اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدLearning the Best Pooling Strategy for Visual Semantic Embedding
110
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Visual Semantic Embedding (VSE) is a dominant approach for vision-language retrieval, which aims at learning a deep embedding space such that visual data are embedded close to their semantic text labels or descriptions. Recent VSE models use complex methods to better contextualize and aggregate multi-modal features into holistic embeddings. However, we discover that surprisingly simple (but carefully selected) global pooling functions (e.g., max pooling) outperform those complex models, across different feature extractors. Despite its simplicity and effectiveness, seeking the best pooling function for different data modality and feature extractor is costly and tedious, especially when the size of features varies (e.g., text, video). Therefore, we propose a Generalized Pooling Operator (GPO), which learns to automatically adapt itself to the best pooling strategy for different features, requiring no manual tuning while staying effective and efficient. We extend the VSE model using this proposed GPO and denote it as VSE$infty$. Without bells and whistles, VSE$infty$ outperforms previous VSE methods significantly on image-text retrieval benchmarks across popular feature extractors. With a simple adaptation, variants of VSE$infty$ further demonstrate its strength by achieving the new state of the art on two video-text retrieval datasets. Comprehensive experiments and visualizations confirm that GPO always discovers the best pooling strategy and can be a plug-and-play feature aggregation module for standard VSE models. Code and pre-trained models are available at https://vse-infty.github.io.
قيم البحث
اقرأ أيضاً
For visual-semantic embedding, the existing methods normally treat the relevance between queries and candidates in a bipolar way -- relevant or irrelevant, and all irrelevant candidates are uniformly pushed away from the query by an equal margin in t
he embedding space, regardless of their various proximity to the query. This practice disregards relatively discriminative information and could lead to suboptimal ranking in the retrieval results and poorer user experience, especially in the long-tail query scenario where a matching candidate may not necessarily exist. In this paper, we introduce a continuous variable to model the relevance degree between queries and multiple candidates, and propose to learn a coherent embedding space, where candidates with higher relevance degrees are mapped closer to the query than those with lower relevance degrees. In particular, the new ladder loss is proposed by extending the triplet loss inequality to a more general inequality chain, which implements variable push-away margins according to respective relevance degrees. In addition, a proper Coherent Score metric is proposed to better measure the ranking results including those irrelevant candidates. Extensive experiments on multiple datasets validate the efficacy of our proposed method, which achieves significant improvement over existing state-of-the-art methods.
Person reidentification (ReID) is a very hot research topic in machine learning and computer vision, and many person ReID approaches have been proposed; however, most of these methods assume that the same person has the same clothes within a short ti
me interval, and thus their visual appearance must be similar. However, in an actual surveillance environment, a given person has a great probability of changing clothes after a long time span, and they also often take different personal belongings with them. When the existing person ReID methods are applied in this type of case, almost all of them fail. To date, only a few works have focused on the cloth-changing person ReID task, but since it is very difficult to extract generalized and robust features for representing people with different clothes, their performances need to be improved. Moreover, visual-semantic information is often ignored. To solve these issues, in this work, a novel multigranular visual-semantic embedding algorithm (MVSE) is proposed for cloth-changing person ReID, where visual semantic information and human attributes are embedded into the network, and the generalized features of human appearance can be well learned to effectively solve the problem of clothing changes. Specifically, to fully represent a person with clothing changes, a multigranular feature representation scheme (MGR) is employed to focus on the unchanged part of the human, and then a cloth desensitization network (CDN) is designed to improve the feature robustness of the approach for the person with different clothing, where different high-level human attributes are fully utilized. Moreover, to further solve the issue of pose changes and occlusion under different camera perspectives, a partially semantically aligned network (PSA) is proposed to obtain the visual-semantic information that is used to align the human attributes.
Self-supervised representation learning for visual pre-training has achieved remarkable success with sample (instance or pixel) discrimination and semantics discovery of instance, whereas there still exists a non-negligible gap between pre-trained mo
del and downstream dense prediction tasks. Concretely, these downstream tasks require more accurate representation, in other words, the pixels from the same object must belong to a shared semantic category, which is lacking in the previous methods. In this work, we present Dense Semantic Contrast (DSC) for modeling semantic category decision boundaries at a dense level to meet the requirement of these tasks. Furthermore, we propose a dense cross-image semantic contrastive learning framework for multi-granularity representation learning. Specially, we explicitly explore the semantic structure of the dataset by mining relations among pixels from different perspectives. For intra-image relation modeling, we discover pixel neighbors from multiple views. And for inter-image relations, we enforce pixel representation from the same semantic class to be more similar than the representation from different classes in one mini-batch. Experimental results show that our DSC model outperforms state-of-the-art methods when transferring to downstream dense prediction tasks, including object detection, semantic segmentation, and instance segmentation. Code will be made available.
Few-shot learning aims at rapidly adapting to novel categories with only a handful of samples at test time, which has been predominantly tackled with the idea of meta-learning. However, meta-learning approaches essentially learn across a variety of f
ew-shot tasks and thus still require large-scale training data with fine-grained supervision to derive a generalized model, thereby involving prohibitive annotation cost. In this paper, we advance the few-shot classification paradigm towards a more challenging scenario, i.e., cross-granularity few-shot classification, where the model observes only coarse labels during training while is expected to perform fine-grained classification during testing. This task largely relieves the annotation cost since fine-grained labeling usually requires strong domain-specific expertise. To bridge the cross-granularity gap, we approximate the fine-grained data distribution by greedy clustering of each coarse-class into pseudo-fine-classes according to the similarity of image embeddings. We then propose a meta-embedder that jointly optimizes the visual- and semantic-discrimination, in both instance-wise and coarse class-wise, to obtain a good feature space for this coarse-to-fine pseudo-labeling process. Extensive experiments and ablation studies are conducted to demonstrate the effectiveness and robustness of our approach on three representative datasets.
In this work, we evaluate the use of superpixel pooling layers in deep network architectures for semantic segmentation. Superpixel pooling is a flexible and efficient replacement for other pooling strategies that incorporates spatial prior informatio
n. We propose a simple and efficient GPU-implementation of the layer and explore several designs for the integration of the layer into existing network architectures. We provide experimental results on the IBSR and Cityscapes dataset, demonstrating that superpixel pooling can be leveraged to consistently increase network accuracy with minimal computational overhead. Source code is available at https://github.com/bermanmaxim/superpixPool
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
