Referring expression comprehension (REF) aims at identifying a particular object in a scene by a natural language expression. It requires joint reasoning over the textual and visual domains to solve the problem. Some ...
详细信息
ISBN:
(纸本)9781728171685
Referring expression comprehension (REF) aims at identifying a particular object in a scene by a natural language expression. It requires joint reasoning over the textual and visual domains to solve the problem. Some popular referring expression datasets, however, fail to provide an ideal test bed for evaluating the reasoning ability of the models, mainly because 1) their expressions typically describe only some simple distinctive properties of the object and 2) their images contain limited distracting information. To bridge the gap, we propose a new dataset for visual reasoning in context of referring expression comprehension with two main features. First, we design a novel expression engine rendering various reasoning logics that can be flexibly combined with rich visual properties to generate expressions with varying compositionality. Second, to better exploit the full reasoning chain embodied in an expression, we propose a new test setting by adding additional distracting images containing objects sharing similar properties with the referent, thus minimising the success rate of reasoning-free cross-domain alignment. We evaluate several state-of-the-art REF models, but find none of them can achieve promising performance. A proposed modular hard mining strategy performs the best but still leaves substantial room for improvement. The dataset and code are available at: https://***/ zfchenUnique/Cops- Ref.
3D object detection has attracted much attention thanks to the advances in sensors and deep learning methods for point clouds. Current state-of-the-art methods like VoteNet regress direct offset towards object centers...
详细信息
ISBN:
(数字)9781665469463
ISBN:
(纸本)9781665469463
3D object detection has attracted much attention thanks to the advances in sensors and deep learning methods for point clouds. Current state-of-the-art methods like VoteNet regress direct offset towards object centers and box orientations with an additional Multi-Layer-Perceptron network Both their offset and orientation predictions are not accurate due to the fundamental difficulty in rotation classification. In the work, we disentangle the direct offset into Local Canonical Coordinates (LCC), box scales and box orientations. Only LCC and box scales are regressed, while box orientations are generated by a canonical voting scheme. Finally, an LCC-aware back-projection checking algorithm iteratively cuts out bounding boxes from the generated vote maps, with the elimination of false positives. Our model achieves state-of-the-art performance on three standard real-world benchmarks: ScanNet, SceneNN and SUN RGB-D. Our code is available on hups://***/qq456evb/CanonicalVoting.
Profiting from the advance of deep convolutional networks, current state-of-the-art video action recognition models have achieved remarkable progress. Nevertheless, most of existing models suffer from low interpretabi...
详细信息
ISBN:
(数字)9781665469463
ISBN:
(纸本)9781665469463
Profiting from the advance of deep convolutional networks, current state-of-the-art video action recognition models have achieved remarkable progress. Nevertheless, most of existing models suffer from low interpretability of the predicted actions. Inspired by the observation that temporally-configured human-object interactions often serve as a key indicator of many actions, this work crafts an action reasoning framework that performs Markov Logic Network (MLN) based probabilistic logical inference. Crucially, we propose to encode an action by first-order logical rules that correspond to the temporal changes of visual relationships in videos. The main contributions of this work are two-fold: 1) Different from existing black-box models, the proposed model simultaneously implements the localization of temporal boundaries and the recognition of action categories by grounding the logical rules of MLN in videos. The weight associated with each such rule further provides an estimate of confidence. These collectively make our model more explainable and robust. 2) Instead of using hand-crafted logical rules in conventional MLN, we develop a data-driven instantiation of the MLN. In specific, a hybrid learning scheme is proposed. It combines MLN's weight learning and reinforcement learning, using the former's results as a self-critic for guiding the latter's training. Additionally, by treating actions as logical predicates, the proposed framework can also be integrated with deep models for further performance boost. Comprehensive experiments on two complex video action datasets (Charades & CAD-120) clearly demonstrate the effectiveness and explainability of our proposed method.
This paper presents a grounded language-image pretraining (GLIP) model for learning object-level, language-aware, and semantic-rich visual representations. GLIP unifies object detection and phrase grounding for pre-tr...
详细信息
ISBN:
(数字)9781665469463
ISBN:
(纸本)9781665469463
This paper presents a grounded language-image pretraining (GLIP) model for learning object-level, language-aware, and semantic-rich visual representations. GLIP unifies object detection and phrase grounding for pre-training. The unification brings two benefits: 1) it allows GLIP to learn from both detection and grounding data to improve both tasks and bootstrap a good grounding model;2) GLIP can leverage massive image-text pairs by generating grounding boxes in a self-training fashion, making the learned representations semantic-rich. In our experiments, we pre-train GLIP on 27M grounding data, including 3M human-annotated and 24M web-crawled image-text pairs. The learned representations demonstrate strong zero-shot and few-shot transferability to various object-level recognition tasks. 1) When directly evaluated on COCO and LVIS (without seeing any images in COCO during pre-training), GLIP achieves 49.8 AP and 26.9 AP respectively, surpassing many supervised baselines.(1) 2) After fine-tuned on COCO, GLIP achieves 60.8 AP on val and 61.5 AP on test-dev, surpassing prior SoTA. 3) When transferred to 13 downstream object detection tasks, a 1-shot GLIP rivals with a fully-supervised Dynamic Head. Code will be released at https://***/microsoft/GLIP.
From image-text pairs, large-scale vision-language models (VLMs) learn to implicitly associate image regions with words, which prove effective for tasks like visual question answering. However, leveraging the learned ...
详细信息
ISBN:
(纸本)9798350353013;9798350353006
From image-text pairs, large-scale vision-language models (VLMs) learn to implicitly associate image regions with words, which prove effective for tasks like visual question answering. However, leveraging the learned association for open-vocabulary semantic segmentation remains a challenge. In this paper, we propose a simple, yet extremely effective, training-free technique, Plug-and-Play Open-Vocabulary Semantic Segmentation (PnP-OVSS) for this task. PnP-OVSS leverages a VLM with direct text-to-image cross-attention and an image-text matching loss. To balance between over-segmentation and under-segmentation, we introduce Salience Dropout;by iteratively dropping patches that the model is most attentive to, we are able to better resolve the entire extent of the segmentation mask. PnP-OVSS does not require any neural network training and performs hyperparameter tuning without the need for any segmentation annotations, even for a validation set. PnP-OVSS demonstrates substantial improvements over comparable baselines (+29.4% mIoU on Pascal VOC, +13.2% mIoU on Pascal Context, +14.0% mIoU on MS COCO, +2.4% mIoU on COCO Stuff) and even outperforms most baselines that conduct additional network training on top of pretrained VLMs. Our codebase is at https://***/letitiabanana/PnP-OVSS.
vision-language models (VLMs) have recently shown promising results in traditional downstream tasks. Evaluation studies have emerged to assess their abilities, with the majority focusing on the third-person perspectiv...
详细信息
ISBN:
(纸本)9798350353006
vision-language models (VLMs) have recently shown promising results in traditional downstream tasks. Evaluation studies have emerged to assess their abilities, with the majority focusing on the third-person perspective, and only a few addressing specific tasks from the first-person perspective. However, the capability of VLMs to "think" from a first-person perspective, a crucial attribute for advancing autonomous agents and robotics, remains largely unexplored. To bridge this research gap, we introduce EgoThink, a novel visual question-answering benchmark that encompasses six core capabilities with twelve detailed dimensions. The benchmark is constructed using selected clips from ego-centric videos, with manually annotated question-answer pairs containing first-person information. To comprehensively assess VLMs, we evaluate twenty-one popular VLMs on EgoThink. Moreover, given the open-ended format of the answers, we use GPT-4 as the automatic judge to compute single-answer grading. Experimental results indicate that although GPT-4V leads in numerous dimensions, all evaluated VLMs still possess considerable potential for improvement in first-person perspective tasks. Meanwhile, enlarging the number of trainable parameters has the most significant impact on model performance on EgoThink. In conclusion, EgoThink serves as a valuable addition to existing evaluation benchmarks for VLMs, providing an indispensable resource for future research in the realm of embodied artificial intelligence and robotics.
In this paper, we propose an adversarial learning network for the task of multi-style image captioning (MSCap) with a standard factual image caption dataset and a multi-stylized language corpus without paired images. ...
详细信息
ISBN:
(纸本)9781728132938
In this paper, we propose an adversarial learning network for the task of multi-style image captioning (MSCap) with a standard factual image caption dataset and a multi-stylized language corpus without paired images. How to learn a single model for multi-stylized image captioning with unpaired data is a challenging and necessary task, whereas rarely studied in previous works. The proposed framework mainly includes four contributive modules following a typical image encoder. First, a style dependent caption generator to output a sentence conditioned on an encoded image and a specified style. Second, a caption discriminator is presented to distinguish the input sentence to be real or not. The discriminator and the generator are trained in an adversarial manner to enable more natural and human-like captions. Third, a style classifier is employed to discriminate the specific style of the input sentence. Besides, a back-translation module is designed to enforce the generated stylized captions are visually grounded with the intuition of the cycle consistency for factual caption and stylized caption. We enable an end-to-end optimization of the whole model with differentiable sofiinax *** last, we conduct comprehensive experiments using a combined dataset containing four caption styles to demonstrate the outstanding performance of our proposed method.
Over the past few years, we have witnessed the success of deep learning in image recognition thanks to the availability of large-scale human-annotated datasets such as PAS-CAL VOC, ImageNet, and COCO. Although these d...
详细信息
ISBN:
(纸本)9781728171685
Over the past few years, we have witnessed the success of deep learning in image recognition thanks to the availability of large-scale human-annotated datasets such as PAS-CAL VOC, ImageNet, and COCO. Although these datasets have covered a wide range of object categories, there are still a significant number of objects that are not included. Can we perform the same task without a lot of human annotations? In this paper, we are interested in few-shot object segmentation where the number of annotated training examples are limited to 5 only. To evaluate and validate the performance of our approach, we have built a few-shot segmentation dataset, FSS-1000, which consists of 1000 object classes with pixelwise annotation of ground-truth segmentation. Unique in FSS-1000, our dataset contains significant number of objects that have never been seen or annotated in previous datasets, such as tiny daily objects, merchandise, cartoon characters, logos, etc. We build our baseline model using standard backbone networks such as VGG-16, ResNet-101, and Inception. To our surprise, we found that training our model from scratch using FSS-1000 achieves comparable and even better results than training with weights pre-trained by ImageNet which is more than 100 times larger than FSS-1000. Both our approach and dataset are simple, effective, and easily extensible to learn segmentation of new object classes given very few annotated training examples. Dataset is available at https : //***/HKUSTCV/FSS-1000
Despite the promising progress having been made, the two challenges of multi-view clustering (MVC) are still waiting for better solutions: i) Most existing methods are either not qualified or require additional steps ...
详细信息
ISBN:
(数字)9781665469463
ISBN:
(纸本)9781665469463
Despite the promising progress having been made, the two challenges of multi-view clustering (MVC) are still waiting for better solutions: i) Most existing methods are either not qualified or require additional steps for incomplete multi-view clustering and ii) noise or outliers might significantly degrade the overall clustering performance. In this paper, we propose a novel unified framework for incomplete and complete MVC named multi-view probabilistic clustering (MPC). MPC equivalently transforms multiview pairwise posterior matching probability into composition of each view's individual distribution, which tolerates data missing and might extend to any number of views. Then graph-context-aware refinement with path propagation and co-neighbor propagation is used to refine pairwise probability, which alleviates the impact of noise and outliers. Finally, MPC also equivalently transforms probabilistic clustering's objective to avoid complete pairwise computation and adjusts clustering assignments by maximizing joint probability iteratively. Extensive experiments on multiple benchmarks for incomplete and complete MVC show that MPC significantly outperforms previous state-ofthe-art methods in both effectiveness and efficiency.
In this work, we propose MVFuseNet, a novel end-to-end method for joint object detection and motion forecasting from a temporal sequence of LiDAR data. Most existing methods operate in a single view by projecting data...
详细信息
ISBN:
(纸本)9781665448994
In this work, we propose MVFuseNet, a novel end-to-end method for joint object detection and motion forecasting from a temporal sequence of LiDAR data. Most existing methods operate in a single view by projecting data in either range view (RV) or bird's eye view (BEV). In contrast, we propose a method that effectively utilizes both RV and BEV for spatio-temporal feature learning as part of a temporal fusion network as well as for multi-scale feature learning in the backbone network. Further, we propose a novel sequential fusion approach that effectively utilizes multiple views in the temporal fusion network. We show the benefits of our multi-view approach for the tasks of detection and motion forecasting on two large-scale self-driving data sets, achieving state-of-the-art results. Furthermore, we show that MVFusenet scales well to large operating ranges while maintaining real-time performance.
暂无评论