Vision Transformers have achieved state-of-the-art performance in many visual tasks. Due to the quadratic computational and memory complexities of self-attention, recent works either apply attention only to low-resolution inputs or restrict the receptive field to a small local region. To overcome these limitations, we propose key-only attention, which excludes query-key pairwise interactions and uses a compute-efficient saliency-gate to obtain attention weights, modeling local-global interactions in all stages. Key-only attention has linear computational and memory complexities w.r.t input size. We use alternate layout to hybridize convolution and attention layers instead of grafting which is suggested by previous works, so that all stages can benefit from both spatial attentions and convolutions. We leverage these improvements to develop a new self-attention model family, LinGlos, which reach state-of-the-art accuracies on the parameter-limited setting of ImageNet classification benchmark, and outperform baselines significantly in downstream tasks, e.g., COCO object detection and ADE20K semantic segmentation.
ETH Zurich（苏黎世联邦理工学院）；University of Technology Sydney（悉尼科技大学）
Prevalent semantic segmentation solutions, despite their different network designs (FCN based or attention based) and mask decoding strategies (parametric softmax based or pixel-query based), can be placed in one category, by considering the softmax weights or query vectors as learnable class prototypes. In light of this prototype view, this study uncovers several limitations of such parametric segmentation regime, and proposes a nonparametric alternative based on non-learnable prototypes. Instead of prior methods learning a single weight/query vector for each class in a fully parametric manne…
Dual-R-DETR: Resolving Query Competition with Pairwise Routing in Transformer Decoders
University of Pittsburgh（匹兹堡大学）；University of California, Irvine（加州大学尔湾分校）；Stevens Institute of Technology（史蒂文斯理工学院）；Illinois Institute of Technology（伊利诺伊理工学院）；New York University（纽约大学）
University of Science and Technology of China（中国科学技术大学）；Harbin Institute of Technology（哈尔滨工业大学）；SenseTime Research（商汤科技研究院）
3D object detection from multiple image views is a fundamental and challenging task for visual scene understanding. Due to its low cost and high efficiency, multi-view 3D object detection has demonstrated promising application prospects. However, accurately detecting objects through perspective views in the 3D space is extremely difficult due to the lack of depth information. Recently, DETR3D introduces a novel 3D-2D query paradigm in aggregating multi-view images for 3D object detection and achieves state-of-the-art performance. In this paper, with intensive pilot experiments, we quantify the…
Few-shot object detection (FSOD) aims to detect never-seen objects using few examples. This field sees recent improvement owing to the meta-learning techniques by learning how to match between the query image and few-shot class examples, such that the learned model can generalize to few-shot novel classes. However, currently, most of the meta-learning-based methods perform pairwise matching between query image regions (usually proposals) and novel classes separately, therefore failing to take into account multiple relationships among them. In this paper, we propose a novel FSOD model using het…
Huazhong University of Science and Technology（华中科技大学）；Hong Kong University of Science and Technology（香港科技大学）
Vision transformers have recently set off a new wave in the field of medical image analysis due to their remarkable performance on various computer vision tasks. However, recent hybrid-/transformer-based approaches mainly focus on the benefits of transformers in capturing long-range dependency while ignoring the issues of their daunting computational complexity, high training costs, and redundant dependency. In this paper, we propose to employ adaptive pruning to transformers for medical image segmentation and propose a lightweight and effective hybrid network APFormer. To our best knowledge, …
ProtagoLabs Inc（ProtagoLabs公司）；Microsoft Research（微软研究院）；Beijing Institute of Technology（北京理工大学）；Huazhong University of Science and Technology（华中科技大学）；Sichuan University（四川大学）；Dalian University of Technology（大连理工大学）；Lehigh University（利哈伊大学）；Peking University（北京大学）
Temporal sentence grounding (TSG) aims to identify the temporal boundary of a specific segment from an untrimmed video by a sentence query. All existing works first utilize a sparse sampling strategy to extract a fixed number of video frames and then conduct multi-modal interactions with query sentence for reasoning. However, we argue that these methods have overlooked two indispensable issues: 1) Boundary-bias: The annotated target segment generally refers to two specific frames as corresponding start and end timestamps. The video downsampling process may lose these two frames and take the ad…
Tokyo Institute of Technology（东京工业大学）；Dalian University of Technology（大连理工大学）
We present a simple but effective attention named the unary-pairwise attention (UPA) for modeling the relationship between 3D point clouds. Our idea is motivated by the analysis that the standard self-attention (SA) that operates globally tends to produce almost the same attention maps for different query positions, revealing difficulties for learning query-independent and query-dependent information jointly. Therefore, we reformulate the SA and propose query-independent (Unary) and query-dependent (Pairwise) components to facilitate the learning of both terms. In contrast to the SA, the UPA e…
The Hong Kong University of Science and Technology（香港科技大学）
This paper presents a simple yet effective approach to modeling space-time correspondences in the context of video object segmentation. Unlike most existing approaches, we establish correspondences directly between frames without re-encoding the mask features for every object, leading to a highly efficient and robust framework. With the correspondences, every node in the current query frame is inferred by aggregating features from the past in an associative fashion. We cast the aggregation process as a voting problem and find that the existing inner-product affinity leads to poor use of memory…
Institute of Computing Technology, CAS（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；University of Science and Technology of China（中国科学技术大学）
Weakly supervised referring expression grounding (REG) aims at localizing the referential entity in an image according to linguistic query, where the mapping between the image region (proposal) and the query is unknown in the training stage. In referring expressions, people usually describe a target entity in terms of its relationship with other contextual entities as well as visual attributes. However, previous weakly supervised REG methods rarely pay attention to the relationship between the entities. In this paper, we propose a knowledge-guided pairwise reconstruction network (KPRN), which …
Aalto University（阿尔托大学）；Indian Institute of Technology, Delhi（印度理工学院德里分校）
We propose a new deep learning based approach for camera relocalization. Our approach localizes a given query image by using a convolutional neural network (CNN) for first retrieving similar database images and then predicting the relative pose between the query and the database images, whose poses are known. The camera location for the query image is obtained via triangulation from two relative translation estimates using a RANSAC based approach. Each relative pose estimate provides a hypothesis for the camera orientation and they are fused in a second RANSAC scheme. The neural network is tra…
Rethinking Weakly-supervised Video Temporal Grounding From a Game Perspective
Hubei Key Laboratory of Distributed System Security（湖北分布式系统安全重点实验室）；Hubei Engineering Research Center on Big Data Security（大数据安全工程研究中心）；School of Cyber Science and Engineering（网络安全科学与工程学院）；Huazhong University of Science and Technology（华中科技大学）；University of Central Florida（佛罗里达中央大学）；Zhejiang Gongshang University（浙江工商大学）；Guangzhou University（广州大学）；The Chinese University of Hong Kong（香港中文大学）；Peking University（北京大学）
Faculty of Engineering and Information Technology, University of Technology Sydney（悉尼科技大学工程与信息技术学院）；School of Computer Science, The University of Adelaide（阿德莱德大学计算机学院）
Deep neural networks have demonstrated advanced abilities on various visual classification tasks, which heavily rely on the large-scale training samples with annotated ground-truth. However, it is unrealistic always to require such annotation in real-world applications. Recently, Few-Shot learning (FS), as an attempt to address the shortage of training samples, has made significant progress in generic classification tasks. Nonetheless, it is still challenging for current FS models to distinguish the subtle differences between fine-grained categories given limited training data. To filling the …
Lumada Data Science Lab, Hitachi, Ltd.（日立株式会社 Lumada 数据科学实验室）；Center for Technology Innovation - Artificial Intelligence, Hitachi, Ltd.（日立株式会社 技术创新中心人工智能部）
We propose a simple, intuitive yet powerful method for human-object interaction (HOI) detection. HOIs are so diverse in spatial distribution in an image that existing CNN-based methods face the following three major drawbacks; they cannot leverage image-wide features due to CNN's locality, they rely on a manually defined location-of-interest for the feature aggregation, which sometimes does not cover contextually important regions, and they cannot help but mix up the features for multiple HOI instances if they are located closely. To overcome these drawbacks, we propose a transformer-based fea…
Love Me, Love My Label: Rethinking the Role of Labels in Prompt Retrieval for Visual In-Context Learning
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；School of Computer Science and Engineering, Northeastern University（东北大学计算机科学与工程学院）
ANFI: Rethinking Neighbor Feature Interaction in Person Re-ID
University of Science and Technology of China（中国科学技术大学）；Anhui Province Key Laboratory of Digital Security（安徽省数字安全重点实验室）；The Chinese University of Hong Kong（香港中文大学）
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院，清华大学）；ByteDance Inc.（字节跳动公司）
The vanilla self-attention mechanism inherently relies on pre-defined and steadfast computational dimensions. Such inflexibility restricts it from possessing context-oriented generalization that can bring more contextual cues and global representations. To mitigate this issue, we propose a Scalable Self-Attention (SSA) mechanism that leverages two scaling factors to release dimensions of query, key, and value matrices while unbinding them with the input. This scalability fetches context-oriented generalization and enhances object sensitivity, which pushes the whole network into a more effectiv…
WikiSeeker: Rethinking the Role of Vision-Language Models in Knowledge-Based Visual Question Answering
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所多模态人工智能系统国家重点实验室 (MAIS)）
