Related papers: ECO-TR: Efficient Correspondences Finding Via Coar…

We present a comprehensive framework for structured sparse coding and modeling extending the recent ideas of using learnable fast regressors to approximate exact sparse codes. For this purpose, we develop a novel block-coordinate proximal…

To address data locality and privacy restrictions, Federated Learning (FL) has recently been adopted to fine-tune large language models (LLMs), enabling improved performance on various downstream tasks without requiring aggregated data.…

Parameter-efficient finetuning (PEFT) has become ubiquitous to adapt foundation models to downstream task requirements while retaining their generalization ability. However, the amount of additionally introduced parameters and compute for…

DETR has been recently proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance. However, it suffers from slow convergence and limited feature spatial resolution, due to the…

Dense image correspondence is central to many applications, such as visual odometry, 3D reconstruction, object association, and re-identification. Historically, dense correspondence has been tackled separately for wide-baseline scenarios…

Transformers have become the backbone of modern AI, yet their high computational demands pose critical system challenges. While sparse training offers efficiency gains, existing methods fail to preserve critical structural relationships…

With the development of pre-trained language models, the dense retrieval models have become promising alternatives to the traditional retrieval models that rely on exact match and sparse bag-of-words representations. Different from most…

We present a novel architecture for dense correspondence. The current state-of-the-art are Transformer-based approaches that focus on either feature descriptors or cost volume aggregation. However, they generally aggregate one or the other…

The mutual intensity and its equivalent phase-space representations quantify an optical field's state of coherence and are important tools in the study of light propagation and dynamics, but they can only be estimated indirectly from…

Image-text matching is an interesting and fascinating task in modern AI research. Despite the evolution of deep-learning-based image and text processing systems, multi-modal matching remains a challenging problem. In this work, we consider…

We present a novel method for local image feature matching. Instead of performing image feature detection, description, and matching sequentially, we propose to first establish pixel-wise dense matches at a coarse level and later refine the…

Achieving more powerful semantic representations and semantic understanding is one of the key problems in improving the performance of semantic communication systems. This work focuses on enhancing the semantic understanding of the text…

We tackle the problem of establishing dense pixel-wise correspondences between a pair of images. In this work, we introduce Dual-Resolution Correspondence Networks (DualRC-Net), to obtain pixel-wise correspondences in a coarse-to-fine…

This paper presents a general scheme for enhancing the convergence and performance of DETR (DEtection TRansformer). We investigate the slow convergence problem in transformers from a new perspective, suggesting that it arises from the…

We present a simple and efficient method for refining maps or correspondences by iterative upsampling in the spectral domain that can be implemented in a few lines of code. Our main observation is that high quality maps can be obtained even…

The recently proposed Conformer architecture has shown state-of-the-art performances in Automatic Speech Recognition by combining convolution with attention to model both local and global dependencies. In this paper, we study how to reduce…

Detection Transformers have achieved competitive performance on the sample-rich COCO dataset. However, we show most of them suffer from significant performance drops on small-size datasets, like Cityscapes. In other words, the detection…

Modern large displacement optical flow algorithms usually use an initialization by either sparse descriptor matching techniques or dense approximate nearest neighbor fields. While the latter have the advantage of being dense, they have the…

Behavioral patterns captured in embeddings learned from interaction data are pivotal across various stages of production recommender systems. However, in the initial retrieval stage, practitioners face an inherent tradeoff between embedding…

We present a deep learning framework for accurate visual correspondences and demonstrate its effectiveness for both geometric and semantic matching, spanning across rigid motions to intra-class shape or appearance variations. In contrast to…