Related papers: Multiscale Vision Transformers meet Bipartite Matc…

This paper investigates two techniques for developing efficient self-supervised vision transformers (EsViT) for visual representation learning. First, we show through a comprehensive empirical study that multi-stage architectures with…

Multi-task learning (MTL) encapsulates multiple learned tasks in a single model and often lets those tasks learn better jointly. However, when deploying MTL onto those real-world systems that are often resource-constrained or…

Model binarization can significantly compress model size, reduce energy consumption, and accelerate inference through efficient bit-wise operations. Although binarizing convolutional neural networks have been extensively studied, there is…

The development of language models have moved from encoder-decoder to decoder-only designs. In addition, we observe that the two most popular multimodal tasks, the generative and contrastive tasks, are nontrivial to accommodate in one…

Vision transformer has demonstrated promising performance on challenging computer vision tasks. However, directly training the vision transformers may yield unstable and sub-optimal results. Recent works propose to improve the performance…

Multimodal Large Language Models (MLLMs) have recently achieved remarkable success in visual-language understanding, demonstrating superior high-level semantic alignment within their vision encoders. An important question thus arises: Can…

Multiview detection incorporates multiple camera views to deal with occlusions, and its central problem is multiview aggregation. Given feature map projections from multiple views onto a common ground plane, the state-of-the-art method…

The introduction of DETR represents a new paradigm for object detection. However, its decoder conducts classification and box localization using shared queries and cross-attention layers, leading to suboptimal results. We observe that…

3D single object tracking with LiDAR points is an important task in the computer vision field. Previous methods usually adopt the matching-based or motion-centric paradigms to estimate the current target status. However, the former is…

Multimodal embedding models, built upon causal Vision Language Models (VLMs), have shown promise in various tasks. However, current approaches face three key limitations: the use of causal attention in VLM backbones is suboptimal for…

DETR accomplishes end-to-end object detection through iteratively generating multiple object candidates based on image features and promoting one candidate for each ground-truth object. The traditional training procedure using one-to-one…

Modern top-performing object detectors depend heavily on backbone networks, whose advances bring consistent performance gains through exploring more effective network structures. In this paper, we propose a novel and flexible backbone…

One recent promising approach to the Visual Place Recognition (VPR) problem has been to fuse the place recognition estimates of multiple complementary VPR techniques using methods such as SRAL and multi-process fusion. These approaches come…

Vision Transformers (ViTs) have emerged as the backbone of many segmentation models, consistently achieving state-of-the-art (SOTA) performance. However, their success comes at a significant computational cost. Image token pruning is one of…

Breast ultrasound interpretation requires simultaneous lesion segmentation and tissue classification. However, conventional multi-task learning approaches suffer from task interference and rigid coordination strategies that fail to adapt to…

Vision Transformers (ViTs) take all the image patches as tokens and construct multi-head self-attention (MHSA) among them. Complete leverage of these image tokens brings redundant computations since not all the tokens are attentive in MHSA.…

We introduce dense vision transformers, an architecture that leverages vision transformers in place of convolutional networks as a backbone for dense prediction tasks. We assemble tokens from various stages of the vision transformer into…

We present a method for trajectory planning for autonomous driving, learning image-based context embeddings that align with motion prediction frameworks and planning-based intention input. Within our method, a ViT encoder takes raw images…

Video understanding requires reasoning at multiple spatiotemporal resolutions -- from short fine-grained motions to events taking place over longer durations. Although transformer architectures have recently advanced the state-of-the-art,…

Multimodal visual object tracking can be divided into to several kinds of tasks (e.g. RGB and RGB+X tracking), based on the input modality. Existing methods often train separate models for each modality or rely on pretrained models to adapt…