In this work, we introduce a Denser Feature Network (DenserNet) for visual localization. Our work provides three principal contributions. First, we develop a convolutional neural network (CNN) architecture which aggregates feature maps at different semantic levels for image representations. Using denser feature maps, our method can produce more keypoint features and increase image retrieval accuracy. Second, our model is trained end-to-end without pixel-level annotation other than positive and negative GPS-tagged image pairs. We use a weakly supervised triplet ranking loss to learn discriminative features and encourage keypoint feature repeatability for image representation. Finally, our method is computationally efficient as our architecture has shared features and parameters during computation. Our method can perform accurate large-scale localization under challenging conditions while remaining the computational constraint. Extensive experiment results indicate that our method sets a new state-of-the-art on four challenging large-scale localization benchmarks and three image retrieval benchmarks.
相關內容
從20世紀70年代開始，有關圖像檢索的研究就已開始，當時主要是基于文本的圖像檢索技術（Text-based Image Retrieval，簡稱TBIR），利用文本描述的方式描述圖像的特征，如繪畫作品的作者、年代、流派、尺寸等。到90年代以后，出現了對圖像的內容語義，如圖像的顏色、紋理、布局等進行分析和檢索的圖像檢索技術，即基于內容的圖像檢索（Content-based Image Retrieval，簡稱CBIR）技術。CBIR屬于基于內容檢索（Content-based Retrieval，簡稱CBR）的一種，CBR中還包括對動態視頻、音頻等其它形式多媒體信息的檢索技術。
This work focuses on mitigating two limitations in the joint learning of local feature detectors and descriptors. First, the ability to estimate the local shape (scale, orientation, etc.) of feature points is often neglected during dense feature extraction, while the shape-awareness is crucial to acquire stronger geometric invariance. Second, the localization accuracy of detected keypoints is not sufficient to reliably recover camera geometry, which has become the bottleneck in tasks such as 3D reconstruction. In this paper, we present ASLFeat, with three light-weight yet effective modifications to mitigate above issues. First, we resort to deformable convolutional networks to densely estimate and apply local transformation. Second, we take advantage of the inherent feature hierarchy to restore spatial resolution and low-level details for accurate keypoint localization. Finally, we use a peakiness measurement to relate feature responses and derive more indicative detection scores. The effect of each modification is thoroughly studied, and the evaluation is extensively conducted across a variety of practical scenarios. State-of-the-art results are reported that demonstrate the superiority of our methods.
We present PPF-FoldNet for unsupervised learning of 3D local descriptors on pure point cloud geometry. Based on the folding-based auto-encoding of well known point pair features, PPF-FoldNet offers many desirable properties: it necessitates neither supervision, nor a sensitive local reference frame, benefits from point-set sparsity, is end-to-end, fast, and can extract powerful rotation invariant descriptors. Thanks to a novel feature visualization, its evolution can be monitored to provide interpretable insights. Our extensive experiments demonstrate that despite having six degree-of-freedom invariance and lack of training labels, our network achieves state of the art results in standard benchmark datasets and outperforms its competitors when rotations and varying point densities are present. PPF-FoldNet achieves $9\%$ higher recall on standard benchmarks, $23\%$ higher recall when rotations are introduced into the same datasets and finally, a margin of $>35\%$ is attained when point density is significantly decreased.
Image-level feature descriptors obtained from convolutional neural networks have shown powerful representation capabilities for image retrieval. In this paper, we present an unsupervised method to aggregate deep convolutional features into compact yet discriminative image vectors by simulating the dynamics of heat diffusion. A distinctive problem in image retrieval is that repetitive or bursty features tend to dominate feature representations, leading to less than ideal matches. We show that by leveraging elegant properties of the heat equation, our method is able to avoiding over-representation of bursty features. We additionally present a theoretical time complexity analysis showing the efficiency of our method, which is further demonstrated in our experimental evaluation. Finally, we extensively evaluate the proposed approach with pre-trained and fine-tuned deep networks on common public benchmarks, and show superior performance compared to previous work.
Image-level feature descriptors obtained from convolutional neural networks have shown powerful representation capabilities for image retrieval. In this paper, we present an unsupervised method to aggregate deep convolutional features into compact yet discriminative image vectors by simulating the dynamics of heat diffusion. A distinctive problem in image retrieval is that repetitive or bursty features tend to dominate feature representations, leading to less than ideal matches. We show that by leveraging elegant properties of the heat equation, our method is able to select informative features while avoiding over-representation of bursty features. We additionally present a theoretical time complexity analysis showing the efficiency of our method, which is further demonstrated in our experimental evaluation. Finally, we extensively evaluate the proposed approach with pre-trained and fine-tuned deep networks on common public benchmarks, and show superior performance compared to previous work.
Weakly supervised instance segmentation with image-level labels, instead of expensive pixel-level masks, remains unexplored. In this paper, we tackle this challenging problem by exploiting class peak responses to enable a classification network for instance mask extraction. With image labels supervision only, CNN classifiers in a fully convolutional manner can produce class response maps, which specify classification confidence at each image location. We observed that local maximums, i.e., peaks, in a class response map typically correspond to strong visual cues residing inside each instance. Motivated by this, we first design a process to stimulate peaks to emerge from a class response map. The emerged peaks are then back-propagated and effectively mapped to highly informative regions of each object instance, such as instance boundaries. We refer to the above maps generated from class peak responses as Peak Response Maps (PRMs). PRMs provide a fine-detailed instance-level representation, which allows instance masks to be extracted even with some off-the-shelf methods. To the best of our knowledge, we for the first time report results for the challenging image-level supervised instance segmentation task. Extensive experiments show that our method also boosts weakly supervised pointwise localization as well as semantic segmentation performance, and reports state-of-the-art results on popular benchmarks, including PASCAL VOC 2012 and MS COCO.
In this paper, we propose a simple but effective semantic-based aggregation (SBA) method. The proposed SBA utilizes the discriminative filters of deep convolutional layers as semantic detectors. Moreover, we propose the effective unsupervised strategy to select some semantic detectors to generate the "probabilistic proposals", which highlight certain discriminative pattern of objects and suppress the noise of background. The final global SBA representation could then be acquired by aggregating the regional representations weighted by the selected "probabilistic proposals" corresponding to various semantic content. Our unsupervised SBA is easy to generalize and achieves excellent performance on various tasks. We conduct comprehensive experiments and show that our unsupervised SBA outperforms the state-of-the-art unsupervised and supervised aggregation methods on image retrieval, place recognition and cloud classification.
This paper introduces an online model for object detection in videos designed to run in real-time on low-powered mobile and embedded devices. Our approach combines fast single-image object detection with convolutional long short term memory (LSTM) layers to create an interweaved recurrent-convolutional architecture. Additionally, we propose an efficient Bottleneck-LSTM layer that significantly reduces computational cost compared to regular LSTMs. Our network achieves temporal awareness by using Bottleneck-LSTMs to refine and propagate feature maps across frames. This approach is substantially faster than existing detection methods in video, outperforming the fastest single-frame models in model size and computational cost while attaining accuracy comparable to much more expensive single-frame models on the Imagenet VID 2015 dataset. Our model reaches a real-time inference speed of up to 15 FPS on a mobile CPU.
In the same vein of discriminative one-shot learning, Siamese networks allow recognizing an object from a single exemplar with the same class label. However, they do not take advantage of the underlying structure of the data and the relationship among the multitude of samples as they only rely on pairs of instances for training. In this paper, we propose a new quadruplet deep network to examine the potential connections among the training instances, aiming to achieve a more powerful representation. We design four shared networks that receive multi-tuple of instances as inputs and are connected by a novel loss function consisting of pair-loss and triplet-loss. According to the similarity metric, we select the most similar and the most dissimilar instances as the positive and negative inputs of triplet loss from each multi-tuple. We show that this scheme improves the training performance. Furthermore, we introduce a new weight layer to automatically select suitable combination weights, which will avoid the conflict between triplet and pair loss leading to worse performance. We evaluate our quadruplet framework by model-free tracking-by-detection of objects from a single initial exemplar in several Visual Object Tracking benchmarks. Our extensive experimental analysis demonstrates that our tracker achieves superior performance with a real-time processing speed of 78 frames-per-second (fps).
In this paper we propose an effective non-rigid object tracking method based on spatial-temporal consistent saliency detection. In contrast to most existing trackers that use a bounding box to specify the tracked target, the proposed method can extract the accurate regions of the target as tracking output, which achieves better description of the non-rigid objects while reduces background pollution to the target model. Furthermore, our model has several unique features. First, a tailored deep fully convolutional neural network (TFCN) is developed to model the local saliency prior for a given image region, which not only provides the pixel-wise outputs but also integrates the semantic information. Second, a multi-scale multi-region mechanism is proposed to generate local region saliency maps that effectively consider visual perceptions with different spatial layouts and scale variations. Subsequently, these saliency maps are fused via a weighted entropy method, resulting in a final discriminative saliency map. Finally, we present a non-rigid object tracking algorithm based on the proposed saliency detection method by utilizing a spatial-temporal consistent saliency map (STCSM) model to conduct target-background classification and using a simple fine-tuning scheme for online updating. Numerous experimental results demonstrate that the proposed algorithm achieves competitive performance in comparison with state-of-the-art methods for both saliency detection and visual tracking, especially outperforming other related trackers on the non-rigid object tracking datasets.
In this work a novel approach for weakly supervised object detection that incorporates pointwise mutual information is presented. A fully convolutional neural network architecture is applied in which the network learns one filter per object class. The resulting feature map indicates the location of objects in an image, yielding an intuitive representation of a class activation map. While traditionally such networks are learned by a softmax or binary logistic regression (sigmoid cross-entropy loss), a learning approach based on a cosine loss is introduced. A pointwise mutual information layer is incorporated in the network in order to project predictions and ground truth presence labels in a non-categorical embedding space. Thus, the cosine loss can be employed in this non-categorical representation. Besides integrating image level annotations, it is shown how to integrate point-wise annotations using a Spatial Pyramid Pooling layer. The approach is evaluated on the VOC2012 dataset for classification, point localization and weakly supervised bounding box localization. It is shown that the combination of pointwise mutual information and a cosine loss eases the learning process and thus improves the accuracy. The integration of coarse point-wise localizations further improves the results at minimal annotation costs.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191