Related papers: DropPos: Pre-Training Vision Transformers by Recon…

Vision transformers have demonstrated remarkable success in classification by leveraging global self-attention to capture long-range dependencies. However, this same mechanism can obscure fine-grained spatial details crucial for tasks such…

We attempt to reduce the computational costs in vision transformers (ViTs), which increase quadratically in the token number. We present a novel training paradigm that trains only one ViT model at a time, but is capable of providing…

Deep robot vision models are widely used for recognizing objects from camera images, but shows poor performance when detecting objects at untrained positions. Although such problem can be alleviated by training with large datasets, the…

Dropout is used to avoid overfitting by randomly dropping units from the neural networks during training. Inspired by dropout, this paper presents GI-Dropout, a novel dropout method integrating with global information to improve neural…

Given new tasks with very little data$-$such as new classes in a classification problem or a domain shift in the input$-$performance of modern vision systems degrades remarkably quickly. In this work, we illustrate how the neural network…

Long-tailed class distributions are prevalent among the practical applications of object detection and instance segmentation. Prior work in long-tail instance segmentation addresses the imbalance of losses between rare and frequent…

Category-level 6D object pose estimation is typically formulated as a multi-category joint learning problem with fully shared model parameters. However, pronounced geometric heterogeneity across categories entangles incompatible…

Unlike quasi-static robotic manipulation tasks like pick-and-place, dynamic tasks such as non-prehensile manipulation pose greater challenges, especially for vision-based control. Successful control requires the extraction of features…

Vision Transformers (ViTs) have shown promising performance compared with Convolutional Neural Networks (CNNs), but the training of ViTs is much harder than CNNs. In this paper, we define several metrics, including Dynamic Data Proportion…

Weakly supervised learning has emerged as a compelling tool for object detection by reducing the need for strong supervision during training. However, major challenges remain: (1) differentiation of object instances can be ambiguous; (2)…

We present Region-aware Open-vocabulary Vision Transformers (RO-ViT) - a contrastive image-text pretraining recipe to bridge the gap between image-level pretraining and open-vocabulary object detection. At the pretraining phase, we propose…

Visual Transformers (VTs) are emerging as an architectural paradigm alternative to Convolutional networks (CNNs). Differently from CNNs, VTs can capture global relations between image elements and they potentially have a larger…

The advent of Vision Transformers (ViTs) marks a substantial paradigm shift in the realm of computer vision. ViTs capture the global information of images through self-attention modules, which perform dot product computations among…

Multi-scale Vision Transformer (ViT) has emerged as a powerful backbone for computer vision tasks, while the self-attention computation in Transformer scales quadratically w.r.t. the input patch number. Thus, existing solutions commonly…

The annotation of 3D datasets is required for semantic-segmentation and object detection in scene understanding. In this paper we present a framework for the weakly supervision of a point clouds transformer that is used for 3D object…

Attention is sparse in vision transformers. We observe the final prediction in vision transformers is only based on a subset of most informative tokens, which is sufficient for accurate image recognition. Based on this observation, we…

Vision Transformers (ViTs) have a radically different architecture with significantly less inductive bias than Convolutional Neural Networks. Along with the improvement in performance, security and robustness of ViTs are also of great…

Vision-language retrieval is an important multi-modal learning topic, where the goal is to retrieve the most relevant visual candidate for a given text query. Recently, pre-trained models, e.g., CLIP, show great potential on retrieval…

Grounding (i.e. localizing) arbitrary, free-form textual phrases in visual content is a challenging problem with many applications for human-computer interaction and image-text reference resolution. Few datasets provide the ground truth…

Dropped Pronouns (DP) in which pronouns are frequently dropped in the source language but should be retained in the target language are challenge in machine translation. In response to this problem, we propose a semi-supervised approach to…