It it an efficient technique to train an encoder generating distinguishable and informative…
Cross-modal retrieval is the task of retrieving samples of a given modality by using queries of a different one. Due to the wide range of practical applications, the problem has been mainly focused on the vision and language case, e.g. text…
Contrastive representation learning has shown to be effective to learn representations from unlabeled data. However, much progress has been made in vision domains relying on data augmentations carefully designed using domain knowledge. In…
A range of video modeling tasks, from optical flow to multiple object tracking, share the same fundamental challenge: establishing space-time correspondence. Yet, approaches that dominate each space differ. We take a step towards bridging…
Learning representations of images that are invariant to sensitive or unwanted attributes is important for many tasks including bias removal and cross domain retrieval. Here, our objective is to learn representations that are invariant to…
The advent of deep learning has brought an impressive advance to monocular depth estimation, e.g., supervised monocular depth estimation has been thoroughly investigated. However, the large amount of the RGB-to-depth dataset may not be…
Domain adaptation is one of the prominent strategies for handling both domain shift, that is widely encountered in large-scale land use/land cover map calculation, and the scarcity of pixel-level ground truth that is crucial for supervised…
Recently, unsupervised image-to-image translation methods based on contrastive learning have achieved state-of-the-art results in many tasks. However, in the previous works, the negatives are sampled from the input image itself, which…
How to achieve neural machine translation with limited parallel data? Existing techniques often rely on large-scale monolingual corpora, which is impractical for some low-resource languages. In this paper, we turn to connect several…
Exemplar-based image translation establishes dense correspondences between a conditional input and an exemplar (from two different domains) for leveraging detailed exemplar styles to achieve realistic image translation. Existing work builds…
Contrastive Language-Image Pretraining (CLIP) has achieved remarkable success, leading to rapid advancements in multimodal studies. However, CLIP faces a notable challenge in terms of inefficient data utilization. It relies on a single…
This prospective study proposes CoMatch, a novel semi-dense image matcher with dynamic covisibility awareness and bilateral subpixel accuracy. Firstly, observing that modeling context interaction over the entire coarse feature map elicits…
Unsupervised image-to-image translation tasks aim to find a mapping between a source domain X and a target domain Y from unpaired training data. Contrastive learning for Unpaired image-to-image Translation (CUT) yields state-of-the-art…
Visual domain gaps often impact object detection performance. Image-to-image translation can mitigate this effect, where contrastive approaches enable learning of the image-to-image mapping under unsupervised regimes. However, existing…
We introduce MOSAIC (Masked Objective with Selective Adaptation for In-domain Contrastive learning), a multi-stage framework for domain adaptation of text embedding models that incorporates joint domain-specific masked supervision. Our…
Visual imagery does not consist of solitary objects, but instead reflects the composition of a multitude of fluid concepts. While there have been great advances in visual representation learning, such advances have focused on building…
Image-to-image translation has drawn great attention during the past few years. It aims to translate an image in one domain to a given reference image in another domain. Due to its effectiveness and efficiency, many applications can be…
Contrastive learning has become pivotal in unsupervised representation learning, with frameworks like Momentum Contrast (MoCo) effectively utilizing large negative sample sets to extract discriminative features. However, traditional…
Unsupervised domain adaptation is a promising technique for semantic segmentation and other computer vision tasks for which large-scale data annotation is costly and time-consuming. In semantic segmentation, it is attractive to train models…
Foundation models (FM) are transforming artificial intelligence by enabling generalizable, data-efficient solutions across different domains for a broad range of applications. However, the lack of large and diverse datasets limits the…